instruction
stringlengths 999
2.35k
| input
stringlengths 341
562
| output
dict |
|---|---|---|
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['filing_cabinet', 'shoe_rack', 'food_salt', 'mop', 'microwave', 'dog', 'jelly', 'walllamp', 'drawing', 'needle', 'food_egg', 'desk', 'stamp', 'computer', 'ceilinglamp', 'window', 'mousepad', 'food_orange', 'pillow', 'bench', 'cup', 'oven_mitts', 'wooden_spoon', 'pencil', 'dresser', 'maindoor', 'bag', 'table', 'instrument_violin', 'creditcard']
Task:Listen to music
response:
{
"thoughts": go to radio. run on radio.,
"actions": ['[WALK] <stereo>', '[SWITCHON] <stereo>']
}
|
Scene_Objects:['sponge', 'pot', 'scissors', 'tea', 'freezer', 'walllamp', 'wallshelf', 'hanger', 'kitchen_cabinet', 'floor', 'bathroom_counter', 'bedroom', 'bookshelf', 'ceilinglamp', 'dish_soap', 'dining_room', 'nightstand', 'wall_clock', 'bed', 'curtain', 'doorjamb', 'towel_rack', 'dresser', 'door', 'clothes_scarf', 'bathtub', 'light', 'dishwasher', 'table', 'shoe_rack']
Task:Wash dishes with dishwasher
response:
| {
"thoughts": "I walk to the kitchen. I open the dishwasher. I open the kitchen cabinet. I reach inside the cabinet and grab the box of dish soap. I add some soap to the open dishwasher. I put the box of dish soap back in the kitchen cabinet. I close the kitchen cabinet and then I close the dishwasher. I turn the dishwasher on and wait.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <dishwasher>",
"[FIND] <dishwasher>",
"[OPEN] <dishwasher>",
"[FIND] <kitchen_cabinet>",
"[OPEN] <kitchen_cabinet>",
"[FIND] <dish_soap>",
"[GRAB] <dish_soap>",
"[PUTBACK] <dish_soap> <dishwasher>",
"[GRAB] <dish_soap>",
"[PUTIN] <dish_soap> <kitchen_cabinet>",
"[CLOSE] <kitchen_cabinet>",
"[CLOSE] <dishwasher>",
"[SWITCHON] <dishwasher>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tablelamp', 'chair', 'ground_coffee', 'walllamp', 'food_carrot', 'orchid', 'drawing', 'floor', 'ceiling', 'bedroom', 'bookshelf', 'keyboard', 'mail', 'mat', 'faucet', 'wall', 'nightstand', 'powersocket', 'oven', 'cup', 'photoframe', 'bed', 'novel', 'curtain', 'doorjamb', 'diary', 'cupboard', 'door', 'sink', 'instrument_guitar']
Task:Read book
response:
{
"thoughts": Walk over to the bookshelf. Pick storybook off the shelf. Sit on bed. Open storybook and read out loud.,
"actions": ['[WALK] <bedroom>', '[WALK] <bookshelf>', '[FIND] <novel>', '[GRAB] <novel>', '[TURNTO] <novel>', '[LOOKAT] <novel>', '[WALK] <bed>', '[SIT] <bed>', '[READ] <novel>']
}
|
Scene_Objects:['filing_cabinet', 'toilet', 'freezer', 'walllamp', 'drawing', 'floor', 'ceiling', 'computer', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'pillow', 'wall', 'wall_clock', 'powersocket', 'oven', 'box', 'television', 'ice', 'curtain', 'pencil', 'kitchen_counter', 'door', 'hairdryer', 'instrument_guitar', 'table']
Task:Relax on sofa
response:
| {
"thoughts": "allow sofa to support weight in order to decrease gravity induced entropy",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[FIND] <couch>",
"[WALK] <couch>",
"[SIT] <couch>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['fork', 'pot', 'filing_cabinet', 'tablelamp', 'blender', 'beer', 'toilet', 'jelly', 'freezer', 'blow_dryer', 'detergent', 'orchid', 'knifeblock', 'wallshelf', 'cpuscreen', 'bathroom_counter', 'floor', 'mail', 'computer', 'bookmark', 'stereo', 'window', 'couch', 'microphone', 'check', 'television', 'rag', 'pencil', 'controller', 'dishwasher']
Task:Pet cat
response:
{
"thoughts": Pet Cat,
"actions": ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[WALK] <cat>', '[TURNTO] <cat>', '[LOOKAT] <cat>', '[TOUCH] <cat>']
}
|
Scene_Objects:['food_bread', 'filing_cabinet', 'tablelamp', 'food_salt', 'toilet', 'chair', 'bathroom', 'trashcan', 'drawing', 'floor', 'character', 'desk', 'purse', 'computer', 'table_cloth', 'stovefan', 'ceilinglamp', 'tvstand', 'shower', 'foundation', 'couch', 'pillow', 'nightstand', 'powersocket', 'novel', 'tray', 'mouse', 'bathroom_cabinet', 'soap', 'teeth']
Task:Pet cat
response:
| {
"thoughts": "First I need to find the cat in the living room. Then I walk over to the cat and pet it gently.",
"actions": [
"[WALK] <home_office>",
"[WALK] <cat>",
"[FIND] <cat>",
"[WALK] <cat>",
"[TOUCH] <cat>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sheets', 'pot', 'tablelamp', 'microwave', 'detergent', 'clothes_underwear', 'ceiling', 'character', 'desk', 'mail', 'table_cloth', 'bookmark', 'shoe-shine_kit', 'faucet', 'electric_shaver', 'mousepad', 'candle', 'food_jam', 'food_orange', 'nightstand', 'powersocket', 'newspaper', 'coin', 'food_onion', 'pencil', 'dresser', 'home_office', 'dishwasher', 'tooth_paste', 'coffee']
Task:Browse internet
response:
{
"thoughts": The task is browse and surf on the internet regarding a particular topic,
"actions": ['[WALK] <bedroom>', '[WALK] <laptop>', '[FIND] <laptop>', '[SWITCHON] <laptop>', '[TURNTO] <laptop>', '[LOOKAT] <laptop>', '[WATCH] <laptop>']
}
|
Scene_Objects:['tablelamp', 'crayon', 'chair', 'walllamp', 'toothbrush', 'wallshelf', 'dvd_player', 'keyboard', 'bookshelf', 'computer', 'alcohol', 'mousepad', 'couch', 'form', 'pillow', 'bowl', 'nightstand', 'wall_clock', 'bench', 'oven', 'powersocket', 'clothes_gloves', 'doorjamb', 'mouse', 'kitchen_counter', 'dresser', 'hairdryer', 'bathtub', 'home_office', 'table']
Task:Write an email
response:
| {
"thoughts": "I go to my bed room and sit on the chair and in front of me is my desktop computer and start writing an email.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <chair>",
"[FIND] <chair>",
"[SIT] <chair>",
"[FIND] <computer>",
"[SWITCHON] <computer>",
"[TURNTO] <computer>",
"[LOOKAT] <computer>",
"[FIND] <keyboard>",
"[TYPE] <keyboard>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sponge', 'band-aids', 'toothbrush', 'orchid', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'toaster', 'faucet', 'picture', 'shower', 'mousepad', 'candle', 'food_orange', 'oven', 'basket_for_clothes', 'bed', 'check', 'food_food', 'television', 'tray', 'after_shave', 'headset', 'comb', 'dresser', 'laundry_detergent', 'napkin', 'bathroom_cabinet']
Task:Sit in chair
response:
{
"thoughts": I sit in a chair to rest and eat.,
"actions": ['[WALK] <dining_room>', '[WALK] <chair>', '[FIND] <chair>', '[PULL] <chair>', '[SIT] <chair>']
}
|
Scene_Objects:['sheets', 'filing_cabinet', 'tablelamp', 'tea', 'trashcan', 'drawing', 'orchid', 'floor', 'character', 'desk', 'bookshelf', 'computer', 'toaster', 'mat', 'stovefan', 'tvstand', 'window', 'mousepad', 'couch', 'wall', 'nightstand', 'wall_clock', 'cup', 'bed', 'food_donut', 'curtain', 'towel_rack', 'sink', 'napkin', 'bathtub']
Task:Go to sleep
response:
| {
"thoughts": "Enter bedroom, turn on the light, and shut door. Change into night clothes. Turn off light. Turn down comforter, climb into bed, lay head on pillow, and cover up with comforter. Close eyes and drift off to sleep.",
"actions": [
"[WALK] <bedroom>",
"[WALK] <bed>",
"[FIND] <bed>",
"[LIE] <bed>",
"[FIND] <sheets>",
"[PULL] <sheets>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'picture', 'homework', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'keys', 'check', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'door', 'light']
Task:Work
response:
{
"thoughts": walk to Office,Walk to desk ,sit down in chair, turn on computer, start homework.,
"actions": ['[WALK] <home_office>', '[WALK] <desk>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <check>', '[FIND] <homework>', '[TURNTO] <homework>', '[LOOKAT] <homework>']
}
|
Scene_Objects:['spectacles', 'pot', 'band-aids', 'walllamp', 'drawing', 'wallshelf', 'floor', 'character', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'window', 'couch', 'clothes_pants', 'pillow', 'dining_room', 'wall', 'bench', 'photoframe', 'television', 'tray', 'curtain', 'kitchen_counter', 'shoes', 'cupboard', 'clothes_dress', 'home_office', 'table', 'clothes_shirt']
Task:Relax on sofa
response:
| {
"thoughts": "Sitting down and relaxing on the sofa",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[FIND] <couch>",
"[SIT] <couch>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'tablelamp', 'freezer', 'blow_dryer', 'ceilingfan', 'drawing', 'floor', 'ceiling', 'bedroom', 'remote_control', 'ceilinglamp', 'tvstand', 'balanceball', 'stereo', 'window', 'shoe-shine_kit', 'couch', 'microphone', 'food_jam', 'wall', 'coffe_maker', 'check', 'television', 'curtain', 'sink', 'napkin', 'bathroom_cabinet', 'table', 'colander', 'tooth_paste']
Task:Watch TV
response:
{
"thoughts": Walk to the living room. Find the television. Walk to the television. Switch on the television. Find the sofa. Walk to the sofa. Sit on the sofa. Find the remote control. Grab the remote control. Look at the television.,
"actions": ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[WALK] <television>', '[SWITCHON] <television>', '[FIND] <couch>', '[WALK] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[TURNTO] <television>', '[LOOKAT] <television>']
}
|
Scene_Objects:['tablelamp', 'chair', 'freezer', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'character', 'desk', 'bedroom', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'faucet', 'closetdrawer', 'pillow', 'dining_room', 'wall', 'nightstand', 'powersocket', 'oven', 'television', 'doorjamb', 'mouse', 'door', 'sink', 'light', 'instrument_violin']
Task:Turn on light
response:
| {
"thoughts": "I enter the bedroom and find the light. Then I turn it on.",
"actions": [
"[WALK] <bedroom>",
"[WALK] <light>",
"[FIND] <light>",
"[SWITCHON] <light>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['crayon', 'microwave', 'toilet', 'freezer', 'ground_coffee', 'longboard', 'shampoo', 'character', 'thread', 'food_bacon', 'piano_bench', 'balanceball', 'stereo', 'window', 'picture', 'mousepad', 'pillow', 'toy', 'basket_for_clothes', 'photoframe', 'novel', 'coffe_maker', 'oven_mitts', 'colander', 'doorjamb', 'shaving_cream', 'dresser', 'soap', 'washing_machine', 'creditcard']
Task:Wash clothes
response:
{
"thoughts": walk to the bathroom, grab the basket for clothes, find soap, put in washing machine, turn on,
"actions": ['[WALK] <bathroom>', '[WALK] <basket_for_clothes>', '[FIND] <basket_for_clothes>', '[GRAB] <basket_for_clothes>', '[WALK] <washing_machine>', '[OPEN] <washing_machine>', '[PUTBACK] <basket_for_clothes> <washing_machine>', '[FIND] <soap>', '[GRAB] <soap>', '[WALK] <washing_machine>', '[PUTBACK] <soap> <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>']
}
|
Scene_Objects:['microwave', 'toilet', 'chair', 'walllamp', 'trashcan', 'cpuscreen', 'wallshelf', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'keyboard', 'tvstand', 'faucet', 'mousepad', 'closetdrawer', 'couch', 'food_jam', 'wall', 'nightstand', 'oven', 'newspaper', 'food_food', 'vacuum_cleaner', 'sink', 'bathtub', 'bathroom_cabinet', 'light', 'table', 'hands_both']
Task:Wash hands
response:
| {
"thoughts": "I go to the bathroom, walk to the sink, turn on the faucet and then wash my hands under the water.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <sink>",
"[FIND] <faucet>",
"[TURNTO] <faucet>",
"[FIND] <hands_both>",
"[WASH] <hands_both>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'filing_cabinet', 'band-aids', 'freezer', 'nail_polish', 'bathroom', 'cat', 'orchid', 'cpuscreen', 'phone', 'character', 'keyboard', 'mat', 'faucet', 'wall', 'oven', 'bed', 'keys', 'coffe_maker', 'mouthwash', 'food_onion', 'curtain', 'centerpiece', 'console', 'towel_rack', 'kitchen_counter', 'dresser', 'cupboard', 'door', 'home_office']
Task:Pet cat
response:
{
"thoughts": First I need to find the cat in the living room. Then I walk over to the cat and pet it gently.,
"actions": ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[WALK] <cat>', '[TOUCH] <cat>']
}
|
Scene_Objects:['sheets', 'scissors', 'milk', 'wallshelf', 'cpuscreen', 'hanger', 'phone', 'bedroom', 'bookshelf', 'keyboard', 'table_cloth', 'stovefan', 'tvstand', 'window', 'closetdrawer', 'candle', 'dining_room', 'wall_clock', 'oven', 'bench', 'photoframe', 'television', 'tray', 'kitchen_counter', 'door', 'bathtub', 'sink', 'table', 'soap', 'creditcard']
Task:Listen to music
response:
| {
"thoughts": "Listen to music",
"actions": [
"[WALK] <home_office>",
"[WALK] <stereo>",
"[FIND] <stereo>",
"[SWITCHON] <stereo>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tablelamp', 'microwave', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'mat', 'plate', 'faucet', 'tvstand', 'clothes_hat', 'pillow', 'wall', 'oven', 'powersocket', 'newspaper', 'photoframe', 'check', 'coffe_maker', 'doorjamb', 'kitchen_counter', 'dishrack', 'cupboard', 'door', 'sink', 'clothes_scarf', 'table', 'clothes_skirt', 'dishwasher']
Task:Wash dishes by hand
response:
{
"thoughts": Walking towards sink and look at the leftover plates. Scrape dishes to remove leftover food - use a rubber spatula or paper towel. Fill sink or dishpan with clean, hot water. Then wash and rinse to removing residues. Finally leave it to dry.,
"actions": ['[WALK] <dining_room>', '[WALK] <kitchen_counter>', '[FIND] <plate>', '[TURNTO] <plate>', '[LOOKAT] <plate>', '[GRAB] <plate>', '[SCRUB] <plate>', '[RINSE] <plate>', '[WASH] <plate>', '[PUTBACK] <plate> <kitchen_counter>']
}
|
Scene_Objects:['food_pizza', 'filing_cabinet', 'tablelamp', 'microwave', 'chair', 'freezer', 'walllamp', 'bathroom', 'trashcan', 'drawing', 'cpuscreen', 'floor', 'phone', 'bedroom', 'bookshelf', 'mat', 'tvstand', 'ceilinglamp', 'faucet', 'window', 'couch', 'pillow', 'wall', 'photoframe', 'television', 'curtain', 'rag', 'cupboard', 'table', 'colander']
Task:Relax on sofa
response:
| {
"thoughts": "I go to the living room and sit in the sofa",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[FIND] <couch>",
"[WALK] <couch>",
"[SIT] <couch>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['food_pizza', 'tablelamp', 'chair', 'freezer', 'detergent', 'bathroom_counter', 'desk', 'bedroom', 'keyboard', 'button', 'stovefan', 'ceilinglamp', 'stereo', 'shower', 'window', 'clothes_socks', 'dining_room', 'nightstand', 'wall', 'bench', 'oven', 'powersocket', 'bed', 'television', 'curtain', 'doorjamb', 'dresser', 'napkin', 'bathroom_cabinet', 'soap']
Task:Listen to music
response:
{
"thoughts": Walk into living room, look for radio, grab on button,
"actions": ['[WALK] <home_office>', '[WALK] <stereo>', '[FIND] <stereo>', '[TURNTO] <stereo>', '[LOOKAT] <stereo>', '[FIND] <button>', '[GRAB] <button>']
}
|
Scene_Objects:['microwave', 'chair', 'dog', 'walllamp', 'trashcan', 'cpuscreen', 'floor', 'ceiling', 'desk', 'bedroom', 'keyboard', 'computer', 'table_cloth', 'ceilinglamp', 'tvstand', 'faucet', 'mousepad', 'couch', 'form', 'wall', 'powersocket', 'photoframe', 'mouthwash', 'television', 'doorjamb', 'mouse', 'cupboard', 'bathtub', 'sink', 'table']
Task:Work
response:
| {
"thoughts": "go to home office. turn the computer on. begin working",
"actions": [
"[WALK] <home_office>",
"[WALK] <computer>",
"[FIND] <computer>",
"[SWITCHON] <computer>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tablelamp', 'measuring_cup', 'chair', 'orchid', 'drawing', 'cpuscreen', 'wallshelf', 'floor', 'ceiling', 'desk', 'tea_bag', 'keyboard', 'bookshelf', 'computer', 'alcohol', 'stovefan', 'mat', 'ceilinglamp', 'tvstand', 'stereo', 'floor_lamp', 'mousepad', 'wall', 'nightstand', 'novel', 'video_game_controller', 'television', 'mouse', 'door', 'napkin']
Task:Study
response:
{
"thoughts": Study norwegian,
"actions": ['[WALK] <home_office>', '[WALK] <floor_lamp>', '[FIND] <floor_lamp>', '[SWITCHON] <floor_lamp>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <chair>', '[SIT] <chair>', '[READ] <novel>']
}
|
Scene_Objects:['chair', 'freezer', 'walllamp', 'drawing', 'wallshelf', 'floor', 'character', 'keyboard', 'bookshelf', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'window', 'closetdrawer', 'couch', 'pillow', 'wall', 'nightstand', 'powersocket', 'wall_clock', 'toilet_paper', 'mouthwash', 'television', 'food_food', 'coffe_maker', 'curtain', 'doorjamb', 'bathroom_cabinet', 'table']
Task:Relax on sofa
response:
| {
"thoughts": "walk to living room, find sofa, sit in sofa",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[FIND] <couch>",
"[WALK] <couch>",
"[SIT] <couch>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'tablelamp', 'freezer', 'walllamp', 'food_carrot', 'desk', 'food_cake', 'remote_control', 'button', 'ceilinglamp', 'faucet', 'stereo', 'window', 'mousepad', 'couch', 'wall_clock', 'bench', 'box', 'cup', 'bed', 'keys', 'newspaper', 'food_food', 'ice', 'after_shave', 'maindoor', 'bathroom_cabinet', 'light', 'vase', 'soap']
Task:Watch TV
response:
{
"thoughts": I walk to the living room and sit on the couch. I grab the TV remote. I press the power button on the TV remote and the TV turns on. I grab the surround sound remote. I press the power button on the surround sound remote and the system turns on.,
"actions": ['[WALK] <home_office>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[PUSH] <remote_control>', '[FIND] <remote_control>', '[PUSH] <remote_control>']
}
|
Scene_Objects:['filing_cabinet', 'chair', 'walllamp', 'bathroom', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'bedroom', 'keyboard', 'bookshelf', 'computer', 'alcohol', 'stovefan', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'wall', 'powersocket', 'food_food', 'television', 'curtain', 'doorjamb', 'mouse', 'cupboard', 'door', 'bathroom_cabinet', 'table']
Task:Browse internet
response:
| {
"thoughts": "Turn on computer, pull up browser, browse the internet",
"actions": [
"[WALK] <home_office>",
"[WALK] <computer>",
"[FIND] <computer>",
"[SWITCHON] <computer>",
"[TURNTO] <computer>",
"[LOOKAT] <computer>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sheets', 'spectacles', 'glue', 'jelly', 'freezer', 'detergent', 'food_carrot', 'orchid', 'clothes_underwear', 'hanger', 'floor', 'bedroom', 'thread', 'bookmark', 'mat', 'stereo', 'shower', 'mousepad', 'oil', 'nightstand', 'light_bulb', 'coffe_maker', 'television', 'tray', 'pencil', 'shoes', 'bathroom_cabinet', 'dishwasher', 'colander', 'dirt']
Task:Pick up phone
response:
{
"thoughts": Go to the living room. Find the telephone. Lift up the receiver.,
"actions": ['[WALK] <home_office>', '[WALK] <phone>', '[FIND] <phone>', '[GRAB] <phone>']
}
|
Scene_Objects:['tablelamp', 'chair', 'walllamp', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'brush', 'ceilinglamp', 'tvstand', 'faucet', 'mousepad', 'wall', 'powersocket', 'bench', 'coffe_maker', 'mouthwash', 'television', 'curtain', 'doorjamb', 'towel_rack', 'mouse', 'kettle', 'cupboard', 'sink', 'table']
Task:Browse internet
response:
| {
"thoughts": "first i will walk into my home office and i needed to know the today's gold prices so wih the help of keyboard and mouse i will browse and find it",
"actions": [
"[WALK] <home_office>",
"[WALK] <chair>",
"[FIND] <chair>",
"[SIT] <chair>",
"[FIND] <keyboard>",
"[GRAB] <keyboard>",
"[FIND] <mouse>",
"[GRAB] <mouse>",
"[FIND] <computer>",
"[SWITCHON] <computer>",
"[TYPE] <keyboard>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'filing_cabinet', 'toilet', 'chair', 'walllamp', 'ground_coffee', 'orchid', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'bookshelf', 'stovefan', 'tvstand', 'faucet', 'shower', 'electric_shaver', 'towel', 'wall', 'wall_clock', 'oven', 'television', 'tray', 'rag', 'doorjamb', 'dresser', 'sink', 'bathroom_cabinet', 'clothes_skirt', 'laser_pointer']
Task:Take shower
response:
{
"thoughts": Walk to Bathroom. Open the Bathroom Cabinet. Grab a Towel. Close the Bathroom Cabinet. Rinse the Shower.,
"actions": ['[WALK] <bathroom>', '[WALK] <bathroom_cabinet>', '[FIND] <bathroom_cabinet>', '[OPEN] <bathroom_cabinet>', '[FIND] <towel>', '[GRAB] <towel>', '[CLOSE] <bathroom_cabinet>', '[FIND] <shower>', '[RINSE] <shower>']
}
|
Scene_Objects:['spectacles', 'tablelamp', 'walllamp', 'nail_polish', 'orchid', 'cpuscreen', 'phone', 'folder', 'bedroom', 'desk', 'keyboard', 'ceilinglamp', 'tvstand', 'faucet', 'shower', 'floor_lamp', 'iron', 'mousepad', 'couch', 'powersocket', 'photoframe', 'coffe_maker', 'curtain', 'towel_rack', 'pencil', 'cupboard', 'bathtub', 'napkin', 'light', 'soap']
Task:Turn on light
response:
| {
"thoughts": "Walk to the living room, walk to the lamp, switch on the lamp.",
"actions": [
"[WALK] <home_office>",
"[WALK] <floor_lamp>",
"[SWITCHON] <floor_lamp>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['fork', 'filing_cabinet', 'juice', 'food_ice_cream', 'bathroom', 'orchid', 'floor', 'ceiling', 'phone', 'shampoo', 'bookshelf', 'tvstand', 'stereo', 'shower', 'couch', 'wall', 'wall_clock', 'powersocket', 'oven', 'photoframe', 'food_food', 'television', 'after_shave', 'doorjamb', 'mouse', 'dresser', 'controller', 'home_office', 'light', 'coffee']
Task:Pick up phone
response:
{
"thoughts": first i will go to home office and switch on the lights and answer the call after then i will put back it and switch off the lights and close the door,
"actions": ['[RUN] <home_office>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>', '[FIND] <phone>', '[GRAB] <phone>', '[PUTOBJBACK] <phone>', '[SWITCHOFF] <light>']
}
|
Scene_Objects:['toilet', 'walllamp', 'bathroom', 'drawing', 'cpuscreen', 'floor', 'dvd_player', 'desk', 'bedroom', 'bookshelf', 'computer', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'window', 'closetdrawer', 'couch', 'pillow', 'wall', 'nightstand', 'television', 'tray', 'curtain', 'controller', 'sink', 'bathroom_cabinet', 'table', 'home_office', 'light']
Task:Listen to music
response:
| {
"thoughts": "walk to living room, look at the DVD player, switch on the dvd player, look at the sofa, sit on the sofa and listen the music",
"actions": [
"[WALK] <home_office>",
"[WALK] <dvd_player>",
"[FIND] <dvd_player>",
"[TURNTO] <dvd_player>",
"[LOOKAT] <dvd_player>",
"[SWITCHON] <dvd_player>",
"[FIND] <couch>",
"[TURNTO] <couch>",
"[LOOKAT] <couch>",
"[SIT] <couch>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['cat', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'character', 'stovefan', 'mat', 'ceilinglamp', 'faucet', 'iron', 'towel', 'wall', 'wall_clock', 'oven', 'nightstand', 'tape', 'novel', 'food_food', 'television', 'tray', 'mouse', 'sink', 'bathtub', 'bathroom_cabinet', 'light', 'vase', 'soap', 'hands_both']
Task:Wash hands
response:
{
"thoughts": I go into the bathroom, get my hands wet, add soap, suds up my hands, rinse the soap off, turn the faucet off, dry my hands.,
"actions": ['[WALK] <bathroom>', '[WALK] <faucet>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <hands_both>', '[RINSE] <hands_both>', '[FIND] <soap>', '[GRAB] <soap>', '[SCRUB] <soap>', '[PUTOBJBACK] <soap>', '[SCRUB] <hands_both>', '[RINSE] <hands_both>', '[SWITCHOFF] <faucet>', '[FIND] <towel>', '[GRAB] <towel>', '[WIPE] <hands_both>', '[PUTOBJBACK] <towel>']
}
|
Scene_Objects:['glue', 'filing_cabinet', 'tablelamp', 'food_salt', 'ground_coffee', 'drawing', 'cpuscreen', 'wallshelf', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'food_cake', 'ceilinglamp', 'mat', 'stereo', 'window', 'clothes_socks', 'wall', 'bench', 'cup', 'bed', 'coffe_maker', 'tray', 'curtain', 'doorjamb', 'kitchen_counter', 'light', 'table']
Task:Turn on light
response:
| {
"thoughts": "I walk in to the living room. I find the light switch. I turn on the lights.",
"actions": [
"[WALK] <home_office>",
"[WALK] <light>",
"[FIND] <light>",
"[SWITCHON] <light>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['filing_cabinet', 'microwave', 'band-aids', 'drawing', 'longboard', 'floor', 'ceiling', 'folder', 'computer', 'clothes_jacket', 'alcohol', 'ceilinglamp', 'balanceball', 'window', 'foundation', 'couch', 'food_peanut_butter', 'wall', 'powersocket', 'oven', 'television', 'wine', 'towel_rack', 'pencil', 'shoes', 'dresser', 'cupboard', 'table', 'light', 'dishwasher']
Task:Arrange furniture
response:
{
"thoughts": Move furniture where you want it.,
"actions": ['[WALK] <home_office>', '[WALK] <coffee_table>', '[PUSH] <coffee_table>', '[WALK] <couch>', '[PUSH] <couch>', '[WALK] <couch>', '[PUSH] <couch>', '[WALK] <filing_cabinet>', '[PUSH] <filing_cabinet>']
}
|
Scene_Objects:['fork', 'filing_cabinet', 'food_salt', 'toilet', 'bills', 'hanger', 'bathroom_counter', 'floor', 'character', 'stovefan', 'tvstand', 'faucet', 'mousepad', 'towel', 'dining_room', 'wall', 'cup', 'bed', 'photoframe', 'check', 'coffe_maker', 'water', 'tray', 'curtain', 'doorjamb', 'sink', 'bathroom_cabinet', 'table', 'soap', 'hands_both']
Task:Wash hands
response:
| {
"thoughts": "Walk to bathroom. Walk to sink and turn on the water. Grab the soap and wash the hands.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <sink>",
"[FIND] <water>",
"[TURNTO] <water>",
"[FIND] <soap>",
"[GRAB] <soap>",
"[FIND] <hands_both>",
"[WASH] <hands_both>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['measuring_cup', 'microwave', 'toilet', 'jelly', 'walllamp', 'trashcan', 'knifeblock', 'knife', 'desk', 'keyboard', 'computer', 'button', 'brush', 'window', 'mousepad', 'couch', 'bench', 'cutting_board', 'novel', 'check', 'coffe_maker', 'television', 'toothbrush_holder', 'food_rice', 'curtain', 'headset', 'dresser', 'home_office', 'table', 'dishwasher']
Task:Lock door
response:
{
"thoughts": Turn the lock.,
"actions": ['[WALK] <bedroom>']
}
|
Scene_Objects:['toilet', 'walllamp', 'bathroom', 'orchid', 'drawing', 'cpuscreen', 'hanger', 'floor', 'folder', 'bedroom', 'computer', 'stovefan', 'window', 'closetdrawer', 'powersocket', 'basket_for_clothes', 'clothes_gloves', 'food_food', 'doorjamb', 'kettle', 'mouse', 'shoes', 'dresser', 'cupboard', 'sink', 'home_office', 'table', 'light', 'soap', 'washing_machine']
Task:Wash clothes
response:
| {
"thoughts": "Get dirty clothes out of basket for clothes in bedroom, carry dirty clothes to laundry room, place dirty clothes in washing machine, add laundry detergent to washing machine, turn washing machine on, set type of wash, start washing machine",
"actions": [
"[WALK] <bedroom>",
"[WALK] <basket_for_clothes>",
"[FIND] <basket_for_clothes>",
"[OPEN] <basket_for_clothes>",
"[GRAB] <basket_for_clothes>",
"[WALK] <bathroom>",
"[WALK] <washing_machine>",
"[FIND] <washing_machine>",
"[OPEN] <washing_machine>",
"[PUTBACK] <basket_for_clothes> <washing_machine>",
"[FIND] <soap>",
"[GRAB] <soap>",
"[PUTBACK] <soap> <washing_machine>",
"[FIND] <washing_machine>",
"[CLOSE] <washing_machine>",
"[SWITCHON] <washing_machine>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['toilet', 'chair', 'walllamp', 'bathroom', 'wallshelf', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'envelope', 'computer', 'mop_bucket', 'stovefan', 'mat', 'tvstand', 'toaster', 'foundation', 'mousepad', 'pillow', 'wall', 'standingmirror', 'photoframe', 'toilet_paper', 'oven_mitts', 'tray', 'mouse', 'sink']
Task:Read book
response:
{
"thoughts": go to living room,find the text book on the self ,sat on the chair ,open and read the book,
"actions": ['[WALK] <home_office>', '[WALK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[WALK] <home_office>', '[WALK] <chair>', '[FIND] <chair>', '[SIT] <chair>', '[READ] <novel>']
}
|
Scene_Objects:['microwave', 'chair', 'walllamp', 'drawing', 'cpuscreen', 'wallshelf', 'floor', 'ceiling', 'desk', 'bedroom', 'keyboard', 'computer', 'mop_bucket', 'stovefan', 'ceilinglamp', 'tvstand', 'homework', 'mousepad', 'couch', 'wall', 'wall_clock', 'powersocket', 'nightstand', 'television', 'doorjamb', 'mouse', 'headset', 'cupboard', 'table', 'shoe_rack']
Task:Write an email
response:
| {
"thoughts": "I go to the home office to find the computer. I turn switch computer on , i open the email. i write the email and send it.",
"actions": [
"[WALK] <home_office>",
"[WALK] <computer>",
"[FIND] <computer>",
"[SWITCHON] <computer>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'drawing', 'hanger', 'floor', 'ceiling', 'bedroom', 'remote_control', 'computer', 'button', 'brush', 'mat', 'ceilinglamp', 'window', 'closetdrawer', 'couch', 'pillow', 'wall', 'wall_clock', 'standingmirror', 'coffe_maker', 'television', 'food_rice', 'wine', 'curtain', 'doorjamb', 'diary', 'pencil', 'door', 'bathroom_cabinet', 'table']
Task:Change TV channel
response:
{
"thoughts": walk to living room, look at the television, switch on the television, grab the remote control, press the channel button in remote control, now the tv channel is changed,
"actions": ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[TURNTO] <television>', '[LOOKAT] <television>', '[SWITCHON] <television>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <button>', '[GRAB] <button>']
}
|
Scene_Objects:['chair', 'bathroom', 'trashcan', 'drawing', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'stamp', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'dining_room', 'wall', 'powersocket', 'oven', 'bed', 'newspaper', 'television', 'doorjamb', 'kitchen_counter', 'chessboard', 'dresser', 'controller', 'door', 'bathroom_cabinet', 'light']
Task:Turn on light
response:
| {
"thoughts": "Walk into the bedroom and walk to the light switch. Flip the switch.",
"actions": [
"[WALK] <bedroom>",
"[WALK] <light>",
"[FIND] <light>",
"[SWITCHON] <light>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'food_salt', 'toilet', 'chair', 'freezer', 'walllamp', 'drawing', 'orchid', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'closetdrawer', 'couch', 'pillow', 'wall', 'oven', 'tape', 'photoframe', 'television', 'doorjamb', 'kettle', 'mouse', 'dresser']
Task:Watch TV
response:
{
"thoughts": walk to living room, find the television, switch on the television, find the sofa, walk to sofa, sit in sofa, watch the television,
"actions": ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <couch>', '[WALK] <couch>', '[SIT] <couch>', '[TURNTO] <television>', '[WATCH] <television>']
}
|
Scene_Objects:['sheets', 'tablelamp', 'bathroom', 'drawing', 'floor', 'character', 'bedroom', 'stamp', 'computer', 'mat', 'ceilinglamp', 'faucet', 'window', 'mousepad', 'closetdrawer', 'clothes_hat', 'pillow', 'dining_room', 'broom', 'wall', 'bed', 'doorjamb', 'dresser', 'cupboard', 'sink', 'bathroom_cabinet', 'light', 'home_office', 'board_game', 'dirt']
Task:Turn on light
response:
| {
"thoughts": "walk to living room ,find electrical outlet , switch on eletrical outlet",
"actions": [
"[WALK] <home_office>",
"[WALK] <electrical_outlet>",
"[FIND] <electrical_outlet>",
"[SWITCHON] <electrical_outlet>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['dry_pasta', 'filing_cabinet', 'toilet', 'walllamp', 'bathroom', 'bathroom_counter', 'phone', 'tea_bag', 'keyboard', 'toaster', 'ceilinglamp', 'tvstand', 'faucet', 'brush', 'foundation', 'window', 'closetdrawer', 'couch', 'broom', 'wall_clock', 'toy', 'food_cheese', 'novel', 'food_donut', 'tray', 'kitchen_counter', 'dresser', 'bathtub', 'light', 'shoe_rack']
Task:Pick up phone
response:
{
"thoughts": Walk to the living room, Find Phone stand. Find Phone. Pickup the receiver to attend the call.,
"actions": ['[WALK] <home_office>', '[WALK] <phone>', '[FIND] <phone>', '[GRAB] <phone>']
}
|
Scene_Objects:['filing_cabinet', 'beer', 'trashcan', 'dough', 'cpuscreen', 'desk', 'keyboard', 'toaster', 'stovefan', 'tvstand', 'shower', 'faucet', 'window', 'oil', 'couch', 'dining_room', 'cutting_board', 'bed', 'food_food', 'television', 'ice', 'doorjamb', 'towel_rack', 'cd', 'door', 'sink', 'bathtub', 'bathroom_cabinet', 'light', 'home_office']
Task:Pick up phone
response:
| {
"thoughts": "I hear the phone ringing in the living room. I walk to the living room and go to the phone. I pick it up and answer the phone.",
"actions": [
"[WALK] <home_office>",
"[WALK] <phone>",
"[FIND] <phone>",
"[TURNTO] <phone>",
"[LOOKAT] <phone>",
"[GRAB] <phone>",
"[SWITCHON] <phone>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'microwave', 'chair', 'walllamp', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'bedroom', 'remote_control', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'closetdrawer', 'couch', 'pillow', 'wall', 'oven', 'toy', 'photoframe', 'mouthwash', 'television', 'doorjamb', 'pencil', 'dresser', 'sink', 'board_game']
Task:Watch TV
response:
{
"thoughts": Walk to living room, walk to TV, grab TV remote, turn on TV, put down the remote, walk to sofa, sit in soft, watch TV,
"actions": ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[SWITCHON] <television>', '[PUTOBJBACK] <remote_control>', '[WALK] <couch>', '[SIT] <couch>', '[WATCH] <television>']
}
|
Scene_Objects:['microwave', 'toilet', 'freezer', 'band-aids', 'trashcan', 'drawing', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'character', 'envelope', 'clothes_jacket', 'mat', 'shower', 'stereo', 'microphone', 'wall', 'nightstand', 'bed', 'photoframe', 'food_food', 'rag', 'doorjamb', 'towel_rack', 'kitchen_counter', 'cupboard', 'door', 'light']
Task:Put groceries in Fridge
response:
| {
"thoughts": "I take the groceries out of the grocery bags, throw away grocery bags, categorize the food so that I know where it goes in the fridge, open the fridge, and place each item in the fridge before closing the fridge.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <freezer>",
"[FIND] <freezer>",
"[OPEN] <freezer>",
"[FIND] <food_food>",
"[GRAB] <food_food>",
"[PUTIN] <food_food> <freezer>",
"[CLOSE] <freezer>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['microwave', 'nail_polish', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'shampoo', 'bedroom', 'tea_bag', 'laptop', 'tvstand', 'clothes_socks', 'closetdrawer', 'couch', 'clothes_hat', 'wall', 'nightstand', 'powersocket', 'photoframe', 'coffe_maker', 'check', 'television', 'doorjamb', 'towel_rack', 'cards', 'dresser', 'door', 'home_office', 'light']
Task:Turn on light
response:
{
"thoughts": I walk into the dining room and turn on the lights,
"actions": ['[WALK] <dining_room>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>']
}
|
Scene_Objects:['filing_cabinet', 'freezer', 'ground_coffee', 'detergent', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'character', 'bedroom', 'stovefan', 'toaster', 'faucet', 'shower', 'closetdrawer', 'candle', 'dining_room', 'wall', 'oven', 'photoframe', 'bed', 'coffe_maker', 'coffee_filter', 'tray', 'doorjamb', 'kitchen_counter', 'cupboard', 'door', 'sink', 'table']
Task:Make coffee
response:
| {
"thoughts": "Make coffee in the kitchen.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <coffe_maker>",
"[FIND] <coffe_maker>",
"[PLUGIN] <coffe_maker>",
"[OPEN] <coffe_maker>",
"[FIND] <coffee_filter>",
"[GRAB] <coffee_filter>",
"[PUTBACK] <coffee_filter> <coffe_maker>",
"[FIND] <ground_coffee>",
"[GRAB] <ground_coffee>",
"[PUTBACK] <ground_coffee> <coffe_maker>",
"[CLOSE] <coffe_maker>",
"[SWITCHON] <coffe_maker>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'walllamp', 'toothbrush', 'knifeblock', 'orchid', 'cpuscreen', 'drawing', 'shampoo', 'floor', 'ceiling', 'desk', 'mop_bucket', 'stovefan', 'laptop', 'tvstand', 'faucet', 'wall', 'nightstand', 'oven', 'tape', 'food_food', 'tray', 'curtain', 'kettle', 'kitchen_counter', 'cupboard', 'conditioner', 'sink', 'bathroom_cabinet', 'table']
Task:Wipe down counter
response:
{
"thoughts": Clean counter,
"actions": ['[WALK] <dining_room>', '[WALK] <rag>', '[FIND] <rag>', '[GRAB] <rag>', '[WALK] <sink>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[RINSE] <rag>', '[SQUEEZE] <rag>', '[SWITCHOFF] <faucet>', '[WALK] <kitchen_counter>', '[WIPE] <kitchen_counter>']
}
|
Scene_Objects:['tablelamp', 'chair', 'trashcan', 'toothbrush', 'orchid', 'wallshelf', 'hanger', 'floor', 'phone', 'keyboard', 'toaster', 'tvstand', 'shower', 'plate', 'oil', 'closetdrawer', 'pillow', 'tape', 'basket_for_clothes', 'photoframe', 'check', 'television', 'toothbrush_holder', 'shaving_cream', 'mouse', 'towel_rack', 'kitchen_counter', 'sink', 'bathtub', 'tooth_paste']
Task:Brush teeth
response:
| {
"thoughts": "walk to bathroom, look at the toothbrush holder, take toothbrush from the toothbrush holder, find the toothpaste, squeeze the toothpaste into toothbrush, now brush teeth",
"actions": [
"[WALK] <bathroom>",
"[WALK] <toothbrush_holder>",
"[FIND] <toothbrush_holder>",
"[TURNTO] <toothbrush_holder>",
"[LOOKAT] <toothbrush_holder>",
"[FIND] <toothbrush>",
"[TURNTO] <toothbrush>",
"[LOOKAT] <toothbrush>",
"[FIND] <tooth_paste>",
"[SQUEEZE] <tooth_paste>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['fork', 'sheets', 'scissors', 'microwave', 'walllamp', 'bathroom', 'detergent', 'trashcan', 'toothbrush', 'floor', 'phone', 'toaster', 'mat', 'tvstand', 'dustpan', 'wall', 'box', 'photoframe', 'coffe_maker', 'check', 'oven_mitts', 'food_rice', 'curtain', 'coffee_pot', 'kitchen_counter', 'cupboard', 'hairdryer', 'dishwasher', 'soap', 'coffee']
Task:Take dishes out of dishwasher
response:
{
"thoughts": Take clean dishes out of the dishwasher and put away,
"actions": ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[OPEN] <dishwasher>', '[CLOSE] <dishwasher>']
}
|
Scene_Objects:['toilet', 'chair', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'toaster', 'mat', 'stereo', 'faucet', 'mousepad', 'wall', 'wall_clock', 'cup', 'bed', 'photoframe', 'novel', 'coffe_maker', 'television', 'mouse', 'kitchen_counter', 'headset', 'cupboard', 'bathroom_cabinet', 'light']
Task:Listen to music
response:
| {
"thoughts": "I walk to my bedroom. I locate my stereo and turn it on. I put on my headphones and sit to listen.",
"actions": [
"[WALK] <bedroom>",
"[WALK] <stereo>",
"[FIND] <stereo>",
"[WALK] <stereo>",
"[SWITCHON] <stereo>",
"[FIND] <headset>",
"[GRAB] <headset>",
"[PUTON] <headset>",
"[FIND] <chair>",
"[SIT] <chair>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sheets', 'tablelamp', 'microwave', 'walllamp', 'milk', 'clothes_underwear', 'character', 'bedroom', 'keyboard', 'clothes_socks', 'candle', 'clothes_pants', 'wall', 'nightstand', 'powersocket', 'basket_for_clothes', 'photoframe', 'bed', 'food_food', 'curtain', 'diary', 'shoes', 'headset', 'laundry_detergent', 'sink', 'home_office', 'table', 'colander', 'clothes_shirt', 'washing_machine']
Task:Wash clothes
response:
{
"thoughts": I grab the basket for clothes from the bedroom. I carry it and walk to the washing machine. I open the washing machine. I grab the dirty clothes. I put the clothes in the washing machine. I grab the laundry detergent and put it in the washing machine. I close the washing machine. I switch on the washing machine.,
"actions": ['[WALK] <bedroom>', '[WALK] <basket_for_clothes>', '[FIND] <basket_for_clothes>', '[GRAB] <basket_for_clothes>', '[WALK] <washing_machine>', '[DROP] <basket_for_clothes>', '[OPEN] <washing_machine>', '[FIND] <clothes_pants>', '[GRAB] <clothes_pants>', '[PUTBACK] <clothes_pants> <washing_machine>', '[FIND] <clothes_shirt>', '[GRAB] <clothes_shirt>', '[PUTBACK] <clothes_shirt> <washing_machine>', '[FIND] <clothes_underwear>', '[GRAB] <clothes_underwear>', '[PUTBACK] <clothes_underwear> <washing_machine>', '[FIND] <clothes_socks>', '[GRAB] <clothes_socks>', '[PUTBACK] <clothes_socks> <washing_machine>', '[FIND] <laundry_detergent>', '[GRAB] <laundry_detergent>', '[PUTBACK] <laundry_detergent> <washing_machine>', '[GRAB] <laundry_detergent>', '[PUTOBJBACK] <laundry_detergent>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>']
}
|
Scene_Objects:['microwave', 'toilet', 'freezer', 'walllamp', 'trashcan', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'bedroom', 'table_cloth', 'stovefan', 'toaster', 'mat', 'faucet', 'shower', 'tvstand', 'wall', 'wall_clock', 'oven', 'powersocket', 'coffe_maker', 'food_food', 'tray', 'doorjamb', 'kitchen_counter', 'cupboard', 'door', 'sink', 'table']
Task:Put groceries in Fridge
response:
| {
"thoughts": "Walk to kitchen counter, grab a grocery, walk to fridge, open fridge, put the grocery into fridge, and close fridge",
"actions": [
"[WALK] <dining_room>",
"[WALK] <kitchen_counter>",
"[FIND] <food_food>",
"[GRAB] <food_food>",
"[WALK] <freezer>",
"[OPEN] <freezer>",
"[PUTIN] <food_food> <freezer>",
"[CLOSE] <freezer>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['microwave', 'chair', 'freezer', 'band-aids', 'walllamp', 'cat', 'drawing', 'floor', 'alcohol', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'deck_of_cards', 'window', 'shower', 'couch', 'pillow', 'wall', 'wall_clock', 'oven', 'photoframe', 'keys', 'television', 'curtain', 'doorjamb', 'mouse', 'home_office', 'table', 'bathroom_cabinet']
Task:Pet cat
response:
{
"thoughts": Walk into bedrrom and to the sofa. Sit on the sofa and touch cat.,
"actions": ['[WALK] <home_office>', '[WALK] <couch>', '[SIT] <couch>', '[FIND] <cat>', '[TOUCH] <cat>']
}
|
Scene_Objects:['filing_cabinet', 'microwave', 'toilet', 'chair', 'bathroom', 'orchid', 'wallshelf', 'floor', 'ceiling', 'character', 'keyboard', 'piano_bench', 'ceilinglamp', 'plate', 'faucet', 'window', 'dish_soap', 'wall_clock', 'bed', 'coffe_maker', 'coffee_filter', 'tray', 'towel_rack', 'kitchen_counter', 'dresser', 'door', 'napkin', 'home_office', 'table', 'dishwasher']
Task:Wash dishes with dishwasher
response:
| {
"thoughts": "Put dishes in the dishwasher and start the dishwasher.",
"actions": [
"[RUN] <dining_room>",
"[WALK] <bowl>",
"[FIND] <bowl>",
"[GRAB] <bowl>",
"[WALK] <dishwasher>",
"[OPEN] <dishwasher>",
"[PUTBACK] <bowl> <dishwasher>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[WALK] <dishwasher>",
"[PUTBACK] <plate> <dishwasher>",
"[FIND] <dish_soap>",
"[GRAB] <dish_soap>",
"[WALK] <dishwasher>",
"[PUTBACK] <dish_soap> <dishwasher>",
"[CLOSE] <dishwasher>",
"[SWITCHON] <dishwasher>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['microwave', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'keyboard', 'bookshelf', 'computer', 'plate', 'iron', 'mousepad', 'closetdrawer', 'wall', 'wall_clock', 'powersocket', 'cutting_board', 'clothes_gloves', 'check', 'coffe_maker', 'food_food', 'curtain', 'food_onion', 'mouse', 'comb', 'dresser', 'clothes_dress', 'sink', 'light', 'coffee']
Task:Hang up jacket
response:
{
"thoughts": I put clothes on hangers and hang them in the closet,
"actions": ['[WALK] <bedroom>', '[WALK] <clothes_dress>', '[FIND] <clothes_dress>', '[GRAB] <clothes_dress>', '[WALK] <dresser>', '[FIND] <hanger>', '[OPEN] <dresser>', '[PUTIN] <clothes_dress> <dresser>', '[FIND] <clothes_dress>', '[GRAB] <clothes_dress>', '[WALK] <dresser>', '[PUTIN] <clothes_dress> <dresser>', '[CLOSE] <dresser>']
}
|
Scene_Objects:['filing_cabinet', 'tablelamp', 'bathroom', 'trashcan', 'drawing', 'orchid', 'floor', 'phone', 'ceiling', 'desk', 'bedroom', 'keyboard', 'computer', 'faucet', 'picture', 'window', 'closetdrawer', 'couch', 'dining_room', 'bed', 'light_bulb', 'keys', 'check', 'video_game_controller', 'tray', 'doorjamb', 'mouse', 'kitchen_counter', 'bathtub', 'home_office']
Task:Pet cat
response:
| {
"thoughts": "Petting the cat",
"actions": [
"[WALK] <home_office>",
"[WALK] <cat>",
"[FIND] <cat>",
"[TOUCH] <cat>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['fork', 'chair', 'milk', 'drawing', 'cpuscreen', 'shampoo', 'folder', 'bookshelf', 'computer', 'table_cloth', 'ceilinglamp', 'mat', 'oil', 'mousepad', 'couch', 'towel', 'nightstand', 'wall', 'cutting_board', 'cup', 'photoframe', 'bed', 'food_donut', 'mouse', 'kitchen_counter', 'pajamas', 'sink', 'napkin', 'home_office', 'tooth_paste']
Task:Open front door
response:
{
"thoughts": Walk over to the front door, turn the knob, and open the door.,
"actions": ['[WALK] <home_office>']
}
|
Scene_Objects:['dry_pasta', 'chair', 'freezer', 'walllamp', 'food_butter', 'bills', 'cpuscreen', 'bathroom_counter', 'phone', 'ceiling', 'character', 'bedroom', 'computer', 'stovefan', 'ceilinglamp', 'faucet', 'floor_lamp', 'window', 'mousepad', 'closetdrawer', 'couch', 'oven', 'cup', 'photoframe', 'television', 'kitchen_counter', 'dresser', 'bathroom_cabinet', 'table', 'light']
Task:Turn on light
response:
| {
"thoughts": "Walk over to light switch, flip the switch to the on position",
"actions": [
"[WALK] <home_office>",
"[WALK] <floor_lamp>",
"[SWITCHON] <floor_lamp>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['glue', 'food_pizza', 'toilet', 'chair', 'bathroom_counter', 'floor', 'ceiling', 'cleaning_solution', 'food_bacon', 'mop_bucket', 'toaster', 'stovefan', 'faucet', 'shower', 'mousepad', 'dustpan', 'pillow', 'wall', 'nightstand', 'powersocket', 'coffe_maker', 'console', 'towel_rack', 'kitchen_counter', 'chessboard', 'cupboard', 'pajamas', 'sink', 'napkin', 'hands_both']
Task:Wash hands
response:
{
"thoughts": Washing hands,
"actions": ['[WALK] <dining_room>', '[WALK] <faucet>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <hands_both>', '[RINSE] <hands_both>', '[SWITCHOFF] <faucet>', '[FIND] <cleaning_solution>', '[SQUEEZE] <cleaning_solution>', '[SCRUB] <hands_both>', '[SWITCHON] <faucet>', '[RINSE] <hands_both>', '[SWITCHOFF] <faucet>']
}
|
Scene_Objects:['scissors', 'microwave', 'toilet', 'walllamp', 'drawing', 'bills', 'wallshelf', 'floor', 'ceiling', 'character', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'couch', 'pillow', 'dining_room', 'wall', 'nightstand', 'oven', 'bench', 'television', 'tray', 'curtain', 'towel_rack', 'pencil', 'kitchen_counter', 'bathtub', 'spoon', 'table']
Task:Watch TV
response:
| {
"thoughts": "Walk to the room, in which the TV is located. Turn on TV pressing the power button for the TV. Watch TV.",
"actions": [
"[WALK] <home_office>",
"[WALK] <television>",
"[FIND] <television>",
"[SWITCHON] <television>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'television', 'doorjamb', 'mouse', 'dresser', 'door', 'light', 'table']
Task:Draft home
response:
{
"thoughts": Using mathematics and CAD software design a home,
"actions": ['[WALK] <home_office>', '[WALK] <chair>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <mouse>', '[GRAB] <mouse>', '[TURNTO] <computer>', '[POINTAT] <computer>', '[PUTOBJBACK] <mouse>', '[FIND] <keyboard>', '[TYPE] <keyboard>', '[FIND] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>']
}
|
Scene_Objects:['sheets', 'filing_cabinet', 'tablelamp', 'juice', 'microwave', 'toilet', 'walllamp', 'orchid', 'bathroom_counter', 'bookshelf', 'bookmark', 'toaster', 'ceilinglamp', 'tvstand', 'faucet', 'window', 'mousepad', 'wall_clock', 'food_food', 'coffe_maker', 'tray', 'curtain', 'doorjamb', 'diary', 'mouse', 'kitchen_counter', 'cupboard', 'bathtub', 'home_office', 'bathroom_cabinet']
Task:Drink
response:
| {
"thoughts": "Walk to kitchen. Find water glass. Grab water glass. Find water. Pour water in water glass. Drink water from water glass.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <water_glass>",
"[FIND] <water_glass>",
"[GRAB] <water_glass>",
"[WALK] <water>",
"[FIND] <water>",
"[GRAB] <water>",
"[POUR] <water> <water_glass>",
"[DRINK] <water_glass>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['glue', 'pot', 'filing_cabinet', 'food_bread', 'tablelamp', 'mop', 'toilet', 'freezer', 'walllamp', 'desk', 'keyboard', 'toaster', 'ceilinglamp', 'laptop', 'mousepad', 'dining_room', 'nightstand', 'cup', 'photoframe', 'clothes_gloves', 'novel', 'coffe_maker', 'curtain', 'dresser', 'controller', 'clothes_dress', 'door', 'sink', 'light', 'laser_pointer']
Task:Pet cat
response:
{
"thoughts": Find a cat in the kitchen and touch it,
"actions": ['[WALK] <dining_room>', '[WALK] <cat>', '[FIND] <cat>', '[WALK] <cat>', '[TOUCH] <cat>']
}
|
Scene_Objects:['dry_pasta', 'walllamp', 'cat', 'drawing', 'orchid', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'character', 'envelope', 'computer', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'mousepad', 'couch', 'pillow', 'wall', 'wall_clock', 'oven', 'coffe_maker', 'television', 'curtain', 'hair', 'bathroom_cabinet', 'table']
Task:Pet cat
response:
| {
"thoughts": "I would walk into the living room. Then sit on the couch and pet the cat.",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[SIT] <couch>",
"[FIND] <cat>",
"[TOUCH] <cat>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['food_salt', 'chair', 'ground_coffee', 'food_butter', 'dough', 'drawing', 'floor', 'desk', 'bookmark', 'mat', 'faucet', 'floor_lamp', 'window', 'mousepad', 'couch', 'dustpan', 'pillow', 'wall', 'nightstand', 'oven', 'cup', 'novel', 'television', 'curtain', 'doorjamb', 'chessboard', 'controller', 'maindoor', 'home_office', 'table']
Task:Read book
response:
{
"thoughts": First I walk into the living room, I find the lamp and switch it on. Then I find a book, grab it, sit in the sofa, open the book and read it. When I'm finished, I find a bookmark, grab it and put it in the book. Then I close the book, put it back, and switch off the lamp.,
"actions": ['[WALK] <home_office>', '[WALK] <floor_lamp>', '[FIND] <floor_lamp>', '[SWITCHON] <floor_lamp>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <couch>', '[SIT] <couch>', '[READ] <novel>', '[FIND] <bookmark>', '[GRAB] <bookmark>', '[PUTBACK] <bookmark> <novel>', '[PUTOBJBACK] <novel>', '[SWITCHOFF] <floor_lamp>']
}
|
Scene_Objects:['dry_pasta', 'filing_cabinet', 'tablelamp', 'toilet', 'chair', 'walllamp', 'bathroom', 'drawing', 'cpuscreen', 'floor', 'bedroom', 'bookshelf', 'mat', 'tvstand', 'ceilinglamp', 'stereo', 'window', 'shower', 'mousepad', 'couch', 'pillow', 'wall', 'check', 'television', 'curtain', 'doorjamb', 'dresser', 'door', 'table', 'colander']
Task:Relax on sofa
response:
| {
"thoughts": "walk to living room, walk to sofa, sit in sofa",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[SIT] <couch>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['microwave', 'freezer', 'walllamp', 'blow_dryer', 'milk', 'bills', 'orchid', 'floor', 'ceiling', 'character', 'food_cake', 'alcohol', 'stovefan', 'homework', 'closetdrawer', 'pillow', 'broom', 'wall', 'oven', 'cutting_board', 'cup', 'coffe_maker', 'food_food', 'water', 'tray', 'kitchen_counter', 'shoes', 'sink', 'light', 'table']
Task:Drink
response:
{
"thoughts": Feeling tired after hard work I opened the fridge and grabbed cool water and drank from the glass.,
"actions": ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <cup>', '[GRAB] <cup>', '[CLOSE] <freezer>', '[FIND] <water>', '[GRAB] <water>', '[FIND] <cup>', '[POUR] <water> <cup>', '[FIND] <cup>', '[DRINK] <cup>']
}
|
Scene_Objects:['cd_player', 'walllamp', 'needle', 'cpuscreen', 'music_stand', 'floor', 'phone', 'ceiling', 'bedroom', 'tea_bag', 'desk', 'toaster', 'mat', 'window', 'mousepad', 'closetdrawer', 'couch', 'food_peanut_butter', 'pillow', 'nightstand', 'bench', 'photoframe', 'check', 'food_food', 'curtain', 'mouse', 'kitchen_counter', 'door', 'table', 'light']
Task:Listen to music
response:
| {
"thoughts": "Walk to the living and turn to the music stand. Switch on the CD player to listen to music.",
"actions": [
"[WALK] <home_office>",
"[WALK] <music_stand>",
"[FIND] <music_stand>",
"[TURNTO] <music_stand>",
"[FIND] <cd_player>",
"[SWITCHON] <cd_player>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'filing_cabinet', 'food_carrot', 'drawing', 'floor', 'character', 'computer', 'ceilinglamp', 'shower', 'window', 'mousepad', 'couch', 'candle', 'wall', 'wall_clock', 'oven', 'cup', 'photoframe', 'bed', 'novel', 'check', 'toilet_paper', 'television', 'curtain', 'towel_rack', 'mouse', 'hairbrush', 'laundry_detergent', 'table', 'clothes_skirt']
Task:Read book
response:
{
"thoughts": Walk to the couch in the living room, sit on ti and read the book,
"actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <novel>', '[GRAB] <novel>', '[READ] <novel>']
}
|
Scene_Objects:['filing_cabinet', 'food_salt', 'toilet', 'chair', 'walllamp', 'bathroom', 'trashcan', 'drawing', 'wallshelf', 'cpuscreen', 'floor', 'bedroom', 'bookshelf', 'computer', 'mat', 'shower', 'window', 'closetdrawer', 'couch', 'pillow', 'dining_room', 'nightstand', 'oven', 'coffe_maker', 'television', 'cards', 'towel_rack', 'cupboard', 'napkin', 'bathroom_cabinet']
Task:Wash dishes with dishwasher
response:
| {
"thoughts": "Walk to the sink. Take dishes out of sink. Open dishwasher and place dishes in dishwasher.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <dishwasher>",
"[FIND] <dishwasher>",
"[OPEN] <dishwasher>",
"[CLOSE] <dishwasher>",
"[SWITCHON] <dishwasher>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'pencil', 'dresser', 'door', 'light']
Task:Work
response:
{
"thoughts": Walk to over to desk, sit down on chair and face the computer, turn the computer on, use arms to place hands on the keyboard, type work into the computer and use eyes to review.,
"actions": ['[WALK] <home_office>', '[WALK] <desk>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[SWITCHON] <computer>', '[FIND] <keyboard>', '[TYPE] <keyboard>']
}
|
Scene_Objects:['tablelamp', 'walllamp', 'trashcan', 'drawing', 'orchid', 'floor', 'bedroom', 'bookmark', 'mat', 'tvstand', 'ceilinglamp', 'floor_lamp', 'window', 'closetdrawer', 'couch', 'food_peanut_butter', 'pillow', 'wall', 'wall_clock', 'clothes_gloves', 'novel', 'television', 'curtain', 'towel_rack', 'mouse', 'comb', 'cupboard', 'sink', 'table', 'light']
Task:Read book
response:
| {
"thoughts": "First I walk into the living room, I find the lamp and switch it on. Then I find a book, grab it, sit in the sofa, open the book and read it. When I'm finished, I find a bookmark, grab it and put it in the book. Then I close the book, put it back, and switch off the lamp.",
"actions": [
"[WALK] <home_office>",
"[WALK] <floor_lamp>",
"[FIND] <floor_lamp>",
"[SWITCHON] <floor_lamp>",
"[FIND] <novel>",
"[GRAB] <novel>",
"[FIND] <couch>",
"[SIT] <couch>",
"[READ] <novel>",
"[FIND] <bookmark>",
"[GRAB] <bookmark>",
"[PUTBACK] <bookmark> <novel>",
"[PUTOBJBACK] <novel>",
"[SWITCHOFF] <floor_lamp>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sheets', 'dry_pasta', 'food_ice_cream', 'toilet', 'freezer', 'knifeblock', 'wallshelf', 'folder', 'desk', 'stamp', 'bedroom', 'computer', 'toaster', 'mat', 'floor_lamp', 'dustpan', 'pillow', 'dining_room', 'broom', 'wall', 'nightstand', 'check', 'curtain', 'console', 'dresser', 'door', 'sink', 'bathroom_cabinet', 'light', 'dishwasher']
Task:Turn on light
response:
{
"thoughts": I go home and it's dark so I can not see anything,
"actions": ['[WALK] <home_office>', '[WALK] <floor_lamp>', '[FIND] <floor_lamp>', '[SWITCHON] <floor_lamp>']
}
|
Scene_Objects:['dry_pasta', 'freezer', 'walllamp', 'bathroom', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'table_cloth', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'microphone', 'pillow', 'wall', 'wall_clock', 'nightstand', 'television', 'tray', 'curtain', 'towel_rack', 'mouse', 'kitchen_counter', 'home_office', 'table', 'soap']
Task:Relax on sofa
response:
| {
"thoughts": "go to the living room and sit on the couch, ease into the sofa and relax.",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[LIE] <couch>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['microwave', 'toilet', 'freezer', 'trashcan', 'drawing', 'cpuscreen', 'floor', 'stamp', 'bedroom', 'stovefan', 'toaster', 'plate', 'faucet', 'shower', 'dish_soap', 'food_jam', 'towel', 'wall', 'nightstand', 'oven', 'coffe_maker', 'food_food', 'ice', 'tray', 'curtain', 'kitchen_counter', 'cupboard', 'sink', 'bathtub', 'dishwasher']
Task:Wash dishes with dishwasher
response:
{
"thoughts": I walk into the kitchen and go to the dishwasher. I open the dishwasher and grab the dishes. Iplace the dishes into the dishwasher then close it. I add soap then turn the dishwasher on.,
"actions": ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[OPEN] <dishwasher>', '[WALK] <kitchen_counter>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[PUTBACK] <dish_soap> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>']
}
|
Scene_Objects:['chair', 'walllamp', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'bookshelf', 'thread', 'computer', 'toaster', 'ceilinglamp', 'tvstand', 'mousepad', 'closetdrawer', 'dining_room', 'wall', 'powersocket', 'bench', 'keys', 'television', 'doorjamb', 'diary', 'mouse', 'comb', 'cupboard', 'bathtub', 'home_office', 'table']
Task:Browse internet
response:
| {
"thoughts": "Browsing the world wide web for entertainment",
"actions": [
"[WALK] <home_office>",
"[WALK] <chair>",
"[FIND] <chair>",
"[SIT] <chair>",
"[FIND] <computer>",
"[SWITCHON] <computer>",
"[FIND] <mouse>",
"[TOUCH] <mouse>",
"[FIND] <keyboard>",
"[TYPE] <keyboard>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['chair', 'walllamp', 'bills', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'shampoo', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'mat', 'mousepad', 'closetdrawer', 'wall', 'powersocket', 'television', 'toothbrush_holder', 'wine', 'doorjamb', 'mouse', 'dresser', 'hairbrush', 'controller', 'clothes_dress', 'home_office', 'light', 'table']
Task:Turn on computer
response:
{
"thoughts": Press the power button on the computer to turn it on,
"actions": ['[WALK] <home_office>', '[WALK] <computer>', '[SWITCHON] <computer>']
}
|
Scene_Objects:['tablelamp', 'toilet', 'chair', 'drawing', 'cpuscreen', 'kitchen_cabinet', 'floor', 'bedroom', 'piano_bench', 'stovefan', 'toaster', 'plate', 'tvstand', 'faucet', 'shower', 'ceilinglamp', 'dish_soap', 'pillow', 'wall', 'bed', 'coffe_maker', 'television', 'tray', 'kettle', 'kitchen_counter', 'dishrack', 'sink', 'bathroom_cabinet', 'table', 'dishwasher']
Task:Wash dishes with dishwasher
response:
| {
"thoughts": "I went to the kitchen and collected the dishes and put them into the dish washer and wiped them with towel and put back into cabinet..",
"actions": [
"[WALK] <dining_room>",
"[WALK] <kitchen_cabinet>",
"[FIND] <kitchen_cabinet>",
"[OPEN] <kitchen_cabinet>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[FIND] <dishwasher>",
"[OPEN] <dishwasher>",
"[PUTBACK] <plate> <dishwasher>",
"[FIND] <dish_soap>",
"[GRAB] <dish_soap>",
"[PUTBACK] <dish_soap> <dishwasher>",
"[CLOSE] <dishwasher>",
"[SWITCHON] <dishwasher>",
"[GRAB] <plate>",
"[WIPE] <plate>",
"[FIND] <dishrack>",
"[GRAB] <dishrack>",
"[PUTOBJBACK] <dishrack>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tablelamp', 'juice', 'walllamp', 'bathroom', 'ceilingfan', 'trashcan', 'drawing', 'floor', 'ceiling', 'food_bacon', 'ceilinglamp', 'tvstand', 'balanceball', 'mat', 'window', 'couch', 'wall', 'nightstand', 'wall_clock', 'bench', 'bed', 'food_food', 'television', 'coin', 'curtain', 'mouse', 'controller', 'table', 'vase', 'instrument_violin']
Task:Watch TV
response:
{
"thoughts": Sitting on the couch watching my favorite television show.,
"actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <television>', '[TURNTO] <television>', '[WATCH] <television>']
}
|
Scene_Objects:['filing_cabinet', 'tablelamp', 'toilet', 'chair', 'ground_coffee', 'drawing', 'cpuscreen', 'wallshelf', 'floor', 'ceiling', 'stovefan', 'toaster', 'faucet', 'shower', 'window', 'closetdrawer', 'pillow', 'wall', 'oven', 'photoframe', 'coffe_maker', 'coffee_filter', 'water', 'tray', 'kitchen_counter', 'cupboard', 'door', 'sink', 'light', 'table']
Task:Make coffee
response:
| {
"thoughts": "Open coffee maker. Put filter in main basket, put ground coffee in filter, fill reservoir with water, turn on coffee maker.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <coffe_maker>",
"[FIND] <coffe_maker>",
"[OPEN] <coffe_maker>",
"[FIND] <coffee_filter>",
"[GRAB] <coffee_filter>",
"[PUTBACK] <coffee_filter> <coffe_maker>",
"[FIND] <ground_coffee>",
"[GRAB] <ground_coffee>",
"[PUTBACK] <ground_coffee> <coffe_maker>",
"[WALK] <water>",
"[FIND] <water>",
"[GRAB] <water>",
"[POUR] <water> <coffe_maker>",
"[CLOSE] <coffe_maker>",
"[SWITCHON] <coffe_maker>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'tablelamp', 'chair', 'freezer', 'walllamp', 'milk', 'floor', 'keyboard', 'table_cloth', 'stovefan', 'mat', 'tvstand', 'faucet', 'window', 'couch', 'clothes_hat', 'pillow', 'dining_room', 'toy', 'basket_for_clothes', 'coffe_maker', 'video_game_controller', 'tray', 'doorjamb', 'kettle', 'dresser', 'cupboard', 'clothes_dress', 'sink', 'table']
Task:Pick up toys
response:
{
"thoughts": Bend down and pick up the toys off of the floor.,
"actions": ['[WALK] <bedroom>', '[WALK] <toy>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <dresser>', '[OPEN] <dresser>', '[PUTIN] <toy> <dresser>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <dresser>', '[PUTIN] <toy> <dresser>', '[FIND] <toy>', '[WALK] <dresser>', '[GRAB] <toy>', '[PUTIN] <toy> <dresser>', '[CLOSE] <dresser>']
}
|
Scene_Objects:['microwave', 'chair', 'freezer', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'floor', 'keyboard', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'stereo', 'window', 'couch', 'candle', 'clothes_hat', 'pillow', 'wall', 'oven', 'coffe_maker', 'television', 'curtain', 'diary', 'towel_rack', 'mouse', 'dishrack', 'home_office', 'table']
Task:Relax on sofa
response:
| {
"thoughts": "I walk to the living room. I see the couch. I sit down on the couch, then lie down and put my feet up.",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[FIND] <couch>",
"[SIT] <couch>",
"[LIE] <couch>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['filing_cabinet', 'tea', 'microwave', 'cd_player', 'freezer', 'band-aids', 'bathroom', 'food_carrot', 'orchid', 'music_stand', 'phone', 'bookshelf', 'thread', 'mail', 'stereo', 'homework', 'mousepad', 'closetdrawer', 'clothes_hat', 'form', 'broom', 'newspaper', 'photoframe', 'check', 'food_rice', 'food_donut', 'dresser', 'sink', 'napkin', 'light']
Task:Listen to music
response:
{
"thoughts": Walk to the living and turn to the music stand. Switch on the CD player to listen to music.,
"actions": ['[WALK] <home_office>', '[WALK] <music_stand>', '[FIND] <music_stand>', '[TURNTO] <music_stand>', '[FIND] <cd_player>', '[SWITCHON] <cd_player>']
}
|
Scene_Objects:['chair', 'walllamp', 'trashcan', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'phone', 'character', 'desk', 'keyboard', 'thread', 'computer', 'ceilinglamp', 'tvstand', 'mousepad', 'dining_room', 'wall', 'powersocket', 'bench', 'cup', 'light_bulb', 'coffe_maker', 'toilet_paper', 'television', 'doorjamb', 'towel_rack', 'mouse', 'kitchen_counter', 'table']
Task:Work
response:
| {
"thoughts": "Type on a computer in the home office.",
"actions": [
"[WALK] <home_office>",
"[WALK] <computer>",
"[FIND] <computer>",
"[SWITCHON] <computer>",
"[FIND] <keyboard>",
"[TYPE] <keyboard>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['glue', 'food_ice_cream', 'tea', 'walllamp', 'orchid', 'knifeblock', 'wallshelf', 'drawing', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'button', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'dining_room', 'wall', 'powersocket', 'bench', 'photoframe', 'television', 'curtain', 'doorjamb', 'cupboard', 'light', 'dishwasher']
Task:Change TV channel
response:
{
"thoughts": Walk to the living room. Find the television. Switch on the television. Find the remote control. Grab the remote control. Point at television. Find the button. Push button.,
"actions": ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[TURNTO] <television>', '[POINTAT] <television>', '[FIND] <button>', '[PUSH] <button>']
}
|
Scene_Objects:['pot', 'chair', 'walllamp', 'bathroom', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'character', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'window', 'mousepad', 'wall', 'wall_clock', 'powersocket', 'oven', 'check', 'television', 'oven_mitts', 'doorjamb', 'mouse', 'kitchen_counter', 'sink', 'napkin', 'table', 'shoe_rack']
Task:Browse internet
response:
| {
"thoughts": "I will walk to the computer at the desk in my home office, sit in the chair, turn on the computer, open a web browser, type in the address, and view the computer.",
"actions": [
"[WALK] <home_office>",
"[WALK] <desk>",
"[FIND] <chair>",
"[SIT] <chair>",
"[FIND] <computer>",
"[SWITCHON] <computer>",
"[FIND] <mouse>",
"[GRAB] <mouse>",
"[TOUCH] <mouse>",
"[FIND] <keyboard>",
"[GRAB] <keyboard>",
"[TYPE] <keyboard>",
"[TURNTO] <computer>",
"[LOOKAT] <computer>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sheets', 'filing_cabinet', 'tablelamp', 'bathroom', 'knifeblock', 'wallshelf', 'bathroom_counter', 'character', 'bedroom', 'tea_bag', 'keyboard', 'food_cake', 'toaster', 'ceilinglamp', 'shower', 'faucet', 'couch', 'food_jam', 'clothes_pants', 'bowl', 'dining_room', 'nightstand', 'oven', 'ice', 'lighter', 'mouse', 'conditioner', 'door', 'bathroom_cabinet', 'light']
Task:Pick up phone
response:
{
"thoughts": Walk to the living room, Find Phone stand. Find Phone. Pickup the receiver to attend the call.,
"actions": ['[WALK] <home_office>', '[WALK] <phone>', '[FIND] <phone>', '[GRAB] <phone>']
}
|
Scene_Objects:['water_glass', 'tablelamp', 'microwave', 'toilet', 'freezer', 'walllamp', 'trashcan', 'drawing', 'wallshelf', 'floor', 'ceiling', 'phone', 'toaster', 'stovefan', 'mat', 'faucet', 'shower', 'window', 'wall', 'wall_clock', 'oven', 'coffe_maker', 'water', 'tray', 'doorjamb', 'towel_rack', 'kitchen_counter', 'cupboard', 'door', 'sink']
Task:Drink
response:
| {
"thoughts": "I need to go to Kitchen. Get a cup. Fill cup. Drink",
"actions": [
"[WALK] <dining_room>",
"[WALK] <cupboard>",
"[FIND] <cupboard>",
"[OPEN] <cupboard>",
"[FIND] <water_glass>",
"[GRAB] <water_glass>",
"[WALK] <freezer>",
"[WALK] <water>",
"[FIND] <water>",
"[GRAB] <water>",
"[POUR] <water> <water_glass>",
"[DRINK] <water_glass>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'tablelamp', 'tea', 'chair', 'drawing', 'orchid', 'cpuscreen', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'laptop', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'wall', 'nightstand', 'oven', 'powersocket', 'bed', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'door', 'light']
Task:Browse internet
response:
{
"thoughts": I go to the home office. I put the laptop on the desk. I sit on the chair. I switch on my laptop and I type on the keyboard and browse the internet.,
"actions": ['[WALK] <home_office>', '[WALK] <laptop>', '[FIND] <laptop>', '[GRAB] <laptop>', '[FIND] <desk>', '[OPEN] <desk>', '[PUTBACK] <laptop> <desk>', '[FIND] <chair>', '[SIT] <chair>', '[SWITCHON] <laptop>', '[TURNTO] <laptop>', '[LOOKAT] <laptop>', '[FIND] <keyboard>', '[TYPE] <keyboard>', '[TURNTO] <laptop>', '[LOOKAT] <laptop>']
}
|
Scene_Objects:['sheets', 'pot', 'glue', 'filing_cabinet', 'tablelamp', 'toilet', 'freezer', 'bathroom', 'cat', 'trashcan', 'drawing', 'cpuscreen', 'bathroom_counter', 'ceiling', 'bookshelf', 'keyboard', 'button', 'shoe-shine_kit', 'stereo', 'closetdrawer', 'nightstand', 'bench', 'cup', 'bed', 'photoframe', 'coffe_maker', 'curtain', 'shoes', 'dresser', 'light']
Task:Pet cat
response:
| {
"thoughts": "Find the cat. Pet the cat.",
"actions": [
"[WALK] <home_office>",
"[WALK] <cat>",
"[FIND] <cat>",
"[TOUCH] <cat>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['filing_cabinet', 'chair', 'freezer', 'orchid', 'bedroom', 'clothes_jacket', 'mop_bucket', 'stovefan', 'mousepad', 'pillow', 'dining_room', 'nightstand', 'wall', 'powersocket', 'oven', 'basket_for_clothes', 'bed', 'photoframe', 'mouthwash', 'television', 'wine', 'after_shave', 'doorjamb', 'sink', 'bathroom_cabinet', 'light', 'dishwasher', 'soap', 'washing_machine', 'coffee']
Task:Wash clothes
response:
{
"thoughts": Walk to the kitchen and find the basket of clothes. Put the soap and clothes into the washing machine. Turn on the washing machine.,
"actions": ['[WALK] <dining_room>', '[WALK] <basket_for_clothes>', '[FIND] <basket_for_clothes>', '[FIND] <washing_machine>', '[TURNTO] <washing_machine>', '[FIND] <soap>', '[GRAB] <soap>', '[OPEN] <washing_machine>', '[PUTBACK] <soap> <washing_machine>', '[FIND] <clothes_jacket>', '[GRAB] <clothes_jacket>', '[PUTBACK] <clothes_jacket> <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>']
}
|
Scene_Objects:['filing_cabinet', 'tablelamp', 'chair', 'bathroom', 'detergent', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'toaster', 'mousepad', 'couch', 'pillow', 'wall', 'powersocket', 'bench', 'toilet_paper', 'television', 'curtain', 'doorjamb', 'mouse', 'door', 'bathroom_cabinet', 'light', 'home_office']
Task:Turn on light
response:
| {
"thoughts": "I walk towards to the bedroom, and I open the door of the bedroom, and I switch on the lights inside the bedroom, the switch is beside the door.",
"actions": [
"[WALK] <bedroom>",
"[WALK] <light>",
"[FIND] <light>",
"[SWITCHON] <light>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sheets', 'pot', 'filing_cabinet', 'walllamp', 'drawing', 'cpuscreen', 'floor', 'phone', 'button', 'mat', 'stereo', 'window', 'homework', 'foundation', 'couch', 'pillow', 'wall', 'toy', 'cup', 'light_bulb', 'television', 'razor', 'curtain', 'after_shave', 'doorjamb', 'rag', 'coffee_pot', 'laundry_detergent', 'bathtub', 'table']
Task:Arrange furniture
response:
{
"thoughts": Move furniture where you want it.,
"actions": ['[WALK] <home_office>', '[WALK] <coffee_table>', '[PUSH] <coffee_table>', '[WALK] <couch>', '[PUSH] <couch>', '[WALK] <couch>', '[PUSH] <couch>', '[WALK] <filing_cabinet>', '[PUSH] <filing_cabinet>']
}
|
Scene_Objects:['filing_cabinet', 'microwave', 'toilet', 'freezer', 'walllamp', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'character', 'desk', 'toaster', 'shower', 'faucet', 'window', 'couch', 'wall', 'powersocket', 'bed', 'coffe_maker', 'doorjamb', 'mouse', 'kitchen_counter', 'cupboard', 'door', 'sink', 'bathtub', 'light', 'laser_pointer']
Task:Take shower
response:
| {
"thoughts": "walk to bathroom , find shower , take a shower",
"actions": [
"[WALK] <bathroom>",
"[WALK] <shower>",
"[FIND] <shower>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['filing_cabinet', 'microwave', 'toilet', 'detergent', 'cat', 'food_butter', 'knife', 'phone', 'character', 'table_cloth', 'mat', 'deck_of_cards', 'stereo', 'form', 'pillow', 'dining_room', 'nightstand', 'wall', 'basket_for_clothes', 'photoframe', 'tray', 'doorjamb', 'kitchen_counter', 'chessboard', 'dresser', 'clothes_dress', 'table', 'soap', 'washing_machine', 'creditcard']
Task:Wash clothes
response:
{
"thoughts": Walk to Bathroom. Find basket for clothes. Lift clothes dress from basket. Find washing machine. Walk to washing machine. Put clothes in washing machine. Put soap in washing machine. Switch on washing machine.,
"actions": ['[WALK] <bathroom>', '[WALK] <basket_for_clothes>', '[FIND] <basket_for_clothes>', '[FIND] <clothes_dress>', '[GRAB] <clothes_dress>', '[FIND] <washing_machine>', '[WALK] <washing_machine>', '[OPEN] <washing_machine>', '[PUTBACK] <clothes_dress> <washing_machine>', '[FIND] <soap>', '[GRAB] <soap>', '[PUTBACK] <soap> <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>']
}
|
Scene_Objects:['wallshelf', 'cpuscreen', 'hanger', 'floor', 'phone', 'desk', 'keyboard', 'bookshelf', 'toaster', 'ceilinglamp', 'tvstand', 'shower', 'window', 'dish_soap', 'form', 'nightstand', 'wall_clock', 'oven', 'powersocket', 'bench', 'tape', 'video_game_controller', 'doorjamb', 'kitchen_counter', 'dresser', 'home_office', 'light', 'dishwasher', 'bathroom_cabinet', 'table']
Task:Wash dishes with dishwasher
response:
| {
"thoughts": "I go to the dishwasher and put dish soap. I close the dishwasher and turn it on.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <dishwasher>",
"[FIND] <dishwasher>",
"[OPEN] <dishwasher>",
"[FIND] <dish_soap>",
"[GRAB] <dish_soap>",
"[PUTBACK] <dish_soap> <dishwasher>",
"[GRAB] <dish_soap>",
"[PUTBACK] <dish_soap> <dishwasher>",
"[CLOSE] <dishwasher>",
"[SWITCHON] <dishwasher>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'chair', 'walllamp', 'knife', 'desk', 'bookshelf', 'button', 'clothes_jacket', 'stovefan', 'deck_of_cards', 'mousepad', 'closetdrawer', 'oil', 'towel', 'pillow', 'broom', 'basket_for_clothes', 'photoframe', 'novel', 'coffe_maker', 'television', 'wine', 'curtain', 'after_shave', 'cards', 'home_office', 'light', 'clothes_skirt', 'soap', 'washing_machine']
Task:Wash clothes
response:
{
"thoughts": walk to the bathroom, grab the basket for clothes, find soap, put in washing machine, turn on,
"actions": ['[WALK] <bathroom>', '[WALK] <basket_for_clothes>', '[FIND] <basket_for_clothes>', '[GRAB] <basket_for_clothes>', '[WALK] <washing_machine>', '[OPEN] <washing_machine>', '[PUTBACK] <basket_for_clothes> <washing_machine>', '[FIND] <soap>', '[GRAB] <soap>', '[WALK] <washing_machine>', '[PUTBACK] <soap> <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>']
}
|
Scene_Objects:['microwave', 'chair', 'hanger', 'bathroom_counter', 'character', 'keyboard', 'bookshelf', 'computer', 'stovefan', 'plate', 'tvstand', 'faucet', 'shower', 'dish_soap', 'mousepad', 'wall', 'wall_clock', 'oven', 'photoframe', 'bed', 'television', 'tray', 'towel_rack', 'dresser', 'door', 'sink', 'bathroom_cabinet', 'table', 'dishwasher', 'dirt']
Task:Wash dishes with dishwasher
response:
| {
"thoughts": "walk into kitchen, find dishwasher, put plates in dishwasher, put soap in dishwasher, turn on dishwasher",
"actions": [
"[WALK] <dining_room>",
"[WALK] <dishwasher>",
"[FIND] <dishwasher>",
"[OPEN] <dishwasher>",
"[FIND] <dish_soap>",
"[GRAB] <dish_soap>",
"[PUTBACK] <dish_soap> <dishwasher>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[PUTBACK] <plate> <dishwasher>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[PUTBACK] <plate> <dishwasher>",
"[CLOSE] <dishwasher>",
"[SWITCHON] <dishwasher>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['glue', 'tablelamp', 'chair', 'walllamp', 'trashcan', 'ceilingfan', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'character', 'desk', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'balanceball', 'mousepad', 'pillow', 'wall', 'nightstand', 'bench', 'food_food', 'doorjamb', 'kettle', 'mouse', 'pencil', 'headset', 'light']
Task:Browse internet
response:
{
"thoughts": go to the office, turn computer on, open an browser or any application to open any website.,
"actions": ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <computer>']
}
|
Scene_Objects:['filing_cabinet', 'chair', 'freezer', 'walllamp', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mousepad', 'closetdrawer', 'pillow', 'dining_room', 'wall', 'wall_clock', 'powersocket', 'photoframe', 'coffe_maker', 'television', 'doorjamb', 'centerpiece', 'mouse', 'cupboard', 'sink', 'bathroom_cabinet', 'table']
Task:Browse internet
response:
| {
"thoughts": "Go find a computer, turn it on, click google, and browse the internet.",
"actions": [
"[WALK] <home_office>",
"[WALK] <computer>",
"[FIND] <computer>",
"[SWITCHON] <computer>",
"[TURNTO] <computer>",
"[LOOKAT] <computer>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tea', 'walllamp', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'phone', 'bookshelf', 'remote_control', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'form', 'pillow', 'wall', 'powersocket', 'photoframe', 'bed', 'television', 'curtain', 'doorjamb', 'cupboard', 'door', 'table', 'light']
Task:Watch TV
response:
{
"thoughts": Walk to livingroom, sit on couch, grab remote and turn on tv.,
"actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[TURNTO] <television>', '[WATCH] <television>']
}
|
Scene_Objects:['filing_cabinet', 'chair', 'walllamp', 'knife', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'character', 'desk', 'keyboard', 'computer', 'toaster', 'ceilinglamp', 'tvstand', 'mousepad', 'microphone', 'pillow', 'wall', 'powersocket', 'novel', 'television', 'doorjamb', 'towel_rack', 'mouse', 'chessboard', 'door', 'sink', 'home_office', 'table']
Task:Work
response:
| {
"thoughts": "walk to home office ,find computer ,switch on computer and work",
"actions": [
"[WALK] <home_office>",
"[WALK] <computer>",
"[FIND] <computer>",
"[SWITCHON] <computer>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sheets', 'tablelamp', 'food_salt', 'crayon', 'drawing', 'orchid', 'hanger', 'floor', 'ceiling', 'bedroom', 'bookshelf', 'ceilinglamp', 'clothes_socks', 'closetdrawer', 'couch', 'pillow', 'wall', 'nightstand', 'powersocket', 'bed', 'food_food', 'video_game_controller', 'doorjamb', 'diary', 'chessboard', 'dresser', 'door', 'light', 'table', 'dishwasher']
Task:Turn on light
response:
{
"thoughts": flip the switch and turn on the lights,
"actions": ['[WALK] <light>', '[SWITCHON] <light>']
}
|
Scene_Objects:['tablelamp', 'chair', 'freezer', 'bathroom', 'orchid', 'wallshelf', 'bathroom_counter', 'floor', 'phone', 'bedroom', 'desk', 'bookshelf', 'keyboard', 'computer', 'stovefan', 'mat', 'tvstand', 'shower', 'stereo', 'ceilinglamp', 'closetdrawer', 'wall', 'nightstand', 'oven', 'newspaper', 'coffe_maker', 'mouse', 'dresser', 'door', 'bathroom_cabinet']
Task:Read book
response:
| {
"thoughts": "Open coffee maker. Put filter in main basket, put ground coffee in filter, fill reservoir with water, turn on coffee maker.",
"actions": [
"[WALK] <home_office>",
"[WALK] <address_book>",
"[FIND] <address_book>",
"[GRAB] <address_book>",
"[READ] <address_book>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'food_pizza', 'tablelamp', 'food_salt', 'toilet', 'freezer', 'detergent', 'bills', 'orchid', 'hanger', 'ceiling', 'envelope', 'table_cloth', 'brush', 'mat', 'ceilinglamp', 'shower', 'stovefan', 'nightstand', 'powersocket', 'bench', 'photoframe', 'check', 'food_food', 'wooden_spoon', 'sink', 'napkin', 'instrument_guitar', 'table', 'coffee']
Task:Pull up carpet
response:
{
"thoughts": Pry up a corner of your old dirty carpet. Tug as hard as you can until it comes off the tacs. Pull up the pad. Try not to be sick at all the dirt.,
"actions": ['[WALK] <home_office>', '[WALK] <mat>', '[FIND] <mat>', '[TOUCH] <mat>', '[PULL] <mat>']
}
|
Scene_Objects:['freezer', 'walllamp', 'bathroom', 'drawing', 'floor', 'character', 'bedroom', 'keyboard', 'computer', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'window', 'couch', 'pillow', 'wall', 'pasta', 'bench', 'cup', 'bed', 'television', 'curtain', 'doorjamb', 'towel_rack', 'mouse', 'headset', 'cupboard', 'instrument_guitar', 'table']
Task:Relax on sofa
response:
| {
"thoughts": "I walk into the living room. I bend down. I sit on the sofa.",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[FIND] <couch>",
"[SIT] <couch>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['microwave', 'toilet', 'chair', 'bathroom', 'toothbrush', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'bedroom', 'bookshelf', 'computer', 'toaster', 'faucet', 'closetdrawer', 'couch', 'pillow', 'wall', 'wall_clock', 'oven', 'nightstand', 'television', 'toothbrush_holder', 'curtain', 'mouse', 'shoes', 'clothes_dress', 'sink', 'bathroom_cabinet', 'tooth_paste']
Task:Brush teeth
response:
{
"thoughts": go to bathroom. grab toothbrush. put toothpaste on toothbrush. brush teeth. turn on faucet. rinse toothbrush and mouth. put toothbrush away.,
"actions": ['[WALK] <bathroom>', '[WALK] <sink>', '[FIND] <toothbrush_holder>', '[TURNTO] <toothbrush_holder>', '[LOOKAT] <toothbrush_holder>', '[FIND] <tooth_paste>', '[GRAB] <tooth_paste>', '[FIND] <toothbrush>', '[GRAB] <toothbrush>', '[PUTBACK] <tooth_paste> <toothbrush_holder>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[RINSE] <toothbrush>', '[PUTBACK] <toothbrush> <toothbrush_holder>']
}
|
Scene_Objects:['pot', 'filing_cabinet', 'microwave', 'chair', 'freezer', 'bathroom', 'drawing', 'cpuscreen', 'wallshelf', 'bathroom_counter', 'ceiling', 'desk', 'computer', 'stovefan', 'mat', 'ceilinglamp', 'homework', 'mousepad', 'closetdrawer', 'pillow', 'dining_room', 'wall_clock', 'oven', 'tape', 'photoframe', 'dresser', 'cupboard', 'bathtub', 'light', 'dirt']
Task:Listen to music
response:
| {
"thoughts": "I reach out arm. I put hand on radio. I turn on radio. I pick a station.",
"actions": [
"[WALK] <bedroom>",
"[WALK] <stereo>",
"[TOUCH] <stereo>",
"[TURNTO] <stereo>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sheets', 'food_ice_cream', 'measuring_cup', 'knife', 'orchid', 'cpuscreen', 'bathroom_counter', 'ceiling', 'phone', 'alcohol', 'computer', 'table_cloth', 'mat', 'deck_of_cards', 'stereo', 'window', 'pillow', 'powersocket', 'cup', 'newspaper', 'check', 'ice', 'after_shave', 'lighter', 'diary', 'cd', 'cupboard', 'maindoor', 'colander', 'board_game']
Task:Listen to music
response:
{
"thoughts": Find radio, turn it on,
"actions": ['[WALK] <home_office>', '[WALK] <stereo>', '[FIND] <stereo>', '[SWITCHON] <stereo>']
}
|
Scene_Objects:['pot', 'filing_cabinet', 'freezer', 'walllamp', 'bathroom', 'drawing', 'orchid', 'wallshelf', 'bathroom_counter', 'floor', 'phone', 'character', 'keyboard', 'mat', 'tvstand', 'ceilinglamp', 'window', 'closetdrawer', 'couch', 'pillow', 'wall', 'bench', 'tape', 'photoframe', 'television', 'curtain', 'cards', 'bathtub', 'table', 'light']
Task:Relax on sofa
response:
| {
"thoughts": "go to living room and lie down on the sofa.",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[FIND] <couch>",
"[LIE] <couch>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tablelamp', 'toilet', 'chair', 'drawing', 'cpuscreen', 'floor', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'mop_bucket', 'mat', 'laptop', 'window', 'homework', 'mousepad', 'food_orange', 'dining_room', 'wall', 'nightstand', 'oven', 'powersocket', 'cup', 'bed', 'tray', 'curtain', 'mouse', 'pencil', 'light']
Task:Watch movie
response:
{
"thoughts": Bring laptop to bed and watch a movie,
"actions": ['[WALK] <bedroom>', '[WALK] <laptop>', '[FIND] <laptop>', '[GRAB] <laptop>', '[WALK] <bed>', '[SIT] <bed>', '[SWITCHON] <laptop>', '[FIND] <keyboard>', '[TYPE] <keyboard>', '[TURNTO] <laptop>', '[LOOKAT] <laptop>']
}
|
Scene_Objects:['tablelamp', 'trashcan', 'toothbrush', 'bathroom_counter', 'shampoo', 'floor', 'phone', 'character', 'desk', 'bookshelf', 'keyboard', 'toaster', 'ceilinglamp', 'iron', 'shower', 'stereo', 'pillow', 'wall', 'wall_clock', 'photoframe', 'food_food', 'water', 'tray', 'kitchen_counter', 'cupboard', 'sink', 'home_office', 'bathroom_cabinet', 'tooth_paste', 'teeth']
Task:Wash teeth
response:
| {
"thoughts": "Walk to bathroom. Find tooth paste, tooth brush and water. Squeeze tooth paste on tooth brush. Wash teeth.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <tooth_paste>",
"[FIND] <tooth_paste>",
"[FIND] <toothbrush>",
"[FIND] <water>",
"[SQUEEZE] <tooth_paste>",
"[FIND] <teeth>",
"[WASH] <teeth>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tablelamp', 'food_ice_cream', 'chair', 'nail_polish', 'trashcan', 'ceilingfan', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'character', 'desk', 'keyboard', 'bookshelf', 'computer', 'button', 'ceilinglamp', 'balanceball', 'shower', 'mousepad', 'pillow', 'wall', 'nightstand', 'basket_for_clothes', 'toothbrush_holder', 'doorjamb', 'mouse', 'light', 'vase']
Task:Browse internet
response:
{
"thoughts": Walk to the Home Office. Find the computer. Turn on the computer.,
"actions": ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>']
}
|
Scene_Objects:['food_salt', 'microwave', 'detergent', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'shoe-shine_kit', 'faucet', 'clothes_socks', 'closetdrawer', 'mousepad', 'dining_room', 'broom', 'wall', 'nightstand', 'photoframe', 'television', 'water', 'tray', 'cards', 'paper_towel', 'door', 'sink', 'bathroom_cabinet', 'home_office', 'soap', 'hands_both']
Task:Wash hands
response:
| {
"thoughts": "I walk into the bathroom. I turn on the water. I put soap on my hands. I rinse my hands. I turn off the water. I dry my hands.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <sink>",
"[FIND] <water>",
"[TURNTO] <water>",
"[FIND] <soap>",
"[GRAB] <soap>",
"[FIND] <hands_both>",
"[SCRUB] <hands_both>",
"[RINSE] <hands_both>",
"[TURNTO] <water>",
"[FIND] <paper_towel>",
"[GRAB] <paper_towel>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['food_salt', 'bathroom', 'detergent', 'ceilingfan', 'drawing', 'orchid', 'floor', 'ceiling', 'character', 'keyboard', 'remote_control', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'couch', 'food_peanut_butter', 'pillow', 'towel', 'dining_room', 'wall', 'powersocket', 'toilet_paper', 'television', 'curtain', 'pencil', 'headset', 'cd', 'table', 'dishwasher']
Task:Change TV channel
response:
{
"thoughts": Lift the remote and change the channel,
"actions": ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[TURNTO] <television>', '[WATCH] <television>']
}
|
Scene_Objects:['chair', 'drawing', 'orchid', 'cpuscreen', 'phone', 'desk', 'bedroom', 'bookshelf', 'thread', 'computer', 'stovefan', 'mat', 'tvstand', 'shower', 'closetdrawer', 'pillow', 'nightstand', 'wall_clock', 'bed', 'light_bulb', 'photoframe', 'tray', 'doorjamb', 'mouse', 'cupboard', 'door', 'bathtub', 'sink', 'light', 'clothes_shirt']
Task:Brush teeth
response:
| {
"thoughts": "go to the bathroom and brush your teeth",
"actions": [
"[WALK] <bathroom>",
"[WALK] <toothbrush>",
"[FIND] <toothbrush>",
"[GRAB] <toothbrush>",
"[WALK] <tooth_paste>",
"[FIND] <tooth_paste>",
"[GRAB] <tooth_paste>",
"[POUR] <tooth_paste> <toothbrush>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sheets', 'cpuscreen', 'phone', 'desk', 'cleaning_solution', 'keyboard', 'purse', 'table_cloth', 'stovefan', 'tvstand', 'shower', 'stereo', 'food_noodles', 'towel', 'pillow', 'wall', 'wall_clock', 'oven', 'basket_for_clothes', 'photoframe', 'novel', 'food_rice', 'rag', 'towel_rack', 'mouse', 'dresser', 'cupboard', 'clothes_dress', 'napkin', 'table']
Task:Clean mirror
response:
{
"thoughts": GET CLEANING CLOTH, SPRAY CLEANER ON CLOTH, CLEAN MIRROR,
"actions": ['[WALK] <bathroom>', '[WALK] <cleaning_solution>', '[FIND] <cleaning_solution>', '[GRAB] <cleaning_solution>', '[FIND] <rag>', '[GRAB] <rag>', '[POUR] <cleaning_solution> <rag>', '[PUTOBJBACK] <cleaning_solution>', '[WALK] <mirror>', '[WIPE] <mirror>', '[WIPE] <mirror>', '[WIPE] <mirror>', '[PUTOBJBACK] <rag>']
}
|
Scene_Objects:['filing_cabinet', 'microwave', 'trashcan', 'orchid', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'character', 'ceilinglamp', 'mat', 'faucet', 'shower', 'couch', 'towel', 'wall', 'bench', 'oven', 'photoframe', 'bed', 'mouse', 'kitchen_counter', 'dresser', 'pajamas', 'sink', 'bathroom_cabinet', 'home_office', 'soap', 'hands_both']
Task:Wash hands
response:
| {
"thoughts": "I go to the sink, turn on the water, put soap on my hands, rub them together, then rinse them off and turn off the water. I then towel off my hands.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <sink>",
"[FIND] <faucet>",
"[SWITCHON] <faucet>",
"[FIND] <soap>",
"[GRAB] <soap>",
"[FIND] <hands_both>",
"[WASH] <hands_both>",
"[RINSE] <hands_both>",
"[SWITCHOFF] <faucet>",
"[FIND] <towel>",
"[GRAB] <towel>",
"[FIND] <hands_both>",
"[WIPE] <hands_both>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['microwave', 'toilet', 'detergent', 'food_butter', 'dough', 'orchid', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'purse', 'faucet', 'stereo', 'picture', 'dustpan', 'bowl', 'dining_room', 'wall', 'oven', 'powersocket', 'photoframe', 'wine', 'tray', 'console', 'pencil', 'sink', 'bathroom_cabinet', 'dishwasher', 'hands_both', 'shoe_rack']
Task:Wash hands
response:
{
"thoughts": I go to the bathroom, walk to the sink, turn on the faucet and then wash my hands under the water.,
"actions": ['[WALK] <bathroom>', '[WALK] <sink>', '[FIND] <faucet>', '[TURNTO] <faucet>', '[FIND] <hands_both>', '[WASH] <hands_both>']
}
|
Scene_Objects:['pot', 'food_salt', 'chair', 'freezer', 'walllamp', 'bathroom', 'trashcan', 'toothbrush', 'needle', 'desk', 'keyboard', 'alcohol', 'tvstand', 'faucet', 'window', 'food_noodles', 'couch', 'form', 'pillow', 'wall', 'wall_clock', 'bench', 'bed', 'curtain', 'cupboard', 'instrument_violin', 'bathtub', 'home_office', 'light', 'board_game']
Task:Pick up phone
response:
| {
"thoughts": "i go find the phone. i pick up the phone",
"actions": [
"[WALK] <home_office>",
"[WALK] <phone>",
"[FIND] <phone>",
"[GRAB] <phone>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['spectacles', 'sponge', 'food_bread', 'blender', 'chair', 'walllamp', 'orchid', 'knife', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'mat', 'tvstand', 'window', 'mousepad', 'clothes_socks', 'wall', 'oven', 'cup', 'television', 'mouse', 'cupboard', 'door', 'home_office', 'table']
Task:Browse internet
response:
{
"thoughts": go to the office, turn computer on, open an browser or any application to open any website.,
"actions": ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <computer>']
}
|
Scene_Objects:['sponge', 'tablelamp', 'microwave', 'toilet', 'chair', 'freezer', 'band-aids', 'trashcan', 'drawing', 'orchid', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'character', 'food_bacon', 'mat', 'tvstand', 'shower', 'pillow', 'wall', 'bed', 'photoframe', 'food_food', 'doorjamb', 'console', 'kitchen_counter', 'dresser', 'cupboard', 'door']
Task:Put groceries in Fridge
response:
| {
"thoughts": "I walk in to the kitchen. I open the fridge. I place the groceries in the fridge. I close the fridge.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <freezer>",
"[FIND] <freezer>",
"[OPEN] <freezer>",
"[FIND] <food_food>",
"[GRAB] <food_food>",
"[PUTIN] <food_food> <freezer>",
"[CLOSE] <freezer>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['fork', 'pot', 'filing_cabinet', 'beer', 'bathroom', 'detergent', 'trashcan', 'cpuscreen', 'ceiling', 'bedroom', 'desk', 'keyboard', 'clothes_jacket', 'tvstand', 'couch', 'pillow', 'food_kiwi', 'oven', 'bench', 'coffe_maker', 'oven_mitts', 'towel_rack', 'pencil', 'cupboard', 'hair', 'clothes_dress', 'food_steak', 'napkin', 'vase', 'laser_pointer']
Task:Listen to music
response:
{
"thoughts": I walk into the bedroom. I walk to stereo. I turn on stereo.,
"actions": ['[WALK] <bedroom>', '[WALK] <stereo>', '[SWITCHON] <stereo>']
}
|
Scene_Objects:['filing_cabinet', 'chair', 'walllamp', 'bathroom', 'drawing', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'dvd_player', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'faucet', 'mat', 'mousepad', 'wall', 'nightstand', 'powersocket', 'coffe_maker', 'check', 'television', 'wine', 'doorjamb', 'mouse', 'cupboard', 'controller', 'table']
Task:Browse internet
response:
| {
"thoughts": "I go to my desk. I turn on the computer. I open a web page and look at it.",
"actions": [
"[WALK] <home_office>",
"[WALK] <computer>",
"[FIND] <computer>",
"[SWITCHON] <computer>",
"[TURNTO] <computer>",
"[LOOKAT] <computer>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['microwave', 'walllamp', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'stovefan', 'laptop', 'faucet', 'mousepad', 'candle', 'microphone', 'food_orange', 'wall', 'photoframe', 'check', 'mouthwash', 'after_shave', 'doorjamb', 'cupboard', 'pajamas', 'conditioner', 'door', 'sink', 'bathroom_cabinet', 'light', 'soap', 'clothes_shirt', 'hands_both']
Task:Wash hands
response:
{
"thoughts": I go into the bathroom and turn on the light. I walk to the sink and turn on the water. I grab the soap and wash my hands,
"actions": ['[WALK] <bathroom>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>', '[WALK] <sink>', '[FIND] <soap>', '[GRAB] <soap>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <hands_both>', '[WASH] <hands_both>', '[RINSE] <hands_both>', '[PUTOBJBACK] <soap>', '[SWITCHOFF] <faucet>']
}
|
Scene_Objects:['toilet', 'chair', 'freezer', 'walllamp', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'character', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'faucet', 'window', 'mousepad', 'wall', 'powersocket', 'box', 'coffe_maker', 'television', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'door', 'bathroom_cabinet', 'table']
Task:Browse internet
response:
| {
"thoughts": "Walk to the Home Office. Find the computer. Turn on the computer.",
"actions": [
"[WALK] <home_office>",
"[WALK] <computer>",
"[FIND] <computer>",
"[SWITCHON] <computer>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sponge', 'pot', 'toilet', 'dog', 'freezer', 'walllamp', 'bathroom', 'food_carrot', 'drawing', 'hanger', 'phone', 'ceiling', 'desk', 'computer', 'toaster', 'mat', 'mousepad', 'closetdrawer', 'food_peanut_butter', 'towel', 'cup', 'food_cheese', 'keys', 'tray', 'after_shave', 'towel_rack', 'mouse', 'cupboard', 'sink', 'coffee']
Task:Pet cat
response:
{
"thoughts": I walk into the living room and I pet the cat,
"actions": ['[WALK] <home_office>', '[WALK] <cat>', '[TOUCH] <cat>']
}
|
Scene_Objects:['microwave', 'toilet', 'chair', 'freezer', 'bathroom', 'trashcan', 'orchid', 'floor', 'phone', 'character', 'keyboard', 'envelope', 'clothes_jacket', 'piano_bench', 'toaster', 'ceilinglamp', 'faucet', 'shower', 'closetdrawer', 'couch', 'wall', 'nightstand', 'bench', 'wall_clock', 'television', 'kitchen_counter', 'cupboard', 'sink', 'spoon', 'bathroom_cabinet']
Task:Go to toilet
response:
| {
"thoughts": "I walk to the entrance of the bathroom. I turn to the door. I open the door to the bathroom. I walk inside of the bathroom. I find the toilet inside of the bathroom and walk over to it. I turn and look at the toilet.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <toilet>",
"[FIND] <toilet>",
"[TURNTO] <toilet>",
"[LOOKAT] <toilet>",
"[WALK] <toilet>",
"[TURNTO] <toilet>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sponge', 'sheets', 'tablelamp', 'toilet', 'freezer', 'bathroom', 'orchid', 'wallshelf', 'hanger', 'bathroom_counter', 'floor', 'phone', 'bedroom', 'bookshelf', 'computer', 'ceilinglamp', 'tvstand', 'faucet', 'closetdrawer', 'couch', 'pillow', 'oven', 'bed', 'coffe_maker', 'doorjamb', 'mouse', 'dresser', 'door', 'bathroom_cabinet', 'home_office']
Task:Pet cat
response:
{
"thoughts": I enter the room where the cat is. I look for the cat. I find the cat. I walk over to the cat. I use my hand to pet the cat.,
"actions": ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[TURNTO] <cat>', '[LOOKAT] <cat>', '[FIND] <cat>', '[WALK] <cat>', '[TOUCH] <cat>']
}
|
Scene_Objects:['chair', 'freezer', 'walllamp', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'toaster', 'ceilinglamp', 'shoe-shine_kit', 'tvstand', 'mat', 'shower', 'mousepad', 'wall', 'powersocket', 'oven', 'bench', 'television', 'tray', 'curtain', 'doorjamb', 'mouse', 'door', 'table', 'light', 'coffee']
Task:Browse internet
response:
| {
"thoughts": "I go in my office, sit at my desk turn on the computer, then type on my keyboard and open my web browser.",
"actions": [
"[WALK] <home_office>",
"[WALK] <desk>",
"[FIND] <chair>",
"[SIT] <chair>",
"[FIND] <computer>",
"[SWITCHON] <computer>",
"[FIND] <keyboard>",
"[TYPE] <keyboard>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['filing_cabinet', 'microwave', 'chair', 'knife', 'knifeblock', 'orchid', 'drawing', 'floor', 'phone', 'character', 'bedroom', 'remote_control', 'computer', 'button', 'mat', 'tvstand', 'faucet', 'shower', 'oil', 'dining_room', 'powersocket', 'newspaper', 'ice', 'tray', 'doorjamb', 'towel_rack', 'dresser', 'door', 'home_office', 'table']
Task:Change TV channel
response:
{
"thoughts": I pick up the remote. I press button on remote.,
"actions": ['[WALK] <bedroom>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <button>', '[PUSH] <button>']
}
|
Scene_Objects:['tablelamp', 'microwave', 'toilet', 'freezer', 'walllamp', 'trashcan', 'drawing', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'character', 'food_bacon', 'mat', 'ceilinglamp', 'shower', 'wall', 'wall_clock', 'cup', 'photoframe', 'bed', 'food_food', 'tray', 'doorjamb', 'mouse', 'kitchen_counter', 'cupboard', 'door', 'coffee']
Task:Drink
response:
| {
"thoughts": "Walk into kitchen, look for cup, walk to cup, look for refrigerator, walk to refrigerator, open door, grab water, pour water into cup",
"actions": [
"[WALK] <dining_room>",
"[WALK] <cup>",
"[FIND] <cup>",
"[TURNTO] <cup>",
"[LOOKAT] <cup>",
"[WALK] <cup>",
"[FIND] <freezer>",
"[TURNTO] <freezer>",
"[LOOKAT] <freezer>",
"[WALK] <freezer>",
"[GRAB] <cup>",
"[WALK] <water>",
"[FIND] <water>",
"[GRAB] <water>",
"[POUR] <water> <cup>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'freezer', 'ceilingfan', 'drawing', 'knifeblock', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'keyboard', 'bookshelf', 'faucet', 'picture', 'window', 'dustpan', 'towel', 'wall', 'nightstand', 'photoframe', 'keys', 'toothbrush_holder', 'food_donut', 'mouse', 'kitchen_counter', 'sink', 'bathroom_cabinet', 'table', 'vase', 'soap', 'hands_both']
Task:Wash hands
response:
{
"thoughts": Cleaning hands,
"actions": ['[WALK] <bathroom>', '[WALK] <faucet>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <soap>', '[GRAB] <soap>', '[FIND] <hands_both>', '[SCRUB] <hands_both>', '[PUTOBJBACK] <soap>', '[RINSE] <hands_both>', '[SWITCHOFF] <faucet>', '[FIND] <towel>', '[GRAB] <towel>', '[WIPE] <hands_both>', '[PUTOBJBACK] <towel>']
}
|
Scene_Objects:['filing_cabinet', 'toilet', 'chair', 'trashcan', 'drawing', 'orchid', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'computer', 'toaster', 'deck_of_cards', 'mousepad', 'closetdrawer', 'couch', 'wall', 'wall_clock', 'powersocket', 'bench', 'television', 'doorjamb', 'cd', 'dresser', 'conditioner', 'door', 'home_office', 'light', 'table']
Task:Pick up phone
response:
| {
"thoughts": "I walk to the kitchen and find the phone. I pick up the phone. I hold it to my ear.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <phone>",
"[FIND] <phone>",
"[GRAB] <phone>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'microwave', 'walllamp', 'ground_coffee', 'orchid', 'drawing', 'cpuscreen', 'floor', 'phone', 'ceiling', 'toaster', 'ceilinglamp', 'plate', 'tvstand', 'window', 'dish_soap', 'pillow', 'wall', 'oven', 'powersocket', 'photoframe', 'coffe_maker', 'razor', 'tray', 'mouse', 'kitchen_counter', 'cupboard', 'bathtub', 'dishwasher', 'instrument_violin']
Task:Wash dishes with dishwasher
response:
{
"thoughts": Go to the kitchen. Find the dishwasher. Open the dishwasher. Find the plates. Load the plates into the dishwasher. Find the soap. Load the soap into the dishwasher. Close the dishwasher. Turn on the dishwasher.,
"actions": ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[PUTBACK] <dish_soap> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>']
}
|
Scene_Objects:['chair', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'desk', 'bookshelf', 'computer', 'stovefan', 'toaster', 'laptop', 'faucet', 'closetdrawer', 'couch', 'bowl', 'dining_room', 'wall', 'oven', 'bench', 'bed', 'coffe_maker', 'food_food', 'tray', 'doorjamb', 'kitchen_counter', 'dresser', 'cupboard', 'door', 'bathtub']
Task:Cook some food
response:
| {
"thoughts": "I switch on the stove and cook my groceries there.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <oven>",
"[FIND] <oven>",
"[SWITCHON] <oven>",
"[FIND] <bowl>",
"[GRAB] <bowl>",
"[PUTBACK] <bowl> <oven>",
"[FIND] <food_food>",
"[SWITCHOFF] <oven>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['toilet', 'freezer', 'drawing', 'knifeblock', 'floor', 'ceiling', 'ceilinglamp', 'mat', 'shower', 'picture', 'window', 'food_noodles', 'food_jam', 'wall', 'powersocket', 'oven', 'photoframe', 'check', 'television', 'toothbrush_holder', 'water', 'curtain', 'doorjamb', 'kitchen_counter', 'cd', 'headset', 'door', 'bathroom_cabinet', 'light', 'soap']
Task:Take shower
response:
{
"thoughts": go to a bathroom, open the shower, let water wash your body,
"actions": ['[WALK] <bathroom>', '[WALK] <shower>', '[FIND] <soap>', '[SCRUB] <soap>', '[FIND] <water>', '[RINSE] <water>']
}
|
Scene_Objects:['toilet', 'walllamp', 'detergent', 'trashcan', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'desk', 'mat', 'tvstand', 'ceilinglamp', 'window', 'couch', 'pillow', 'dining_room', 'wall', 'nightstand', 'novel', 'television', 'tray', 'curtain', 'mouse', 'kitchen_counter', 'cupboard', 'door', 'home_office', 'table', 'bathroom_cabinet', 'soap']
Task:Relax on sofa
response:
| {
"thoughts": "Find the sofa and sit on it.",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[FIND] <couch>",
"[SIT] <couch>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['chair', 'band-aids', 'walllamp', 'bathroom', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'mousepad', 'oil', 'broom', 'wall', 'nightstand', 'bench', 'newspaper', 'coffe_maker', 'food_food', 'coin', 'food_donut', 'lighter', 'mouse', 'chessboard', 'door', 'table', 'dirt']
Task:Turking
response:
{
"thoughts": Do a random variety very small jobs from different clients on mturk.Com,
"actions": ['[WALK] <home_office>', '[WALK] <desk>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>']
}
|
Scene_Objects:['tablelamp', 'microwave', 'toilet', 'walllamp', 'trashcan', 'drawing', 'cpuscreen', 'wallshelf', 'floor', 'ceiling', 'keyboard', 'mat', 'tvstand', 'ceilinglamp', 'faucet', 'window', 'mousepad', 'closetdrawer', 'couch', 'pillow', 'dining_room', 'food_kiwi', 'wall', 'light_bulb', 'novel', 'television', 'curtain', 'cupboard', 'bathtub', 'table']
Task:Read book
response:
| {
"thoughts": "I go to the living room, take a book from the shelf, sit in the sofa and read the book",
"actions": [
"[WALK] <home_office>",
"[WALK] <novel>",
"[FIND] <novel>",
"[GRAB] <novel>",
"[FIND] <couch>",
"[SIT] <couch>",
"[READ] <novel>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'food_pizza', 'tablelamp', 'crayon', 'mop', 'toilet', 'chair', 'bathroom', 'detergent', 'dough', 'ceiling', 'keyboard', 'stereo', 'couch', 'pillow', 'cup', 'newspaper', 'keys', 'check', 'toothbrush_holder', 'food_donut', 'after_shave', 'rag', 'mouse', 'pajamas', 'cupboard', 'bag', 'light', 'table', 'tooth_paste']
Task:Put away keys
response:
{
"thoughts": Return keys into a bag,
"actions": ['[WALK] <home_office>', '[WALK] <keys>', '[FIND] <keys>', '[GRAB] <keys>', '[FIND] <bag>', '[OPEN] <bag>', '[PUTBACK] <keys> <bag>', '[CLOSE] <bag>']
}
|
Scene_Objects:['freezer', 'walllamp', 'bathroom', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'character', 'remote_control', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'window', 'electric_shaver', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'powersocket', 'photoframe', 'television', 'curtain', 'mouse', 'kitchen_counter', 'dresser', 'bathtub', 'table', 'light']
Task:Watch TV
response:
| {
"thoughts": "watching TV from sofa",
"actions": [
"[WALK] <home_office>",
"[WALK] <television>",
"[FIND] <television>",
"[PLUGIN] <television>",
"[SWITCHON] <television>",
"[FIND] <couch>",
"[SIT] <couch>",
"[FIND] <remote_control>",
"[GRAB] <remote_control>",
"[DROP] <remote_control>",
"[TURNTO] <television>",
"[LOOKAT] <television>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['filing_cabinet', 'microwave', 'drawing', 'orchid', 'wallshelf', 'floor', 'desk', 'bookshelf', 'purse', 'computer', 'mat', 'tvstand', 'couch', 'clothes_pants', 'pillow', 'wall', 'bench', 'powersocket', 'basket_for_clothes', 'photoframe', 'bed', 'television', 'doorjamb', 'pencil', 'laundry_detergent', 'clothes_dress', 'table', 'light', 'clothes_shirt', 'washing_machine']
Task:Do laundry
response:
{
"thoughts": Collecting laundry from the children's hamper,
"actions": ['[WALK] <bedroom>', '[WALK] <basket_for_clothes>', '[FIND] <basket_for_clothes>', '[GRAB] <basket_for_clothes>', '[WALK] <home_office>', '[WALK] <table>', '[FIND] <table>', '[PUTBACK] <basket_for_clothes> <table>', '[WALK] <filing_cabinet>', '[OPEN] <filing_cabinet>', '[FIND] <laundry_detergent>', '[GRAB] <laundry_detergent>', '[FIND] <washing_machine>', '[OPEN] <washing_machine>', '[POUR] <laundry_detergent> <washing_machine>', '[PUTOBJBACK] <laundry_detergent>', '[CLOSE] <filing_cabinet>', '[FIND] <clothes_dress>', '[GRAB] <clothes_dress>', '[PUTBACK] <clothes_dress> <washing_machine>', '[FIND] <clothes_pants>', '[GRAB] <clothes_pants>', '[PUTBACK] <clothes_pants> <washing_machine>', '[FIND] <clothes_shirt>', '[GRAB] <clothes_shirt>', '[PUTBACK] <clothes_shirt> <washing_machine>', '[PLUGIN] <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>']
}
|
Scene_Objects:['filing_cabinet', 'tablelamp', 'microwave', 'freezer', 'trashcan', 'drawing', 'orchid', 'ceiling', 'bedroom', 'mail', 'mat', 'tvstand', 'mousepad', 'dining_room', 'wall', 'wall_clock', 'basket_for_clothes', 'coffe_maker', 'tray', 'doorjamb', 'mouse', 'kitchen_counter', 'dresser', 'laundry_detergent', 'door', 'clothes_dress', 'bathroom_cabinet', 'table', 'light', 'washing_machine']
Task:Wash clothes
response:
| {
"thoughts": "Go to kitchen, find washing machine, find laundry, put laundry in washing machine, find soap, put soap in washing machine, turn on.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <washing_machine>",
"[FIND] <washing_machine>",
"[FIND] <basket_for_clothes>",
"[GRAB] <basket_for_clothes>",
"[OPEN] <washing_machine>",
"[PUTBACK] <basket_for_clothes> <washing_machine>",
"[WALK] <laundry_detergent>",
"[FIND] <laundry_detergent>",
"[GRAB] <laundry_detergent>",
"[POUR] <laundry_detergent> <washing_machine>",
"[CLOSE] <washing_machine>",
"[SWITCHON] <washing_machine>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['chair', 'walllamp', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'bookshelf', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'stereo', 'closetdrawer', 'couch', 'pillow', 'wall', 'photoframe', 'bed', 'television', 'doorjamb', 'shaving_cream', 'mouse', 'coffee', 'dresser', 'hairbrush', 'clothes_scarf', 'soap', 'teeth']
Task:Watch TV
response:
{
"thoughts": Sitting on the couch watching my favorite television show.,
"actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <television>', '[TURNTO] <television>', '[WATCH] <television>']
}
|
Scene_Objects:['microwave', 'toilet', 'ground_coffee', 'walllamp', 'detergent', 'trashcan', 'drawing', 'wallshelf', 'character', 'remote_control', 'button', 'shower', 'faucet', 'window', 'pillow', 'wall', 'bench', 'newspaper', 'coffee_table', 'photoframe', 'coffe_maker', 'television', 'food_donut', 'tray', 'sink', 'napkin', 'bathroom_cabinet', 'home_office', 'instrument_guitar', 'light']
Task:Change TV channel
response:
| {
"thoughts": "walk next to the coffee table. pick up the remote control from the top of the coffee table. Point the remote to the TV. Press the blue arrow on the remote.",
"actions": [
"[WALK] <home_office>",
"[WALK] <coffee_table>",
"[FIND] <remote_control>",
"[GRAB] <remote_control>",
"[FIND] <button>",
"[PUSH] <button>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'check', 'television', 'doorjamb', 'mouse', 'address_book', 'dresser', 'door']
Task:Write an email
response:
{
"thoughts": Walk to Home office. Sit on the chair. Switch on the computer. Find address in addressbook. Type in the keyboard. Write mail.,
"actions": ['[WALK] <home_office>', '[WALK] <chair>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <address_book>', '[FIND] <keyboard>', '[TYPE] <keyboard>']
}
|
Scene_Objects:['microwave', 'toilet', 'freezer', 'trashcan', 'drawing', 'cpuscreen', 'floor', 'stamp', 'bedroom', 'stovefan', 'toaster', 'plate', 'faucet', 'shower', 'dish_soap', 'food_jam', 'towel', 'wall', 'nightstand', 'oven', 'coffe_maker', 'food_food', 'ice', 'tray', 'curtain', 'kitchen_counter', 'cupboard', 'sink', 'bathtub', 'dishwasher']
Task:Wash dishes with dishwasher
response:
| {
"thoughts": "I walk into the kitchen and go to the dishwasher. I open the dishwasher and grab the dishes. Iplace the dishes into the dishwasher then close it. I add soap then turn the dishwasher on.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <dishwasher>",
"[OPEN] <dishwasher>",
"[WALK] <kitchen_counter>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[PUTBACK] <plate> <dishwasher>",
"[FIND] <dish_soap>",
"[GRAB] <dish_soap>",
"[PUTBACK] <dish_soap> <dishwasher>",
"[CLOSE] <dishwasher>",
"[SWITCHON] <dishwasher>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['filing_cabinet', 'food_salt', 'chair', 'bathroom', 'orchid', 'cpuscreen', 'bathroom_counter', 'desk', 'keyboard', 'button', 'piano_bench', 'ceilinglamp', 'stereo', 'floor_lamp', 'oil', 'mousepad', 'closetdrawer', 'tape', 'love_seat', 'newspaper', 'bed', 'check', 'video_game_controller', 'mouthwash', 'curtain', 'lighter', 'diary', 'doorjamb', 'dresser', 'sink']
Task:Read
response:
{
"thoughts": Sit on an easy chair. Turn on music. Take a book and read. Turn on lamp at night.,
"actions": ['[WALK] <home_office>', '[WALK] <stereo>', '[FIND] <stereo>', '[SWITCHON] <stereo>', '[FIND] <newspaper>', '[GRAB] <newspaper>', '[FIND] <love_seat>', '[SIT] <love_seat>', '[FIND] <floor_lamp>', '[SWITCHON] <floor_lamp>', '[READ] <newspaper>']
}
|
Scene_Objects:['filing_cabinet', 'food_ice_cream', 'chair', 'freezer', 'bathroom', 'trashcan', 'orchid', 'cpuscreen', 'hanger', 'character', 'computer', 'mail', 'stovefan', 'mat', 'shower', 'couch', 'pillow', 'nightstand', 'wall', 'powersocket', 'bed', 'coffe_maker', 'television', 'tray', 'curtain', 'doorjamb', 'towel_rack', 'cupboard', 'sink', 'light']
Task:Pet cat
response:
| {
"thoughts": "I walk to the living room. I find the cat. I pet the cat.",
"actions": [
"[WALK] <home_office>",
"[WALK] <cat>",
"[FIND] <cat>",
"[TOUCH] <cat>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'food_bread', 'tablelamp', 'food_salt', 'microwave', 'chair', 'freezer', 'ground_coffee', 'dough', 'drawing', 'orchid', 'cpuscreen', 'kitchen_cabinet', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'toaster', 'mat', 'ceilinglamp', 'stovefan', 'faucet', 'shower', 'oil', 'couch', 'pillow', 'wall', 'pasta', 'oven', 'powersocket', 'food_food', 'coffe_maker', 'television', 'wine', 'tray', 'doorjamb', 'towel_rack', 'kitchen_counter', 'cupboard', 'food_steak', 'door', 'sink', 'table', 'dishwasher', 'light']
Task:Cook some food
response:
{
"thoughts": Walk into kitchen. Open fridge. Take food from fridge. Close fridge. Put food on kitchen counter. Prepare food. Turn on stove. Open kitchen cabinet. Take pot. Close cabinet. Put food in pot. Put pot on stove. Cook food.,
"actions": ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <food_food>', '[GRAB] <food_food>', '[FIND] <kitchen_counter>', '[PUTBACK] <food_food> <kitchen_counter>', '[CLOSE] <freezer>', '[FIND] <kitchen_cabinet>', '[OPEN] <kitchen_cabinet>', '[FIND] <pot>', '[GRAB] <pot>', '[CLOSE] <kitchen_cabinet>', '[FIND] <oven>', '[PUTBACK] <pot> <oven>', '[GRAB] <food_food>', '[PUTBACK] <food_food> <oven>']
}
|
Scene_Objects:['filing_cabinet', 'tablelamp', 'microwave', 'chair', 'freezer', 'detergent', 'floor', 'phone', 'ceiling', 'bedroom', 'keyboard', 'stovefan', 'shower', 'faucet', 'window', 'closetdrawer', 'wall', 'wall_clock', 'powersocket', 'bench', 'photoframe', 'coffe_maker', 'check', 'television', 'food_food', 'ice', 'rag', 'towel_rack', 'kitchen_counter', 'cupboard']
Task:Turn on light
response:
| {
"thoughts": "I go home and it's dark so I can not see anything",
"actions": [
"[WALK] <home_office>",
"[WALK] <floor_lamp>",
"[FIND] <floor_lamp>",
"[SWITCHON] <floor_lamp>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['filing_cabinet', 'microwave', 'chair', 'freezer', 'walllamp', 'food_butter', 'drawing', 'hanger', 'bathroom_counter', 'floor', 'phone', 'ceiling', 'bedroom', 'alcohol', 'window', 'food_jam', 'dining_room', 'wall', 'bench', 'powersocket', 'newspaper', 'food_food', 'doorjamb', 'kettle', 'towel_rack', 'dresser', 'cupboard', 'door', 'table', 'light']
Task:Eat dinner
response:
{
"thoughts": In our dining room, my family eats dinner. Once the food has been prepared, we gather at the dining room table and prepare to eat.,
"actions": ['[WALK] <dining_room>', '[WALK] <food_food>', '[FIND] <food_food>', '[GRAB] <food_food>', '[WALK] <dining_room>', '[WALK] <table>', '[PUTBACK] <food_food> <table>', '[WALK] <dining_room>', '[WALK] <food_food>', '[FIND] <food_food>', '[GRAB] <food_food>', '[WALK] <dining_room>', '[WALK] <table>', '[PUTBACK] <food_food> <table>', '[WALK] <chair>', '[PULL] <chair>', '[SIT] <chair>', '[TURNTO] <food_food>', '[LOOKAT] <food_food>', '[TURNTO] <food_food>', '[LOOKAT] <food_food>']
}
|
Scene_Objects:['filing_cabinet', 'microwave', 'walllamp', 'trashcan', 'drawing', 'wallshelf', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'bookshelf', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'keys', 'television', 'curtain', 'doorjamb', 'towel_rack', 'mouse', 'door', 'light', 'table']
Task:Relax on sofa
response:
| {
"thoughts": "I want to relax on the sofa to some relaxing music in the living room.",
"actions": [
"[WALK] <home_office>",
"[WALK] <light>",
"[FIND] <light>",
"[SWITCHON] <light>",
"[WALK] <stereo>",
"[PLUGIN] <stereo>",
"[SWITCHON] <stereo>",
"[WALK] <couch>",
"[SIT] <couch>",
"[LIE] <couch>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'crayon', 'tea', 'beer', 'microwave', 'toilet', 'trashcan', 'food_carrot', 'knifeblock', 'cpuscreen', 'bathroom_counter', 'floor', 'character', 'bedroom', 'desk', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'window', 'dining_room', 'food_kiwi', 'nightstand', 'bed', 'photoframe', 'doorjamb', 'dishrack', 'cupboard', 'sink', 'home_office']
Task:Open bathroom window
response:
{
"thoughts": Make sure bathroom window is unlocked. Lift up bathroom window so it is open.,
"actions": ['[WALK] <bathroom>', '[WALK] <window>', '[FIND] <window>', '[OPEN] <window>']
}
|
Scene_Objects:['filing_cabinet', 'tablelamp', 'food_salt', 'microwave', 'toilet', 'walllamp', 'drawing', 'needle', 'hanger', 'bathroom_counter', 'ceiling', 'bedroom', 'desk', 'computer', 'bookmark', 'stovefan', 'plate', 'tvstand', 'dish_soap', 'closetdrawer', 'dining_room', 'wall', 'wall_clock', 'oven', 'powersocket', 'curtain', 'kitchen_counter', 'sink', 'bathroom_cabinet', 'dishwasher']
Task:Wash dishes with dishwasher
response:
| {
"thoughts": "Walk to the kitchen. Open the dishwasher. Grab plate and put it in the dishwasher. Grab dish soap and put it in the dishwasher. Switch on the dishwasher.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <dishwasher>",
"[FIND] <dishwasher>",
"[OPEN] <dishwasher>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[PUTBACK] <plate> <dishwasher>",
"[FIND] <dish_soap>",
"[GRAB] <dish_soap>",
"[PUTBACK] <dish_soap> <dishwasher>",
"[CLOSE] <dishwasher>",
"[SWITCHON] <dishwasher>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sponge', 'food_salt', 'chair', 'detergent', 'trashcan', 'dough', 'drawing', 'character', 'computer', 'button', 'brush', 'mat', 'couch', 'clothes_pants', 'clothes_hat', 'wall', 'nightstand', 'basket_for_clothes', 'food_cheese', 'rag', 'kitchen_counter', 'shoes', 'vacuum_cleaner', 'laundry_detergent', 'conditioner', 'sink', 'home_office', 'table', 'clothes_shirt', 'washing_machine']
Task:Wash clothes
response:
{
"thoughts": Walk to bathroom, open wash-machine, lift laundry basket, grab cloth and put into wash-machine one by one, put down laundry basket, pour detergent, close wash-machine, turn on wash-machine.,
"actions": ['[WALK] <bathroom>', '[WALK] <washing_machine>', '[FIND] <washing_machine>', '[OPEN] <washing_machine>', '[FIND] <basket_for_clothes>', '[GRAB] <basket_for_clothes>', '[FIND] <clothes_pants>', '[GRAB] <clothes_pants>', '[PUTBACK] <clothes_pants> <washing_machine>', '[FIND] <clothes_shirt>', '[GRAB] <clothes_shirt>', '[PUTBACK] <clothes_shirt> <washing_machine>', '[PUTOBJBACK] <basket_for_clothes>', '[WALK] <laundry_detergent>', '[FIND] <laundry_detergent>', '[GRAB] <laundry_detergent>', '[POUR] <laundry_detergent> <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>']
}
|
Scene_Objects:['spectacles', 'microwave', 'freezer', 'walllamp', 'trashcan', 'floor', 'desk', 'keyboard', 'clothes_jacket', 'piano_bench', 'tvstand', 'shower', 'faucet', 'mousepad', 'closetdrawer', 'food_kiwi', 'nightstand', 'oven', 'bench', 'powersocket', 'basket_for_clothes', 'photoframe', 'tray', 'dresser', 'cupboard', 'home_office', 'light', 'clothes_skirt', 'soap', 'washing_machine']
Task:Wash clothes
response:
| {
"thoughts": "Walk to the kitchen and find the basket of clothes. Put the soap and clothes into the washing machine. Turn on the washing machine.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <basket_for_clothes>",
"[FIND] <basket_for_clothes>",
"[FIND] <washing_machine>",
"[TURNTO] <washing_machine>",
"[FIND] <soap>",
"[GRAB] <soap>",
"[OPEN] <washing_machine>",
"[PUTBACK] <soap> <washing_machine>",
"[FIND] <clothes_jacket>",
"[GRAB] <clothes_jacket>",
"[PUTBACK] <clothes_jacket> <washing_machine>",
"[CLOSE] <washing_machine>",
"[SWITCHON] <washing_machine>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'food_salt', 'microwave', 'toilet', 'dog', 'detergent', 'orchid', 'wallshelf', 'food_egg', 'cpuscreen', 'phone', 'stamp', 'bedroom', 'bookshelf', 'bookmark', 'shower', 'mousepad', 'food_jam', 'towel', 'pasta', 'bed', 'novel', 'food_food', 'curtain', 'centerpiece', 'shaving_cream', 'dresser', 'cupboard', 'table', 'creditcard']
Task:Walk through
response:
{
"thoughts": Walk through the entrance hall,
"actions": ['[WALK] <home_office>', '[WALK] <home_office>']
}
|
Scene_Objects:['food_ice_cream', 'microwave', 'toilet', 'chair', 'bathroom_counter', 'floor', 'laptop', 'faucet', 'shower', 'towel', 'wall', 'wall_clock', 'nightstand', 'cup', 'bed', 'photoframe', 'water', 'tray', 'doorjamb', 'towel_rack', 'dresser', 'door', 'sink', 'bathtub', 'bathroom_cabinet', 'light', 'table', 'soap', 'scrabble', 'hands_both']
Task:Wash hands
response:
| {
"thoughts": "Go into the bathroom and go over to the sink. Grab soap and turn on the water. Wet your hands and rub them together so that the soap lathers. Rub the soap all over your hands thoroughly. Rinse off the soap with water and turn off the sink. Dry your hands with a towel.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <sink>",
"[FIND] <soap>",
"[GRAB] <soap>",
"[FIND] <water>",
"[GRAB] <water>",
"[FIND] <hands_both>",
"[POUR] <water> <hands_both>",
"[FIND] <hands_both>",
"[SCRUB] <hands_both>",
"[PUTOBJBACK] <soap>",
"[RINSE] <hands_both>",
"[FIND] <towel>",
"[GRAB] <towel>",
"[WIPE] <hands_both>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sponge', 'glue', 'toilet', 'chair', 'detergent', 'dough', 'drawing', 'orchid', 'hanger', 'floor', 'ceiling', 'keyboard', 'alcohol', 'stovefan', 'ceilinglamp', 'couch', 'microphone', 'wall', 'nightstand', 'photoframe', 'coffe_maker', 'coffee_filter', 'doorjamb', 'kitchen_counter', 'hairbrush', 'cupboard', 'home_office', 'dishwasher', 'coffee', 'shoe_rack']
Task:Make coffee
response:
{
"thoughts": Open coffee maker. Put filter in main basket, put ground coffee in filter, fill reservoir with water, turn on coffee maker.,
"actions": ['[WALK] <dining_room>', '[WALK] <coffe_maker>', '[FIND] <coffe_maker>', '[OPEN] <coffe_maker>', '[FIND] <coffee_filter>', '[GRAB] <coffee_filter>', '[PUTBACK] <coffee_filter> <coffe_maker>', '[FIND] <coffee>', '[GRAB] <coffee>', '[PUTBACK] <coffee> <coffe_maker>']
}
|
Scene_Objects:['filing_cabinet', 'toilet', 'freezer', 'bathroom', 'hanger', 'floor', 'phone', 'ceiling', 'character', 'bedroom', 'bookshelf', 'toaster', 'mat', 'plate', 'faucet', 'dish_soap', 'closetdrawer', 'couch', 'pillow', 'cup', 'coffe_maker', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'sink', 'home_office', 'light', 'dishwasher']
Task:Wash dishes with dishwasher
response:
| {
"thoughts": "I go to the kitchen and open the dishwasher. I fill it up with dirty dishes and glasses. Then I put dish soap in the dishwasher, close it and turn it on.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <dishwasher>",
"[FIND] <dishwasher>",
"[OPEN] <dishwasher>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[PUTBACK] <plate> <dishwasher>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[PUTBACK] <plate> <dishwasher>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[PUTBACK] <plate> <dishwasher>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[PUTBACK] <plate> <dishwasher>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[PUTBACK] <plate> <dishwasher>",
"[FIND] <cup>",
"[GRAB] <cup>",
"[PUTBACK] <cup> <dishwasher>",
"[FIND] <dish_soap>",
"[GRAB] <dish_soap>",
"[PUTBACK] <dish_soap> <dishwasher>",
"[CLOSE] <dishwasher>",
"[SWITCHON] <dishwasher>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['food_salt', 'chair', 'freezer', 'walllamp', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'keyboard', 'thread', 'computer', 'piano_bench', 'ceilinglamp', 'mousepad', 'closetdrawer', 'wall', 'powersocket', 'photoframe', 'bed', 'television', 'doorjamb', 'towel_rack', 'mouse', 'kitchen_counter', 'dresser', 'light', 'table']
Task:Work
response:
{
"thoughts": Walk to the home office and turn to the desk. Switch on the computer. Grab the mouse and keyboard to start working.,
"actions": ['[WALK] <home_office>', '[WALK] <desk>', '[FIND] <desk>', '[TURNTO] <desk>', '[FIND] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[SWITCHON] <computer>', '[FIND] <keyboard>', '[GRAB] <keyboard>', '[FIND] <mouse>', '[GRAB] <mouse>']
}
|
Scene_Objects:['tablelamp', 'toilet', 'walllamp', 'trashcan', 'drawing', 'knife', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'computer', 'toaster', 'ceilinglamp', 'stereo', 'faucet', 'mousepad', 'wall_clock', 'powersocket', 'oven', 'photoframe', 'check', 'curtain', 'doorjamb', 'mouse', 'kitchen_counter', 'controller', 'bathtub', 'home_office', 'light']
Task:Pet cat
response:
| {
"thoughts": "Walk to living room. Find cat. Walk to cat. Pull cat.",
"actions": [
"[WALK] <home_office>",
"[WALK] <cat>",
"[FIND] <cat>",
"[WALK] <cat>",
"[PULL] <cat>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'cup', 'newspaper', 'coffe_maker', 'television', 'doorjamb', 'mouse', 'dresser', 'door']
Task:Start computer
response:
{
"thoughts": Sit in desk chair, press power button, let computer power on,
"actions": ['[WALK] <home_office>', '[WALK] <chair>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[SWITCHON] <computer>']
}
|
Scene_Objects:['microwave', 'chair', 'freezer', 'band-aids', 'walllamp', 'cat', 'drawing', 'floor', 'alcohol', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'deck_of_cards', 'window', 'shower', 'couch', 'pillow', 'wall', 'wall_clock', 'oven', 'photoframe', 'keys', 'television', 'curtain', 'doorjamb', 'mouse', 'home_office', 'table', 'bathroom_cabinet']
Task:Pet cat
response:
| {
"thoughts": "Walk into bedrrom and to the sofa. Sit on the sofa and touch cat.",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[SIT] <couch>",
"[FIND] <cat>",
"[TOUCH] <cat>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['filing_cabinet', 'tablelamp', 'walllamp', 'bathroom', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'shampoo', 'character', 'wine_glass', 'computer', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'faucet', 'window', 'couch', 'pillow', 'wall', 'bench', 'powersocket', 'food_cheese', 'food_food', 'coffe_maker', 'television', 'wine', 'curtain', 'table']
Task:Entertain
response:
{
"thoughts": Give guests wine, cheese, crackers and sit and talk,
"actions": ['[WALK] <home_office>', '[WALK] <food_cheese>', '[FIND] <food_cheese>', '[FIND] <food_food>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <wine_glass>', '[GRAB] <wine_glass>', '[DRINK] <wine_glass>']
}
|
Scene_Objects:['filing_cabinet', 'measuring_cup', 'chair', 'orchid', 'drawing', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'bookshelf', 'keyboard', 'computer', 'ceilinglamp', 'window', 'mousepad', 'closetdrawer', 'dining_room', 'wall', 'nightstand', 'doorjamb', 'mouse', 'dresser', 'controller', 'laundry_detergent', 'door', 'light', 'table', 'scrabble', 'dirt']
Task:Work
response:
| {
"thoughts": "I walk to the bedroom, then find the computer and sit in the chair ,next switch on the computer and finally type in the keyboard to start to work on it",
"actions": [
"[WALK] <bedroom>",
"[WALK] <computer>",
"[FIND] <computer>",
"[FIND] <chair>",
"[SIT] <chair>",
"[SWITCHON] <computer>",
"[FIND] <keyboard>",
"[TYPE] <keyboard>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sponge', 'glue', 'toilet', 'chair', 'detergent', 'dough', 'drawing', 'orchid', 'hanger', 'floor', 'ceiling', 'keyboard', 'alcohol', 'stovefan', 'ceilinglamp', 'couch', 'microphone', 'wall', 'nightstand', 'photoframe', 'coffe_maker', 'coffee_filter', 'doorjamb', 'kitchen_counter', 'hairbrush', 'cupboard', 'home_office', 'dishwasher', 'coffee', 'shoe_rack']
Task:Make coffee
response:
{
"thoughts": Open coffee maker. Put filter in main basket, put ground coffee in filter, fill reservoir with water, turn on coffee maker.,
"actions": ['[WALK] <dining_room>', '[WALK] <coffe_maker>', '[FIND] <coffe_maker>', '[OPEN] <coffe_maker>', '[FIND] <coffee_filter>', '[GRAB] <coffee_filter>', '[PUTBACK] <coffee_filter> <coffe_maker>', '[FIND] <coffee>', '[GRAB] <coffee>', '[PUTBACK] <coffee> <coffe_maker>']
}
|
Scene_Objects:['pot', 'chair', 'walllamp', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'bedroom', 'keyboard', 'tea_bag', 'computer', 'table_cloth', 'ceilinglamp', 'tvstand', 'mousepad', 'pillow', 'wall', 'nightstand', 'powersocket', 'bench', 'photoframe', 'television', 'tray', 'doorjamb', 'mouse', 'home_office', 'table']
Task:Browse internet
response:
| {
"thoughts": "Walk to home office. Find computer. Sit in chair in front of computer desk. Turn on computer. Open internet browser. Browse the internet",
"actions": [
"[WALK] <home_office>",
"[WALK] <computer>",
"[FIND] <computer>",
"[WALK] <desk>",
"[FIND] <chair>",
"[SIT] <chair>",
"[SWITCHON] <computer>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['walllamp', 'bathroom', 'drawing', 'orchid', 'wallshelf', 'bills', 'floor', 'ceiling', 'desk', 'bookshelf', 'remote_control', 'computer', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'bench', 'photoframe', 'television', 'curtain', 'doorjamb', 'door', 'table', 'light']
Task:Watch TV
response:
{
"thoughts": Sit on my couch directly opposite my tv , switch on my tv with the remote control and watch,
"actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>', '[PUTOBJBACK] <remote_control>', '[TURNTO] <television>', '[WATCH] <television>']
}
|
Scene_Objects:['filing_cabinet', 'tablelamp', 'dog', 'freezer', 'orchid', 'drawing', 'wallshelf', 'ceiling', 'character', 'mail', 'clothes_jacket', 'computer', 'mat', 'faucet', 'window', 'closetdrawer', 'nightstand', 'wall_clock', 'oven', 'basket_for_clothes', 'coffe_maker', 'mouse', 'dresser', 'cupboard', 'laundry_detergent', 'sink', 'bathroom_cabinet', 'light', 'scrabble', 'washing_machine']
Task:Wash clothes
response:
| {
"thoughts": "Pick up my dirty clothes, load the washer, add detergent, turn on washer",
"actions": [
"[WALK] <bedroom>",
"[WALK] <basket_for_clothes>",
"[GRAB] <basket_for_clothes>",
"[WALK] <home_office>",
"[WALK] <washing_machine>",
"[OPEN] <washing_machine>",
"[PUTBACK] <basket_for_clothes> <washing_machine>",
"[FIND] <laundry_detergent>",
"[GRAB] <laundry_detergent>",
"[PUTBACK] <laundry_detergent> <washing_machine>",
"[RUN] <washing_machine>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'door', 'light']
Task:Work
response:
{
"thoughts": Using desktop computer in home office,
"actions": ['[WALK] <home_office>', '[WALK] <desk>', '[FIND] <desk>', '[WALK] <desk>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <chair>', '[PULL] <chair>', '[SIT] <chair>', '[FIND] <mouse>', '[GRAB] <mouse>', '[FIND] <keyboard>', '[TYPE] <keyboard>', '[TURNTO] <computer>', '[LOOKAT] <computer>']
}
|
Scene_Objects:['tablelamp', 'microwave', 'toilet', 'freezer', 'walllamp', 'trashcan', 'toothbrush', 'orchid', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'bookshelf', 'table_cloth', 'stovefan', 'tvstand', 'faucet', 'shower', 'mousepad', 'couch', 'towel', 'wall', 'bed', 'coffe_maker', 'door', 'sink', 'bathroom_cabinet', 'tooth_paste', 'teeth']
Task:Wash teeth
response:
| {
"thoughts": "I go to sleep and i eat the dinner so i have to clean my mouth",
"actions": [
"[WALK] <bathroom>",
"[WALK] <sink>",
"[FIND] <tooth_paste>",
"[GRAB] <tooth_paste>",
"[FIND] <toothbrush>",
"[GRAB] <toothbrush>",
"[DROP] <tooth_paste>",
"[FIND] <teeth>",
"[SCRUB] <teeth>",
"[RINSE] <teeth>",
"[FIND] <towel>",
"[GRAB] <towel>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tablelamp', 'chair', 'walllamp', 'orchid', 'drawing', 'cpuscreen', 'wallshelf', 'hanger', 'clothes_underwear', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'television', 'doorjamb', 'shaving_cream', 'mouse', 'dresser', 'door']
Task:Browse internet
response:
{
"thoughts": switch on the computer, grab a chair and sit in front of the computer. type with keyboard and browse the internet.,
"actions": ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[FIND] <chair>', '[SIT] <chair>', '[SWITCHON] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[FIND] <keyboard>', '[TYPE] <keyboard>']
}
|
Scene_Objects:['microwave', 'toilet', 'chair', 'freezer', 'detergent', 'trashcan', 'drawing', 'wallshelf', 'clothes_underwear', 'floor', 'ceiling', 'phone', 'computer', 'toaster', 'mat', 'tvstand', 'shower', 'closetdrawer', 'wall', 'oven', 'cup', 'novel', 'water', 'drinking_glass', 'doorjamb', 'mouse', 'kitchen_counter', 'comb', 'cupboard', 'door']
Task:Drink
response:
| {
"thoughts": "go to the kitchen",
"actions": [
"[WALK] <dining_room>",
"[WALK] <freezer>",
"[FIND] <freezer>",
"[OPEN] <freezer>",
"[FIND] <drinking_glass>",
"[GRAB] <drinking_glass>",
"[FIND] <water>",
"[DRINK] <drinking_glass>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['pot', 'chair', 'freezer', 'walllamp', 'trashcan', 'milk', 'knifeblock', 'floor', 'ceiling', 'keyboard', 'table_cloth', 'ceilinglamp', 'tvstand', 'faucet', 'homework', 'towel', 'dining_room', 'wall', 'nightstand', 'oven', 'food_food', 'tray', 'console', 'kitchen_counter', 'dresser', 'cupboard', 'sink', 'bag', 'napkin', 'soap']
Task:Put groceries in Fridge
response:
{
"thoughts": Walk to kitchen counter, grab a grocery, walk to fridge, open fridge, put the grocery into fridge, and close fridge,
"actions": ['[WALK] <dining_room>', '[WALK] <kitchen_counter>', '[FIND] <food_food>', '[GRAB] <food_food>', '[WALK] <freezer>', '[OPEN] <freezer>', '[PUTIN] <food_food> <freezer>', '[CLOSE] <freezer>']
}
|
Scene_Objects:['tablelamp', 'microwave', 'freezer', 'walllamp', 'detergent', 'cat', 'knife', 'drawing', 'wallshelf', 'cpuscreen', 'bathroom_counter', 'phone', 'ceiling', 'character', 'faucet', 'window', 'foundation', 'closetdrawer', 'food_orange', 'dining_room', 'coffe_maker', 'check', 'television', 'food_food', 'tray', 'curtain', 'mouse', 'pajamas', 'door', 'bathroom_cabinet']
Task:Pet cat
response:
| {
"thoughts": "I walk into the living room and I pet the cat",
"actions": [
"[WALK] <home_office>",
"[WALK] <cat>",
"[TOUCH] <cat>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['glue', 'pot', 'tablelamp', 'microwave', 'dog', 'milk', 'orchid', 'floor', 'ceiling', 'computer', 'toaster', 'plate', 'shower', 'dish_soap', 'wall', 'food_cheese', 'coffe_maker', 'check', 'coffee_filter', 'oven_mitts', 'cards', 'towel_rack', 'pencil', 'kitchen_counter', 'comb', 'cupboard', 'conditioner', 'door', 'bathroom_cabinet', 'dishwasher']
Task:Wash dishes with dishwasher
response:
{
"thoughts": Walk to the kitchen. Open the dishwasher. Put plates into the dishwasher. Put dish soap into the dishwasher. Close the dishwasher. Turn on the dishwasher.,
"actions": ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[PUTBACK] <dish_soap> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>']
}
|
Scene_Objects:['microwave', 'chair', 'ground_coffee', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'stovefan', 'toaster', 'tvstand', 'faucet', 'shower', 'closetdrawer', 'wall', 'nightstand', 'oven', 'bench', 'tape', 'photoframe', 'coffe_maker', 'coffee_filter', 'water', 'tray', 'diary', 'mouse', 'kitchen_counter', 'cupboard', 'sink', 'bathtub', 'bathroom_cabinet']
Task:Make coffee
response:
| {
"thoughts": "Open coffee maker. Put filter in main basket, put ground coffee in filter, fill reservoir with water, turn on coffee maker.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <coffe_maker>",
"[FIND] <coffe_maker>",
"[OPEN] <coffe_maker>",
"[FIND] <coffee_filter>",
"[GRAB] <coffee_filter>",
"[PUTBACK] <coffee_filter> <coffe_maker>",
"[FIND] <ground_coffee>",
"[GRAB] <ground_coffee>",
"[FIND] <ground_coffee>",
"[PUTBACK] <ground_coffee> <coffe_maker>",
"[WALK] <water>",
"[FIND] <water>",
"[GRAB] <water>",
"[POUR] <water> <coffe_maker>",
"[CLOSE] <coffe_maker>",
"[SWITCHON] <coffe_maker>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tablelamp', 'crayon', 'toilet', 'chair', 'bathroom', 'orchid', 'floor', 'ceiling', 'character', 'bedroom', 'desk', 'computer', 'tvstand', 'faucet', 'stereo', 'food_orange', 'photoframe', 'novel', 'television', 'curtain', 'doorjamb', 'diary', 'towel_rack', 'mouse', 'shoes', 'dresser', 'cupboard', 'sink', 'bathtub', 'home_office']
Task:Get dressed
response:
{
"thoughts": I get dressed in my bedroom in the mornings.,
"actions": ['[WALK] <bedroom>', '[WALK] <shoes>', '[FIND] <shoes>', '[GRAB] <shoes>', '[PUTON] <shoes>']
}
|
Scene_Objects:['microwave', 'walllamp', 'bathroom', 'trashcan', 'bathroom_counter', 'floor', 'phone', 'bedroom', 'keyboard', 'bookshelf', 'table_cloth', 'stovefan', 'ceilinglamp', 'tvstand', 'shower', 'faucet', 'window', 'food_peanut_butter', 'clothes_pants', 'oven', 'basket_for_clothes', 'food_food', 'television', 'kettle', 'dresser', 'laundry_detergent', 'door', 'bathtub', 'clothes_shirt', 'washing_machine']
Task:Wash clothes
response:
| {
"thoughts": "Walk to bathroom, open wash-machine, lift laundry basket, grab cloth and put into wash-machine one by one, put down laundry basket, pour detergent, close wash-machine, turn on wash-machine.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <washing_machine>",
"[FIND] <washing_machine>",
"[OPEN] <washing_machine>",
"[FIND] <basket_for_clothes>",
"[GRAB] <basket_for_clothes>",
"[FIND] <clothes_pants>",
"[GRAB] <clothes_pants>",
"[PUTBACK] <clothes_pants> <washing_machine>",
"[FIND] <clothes_shirt>",
"[GRAB] <clothes_shirt>",
"[PUTBACK] <clothes_shirt> <washing_machine>",
"[PUTOBJBACK] <basket_for_clothes>",
"[WALK] <laundry_detergent>",
"[FIND] <laundry_detergent>",
"[GRAB] <laundry_detergent>",
"[POUR] <laundry_detergent> <washing_machine>",
"[CLOSE] <washing_machine>",
"[SWITCHON] <washing_machine>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tablelamp', 'microwave', 'chair', 'dog', 'drawing', 'cpuscreen', 'floor', 'phone', 'desk', 'keyboard', 'computer', 'laptop', 'mat', 'mousepad', 'wall', 'oven', 'love_seat', 'bed', 'coffe_maker', 'food_food', 'doorjamb', 'centerpiece', 'coffee_pot', 'mouse', 'pencil', 'hairbrush', 'controller', 'door', 'dishwasher', 'electrical_outlet']
Task:Write book
response:
{
"thoughts": Writing a book,
"actions": ['[WALK] <home_office>', '[WALK] <laptop>', '[FIND] <laptop>', '[GRAB] <laptop>', '[FIND] <electrical_outlet>', '[PLUGIN] <laptop>', '[WALK] <love_seat>', '[SIT] <love_seat>', '[SWITCHON] <laptop>', '[FIND] <keyboard>', '[TYPE] <keyboard>']
}
|
Scene_Objects:['microwave', 'freezer', 'walllamp', 'bathroom', 'drawing', 'cpuscreen', 'wallshelf', 'hanger', 'bathroom_counter', 'floor', 'character', 'desk', 'computer', 'food_bacon', 'mat', 'tvstand', 'ceilinglamp', 'plate', 'window', 'shower', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'television', 'wine', 'curtain', 'home_office', 'table']
Task:Relax on sofa
response:
| {
"thoughts": "Walk into the living room. Walk to the sofa and sit on it. Put your feet up on the sofa and lay down.",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[SIT] <couch>",
"[LIE] <couch>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['chair', 'freezer', 'food_carrot', 'drawing', 'orchid', 'cpuscreen', 'kitchen_cabinet', 'floor', 'ceiling', 'computer', 'mat', 'plate', 'ceilinglamp', 'stereo', 'couch', 'candle', 'food_orange', 'pillow', 'wall', 'oven', 'food_vegetable', 'novel', 'food_food', 'razor', 'television', 'console', 'kitchen_counter', 'cupboard', 'controller', 'table']
Task:Fix snack
response:
{
"thoughts": Open fridge. Take out carrots and other vegetables. Put vegetables on a plate. Put away carrots and celery. Close fridge.,
"actions": ['[WALK] <dining_room>', '[WALK] <kitchen_cabinet>', '[FIND] <kitchen_cabinet>', '[OPEN] <kitchen_cabinet>', '[FIND] <plate>', '[GRAB] <plate>', '[CLOSE] <kitchen_cabinet>', '[WALK] <freezer>', '[OPEN] <freezer>', '[FIND] <food_carrot>', '[GRAB] <food_carrot>', '[PUTBACK] <food_carrot> <plate>', '[FIND] <food_vegetable>', '[GRAB] <food_vegetable>', '[PUTBACK] <food_vegetable> <plate>', '[CLOSE] <freezer>', '[WALK] <table>', '[PUTBACK] <plate> <table>']
}
|
Scene_Objects:['food_salt', 'chair', 'ground_coffee', 'drawing', 'orchid', 'cpuscreen', 'phone', 'bedroom', 'stamp', 'desk', 'bookshelf', 'computer', 'stovefan', 'ceilinglamp', 'tvstand', 'mat', 'nightstand', 'wall', 'oven', 'wall_clock', 'photoframe', 'coffe_maker', 'mouse', 'dresser', 'cupboard', 'bathtub', 'sink', 'home_office', 'table', 'light']
Task:Pet cat
response:
| {
"thoughts": "You walk to the living room and find the cat. You look at the cat and touch it to pet it.",
"actions": [
"[WALK] <home_office>",
"[WALK] <cat>",
"[FIND] <cat>",
"[TURNTO] <cat>",
"[LOOKAT] <cat>",
"[TOUCH] <cat>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['sheets', 'filing_cabinet', 'food_ice_cream', 'beer', 'microwave', 'freezer', 'walllamp', 'floor', 'ceiling', 'phone', 'dvd_player', 'stovefan', 'ceilinglamp', 'toaster', 'mousepad', 'wall', 'wall_clock', 'cup', 'bed', 'food_food', 'coin', 'food_rice', 'water', 'pencil', 'shoes', 'controller', 'napkin', 'bathroom_cabinet', 'table', 'dishwasher']
Task:Drink
response:
{
"thoughts": Feeling tired after hard work I opened the fridge and grabbed cool water and drank from the glass.,
"actions": ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <cup>', '[GRAB] <cup>', '[CLOSE] <freezer>', '[FIND] <water>', '[GRAB] <water>', '[FIND] <cup>', '[POUR] <water> <cup>', '[FIND] <cup>', '[DRINK] <cup>']
}
|
Scene_Objects:['tablelamp', 'chair', 'freezer', 'dough', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'bookmark', 'stovefan', 'mat', 'window', 'pillow', 'wall', 'nightstand', 'powersocket', 'bed', 'novel', 'coffe_maker', 'curtain', 'doorjamb', 'door', 'sink', 'light', 'laser_pointer']
Task:Read book
response:
| {
"thoughts": "I go to the bedroom and turn on the light. I lie in bed. I grab my book from the nightstand, and look for the bookmark to check where I last left off. I read for a while. When I'm done, I put the bookmark on the page I stop at and place the book back on the nightstand.",
"actions": [
"[WALK] <bedroom>",
"[WALK] <light>",
"[FIND] <light>",
"[SWITCHON] <light>",
"[FIND] <bed>",
"[LIE] <bed>",
"[FIND] <novel>",
"[GRAB] <novel>",
"[FIND] <bookmark>",
"[GRAB] <bookmark>",
"[READ] <novel>",
"[PUTBACK] <bookmark> <novel>",
"[FIND] <nightstand>",
"[PUTBACK] <novel> <nightstand>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['food_pizza', 'microwave', 'chair', 'food_butter', 'drawing', 'bathroom_counter', 'floor', 'stamp', 'desk', 'bookmark', 'stovefan', 'tvstand', 'shower', 'microphone', 'towel', 'dining_room', 'bowl', 'nightstand', 'oven', 'bench', 'shelf', 'food_cheese', 'photoframe', 'light_bulb', 'tray', 'kitchen_counter', 'dresser', 'hair', 'door', 'bathtub']
Task:Pet cat
response:
{
"thoughts": Go into the living room and pet the cat,
"actions": ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[WALK] <cat>', '[TURNTO] <cat>', '[LOOKAT] <cat>', '[TOUCH] <cat>', '[TOUCH] <cat>', '[TOUCH] <cat>']
}
|
Scene_Objects:['filing_cabinet', 'tablelamp', 'microwave', 'toilet', 'freezer', 'bathroom', 'needle', 'cpuscreen', 'hanger', 'bathroom_counter', 'phone', 'character', 'desk', 'bedroom', 'bookshelf', 'mat', 'ceilinglamp', 'faucet', 'couch', 'pillow', 'wall_clock', 'basket_for_clothes', 'cup', 'bed', 'tray', 'kitchen_counter', 'cupboard', 'door', 'soap', 'washing_machine']
Task:Wash clothes
response:
| {
"thoughts": "put clothes and soap in the washing machine, turn it on",
"actions": [
"[WALK] <dining_room>",
"[WALK] <washing_machine>",
"[FIND] <washing_machine>",
"[FIND] <basket_for_clothes>",
"[OPEN] <basket_for_clothes>",
"[FIND] <soap>",
"[GRAB] <soap>",
"[OPEN] <washing_machine>",
"[PUTBACK] <soap> <washing_machine>",
"[CLOSE] <washing_machine>",
"[SWITCHON] <washing_machine>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['tablelamp', 'chair', 'walllamp', 'orchid', 'drawing', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'button', 'ceilinglamp', 'tvstand', 'mat', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'food_food', 'television', 'doorjamb', 'mouse', 'dresser', 'door', 'sink']
Task:Work
response:
{
"thoughts": working on computer,
"actions": ['[WALK] <home_office>', '[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <button>', '[TURNTO] <button>', '[LOOKAT] <button>', '[FIND] <mouse>', '[GRAB] <mouse>', '[GRAB] <button>', '[FIND] <chair>', '[SIT] <chair>', '[SWITCHOFF] <computer>']
}
|
Scene_Objects:['microwave', 'walllamp', 'drawing', 'wallshelf', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'character', 'mat', 'tvstand', 'ceilinglamp', 'window', 'closetdrawer', 'couch', 'pillow', 'wall', 'nightstand', 'novel', 'television', 'tray', 'curtain', 'dresser', 'bathtub', 'sink', 'bathroom_cabinet', 'coffee_cup', 'table', 'light']
Task:Relax on sofa
response:
| {
"thoughts": "you walk to the living room, open the door, find a comfy sofa, sit on it, read a book or sip a cup of coffee and relax.",
"actions": [
"[WALK] <home_office>",
"[WALK] <couch>",
"[FIND] <couch>",
"[FIND] <coffee_cup>",
"[GRAB] <coffee_cup>",
"[SIT] <couch>",
"[FIND] <novel>",
"[GRAB] <novel>",
"[READ] <novel>",
"[DRINK] <coffee_cup>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['spectacles', 'tablelamp', 'blender', 'microwave', 'chair', 'walllamp', 'cpuscreen', 'bathroom_counter', 'ceiling', 'character', 'mail', 'food_bacon', 'mat', 'stereo', 'faucet', 'homework', 'shower', 'dining_room', 'wall', 'oven', 'keys', 'television', 'food_onion', 'coffee_pot', 'towel_rack', 'kitchen_counter', 'laundry_detergent', 'bag', 'spoon', 'table']
Task:Put away keys
response:
{
"thoughts": Return keys into a bag,
"actions": ['[WALK] <home_office>', '[WALK] <keys>', '[FIND] <keys>', '[GRAB] <keys>', '[FIND] <bag>', '[OPEN] <bag>', '[PUTBACK] <keys> <bag>', '[CLOSE] <bag>']
}
|
Scene_Objects:['sheets', 'freezer', 'walllamp', 'trashcan', 'drawing', 'orchid', 'ceiling', 'phone', 'bedroom', 'stovefan', 'mat', 'tvstand', 'shower', 'faucet', 'iron', 'food_noodles', 'couch', 'towel', 'pillow', 'dining_room', 'wall_clock', 'bench', 'bed', 'television', 'after_shave', 'doorjamb', 'door', 'bathtub', 'spoon', 'bathroom_cabinet']
Task:Pick up phone
response:
| {
"thoughts": "Walk to home office 1. Walk over to phone 1 on table 1. Grab phone 1. lift phone 1.",
"actions": [
"[WALK] <home_office>",
"[WALK] <phone>",
"[FIND] <phone>",
"[GRAB] <phone>"
]
} |
You serve as an AI task planner.
1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments.
2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together.
Ensure that you response can be parsed by Python json.loads.
Here is an example plan to achieve a goal for reference:
Scene_Objects:['fork', 'filing_cabinet', 'scissors', 'juice', 'food_salt', 'microwave', 'chair', 'food_butter', 'toothbrush', 'drawing', 'wallshelf', 'bathroom_counter', 'floor', 'button', 'brush', 'ceilinglamp', 'plate', 'wall', 'tape', 'food_food', 'check', 'food_donut', 'wooden_spoon', 'rag', 'door', 'clothes_scarf', 'napkin', 'table', 'light', 'dishwasher']
Task:Eat
response:
{
"thoughts": Serve food on dinning table in appropriate utensils, sit on the chair, eat,
"actions": ['[WALK] <dining_room>', '[WALK] <table>', '[FIND] <table>', '[TURNTO] <table>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <food_food>', '[GRAB] <food_food>', '[FIND] <plate>', '[PUTBACK] <food_food> <plate>', '[GRAB] <food_food>', '[PUTOBJBACK] <food_food>', '[FIND] <fork>', '[GRAB] <fork>', '[EAT] <plate>']
}
|
Scene_Objects:['blender', 'microwave', 'chair', 'freezer', 'bathroom', 'drawing', 'orchid', 'floor', 'ceiling', 'desk', 'ceilinglamp', 'tvstand', 'stereo', 'picture', 'mat', 'closetdrawer', 'couch', 'dining_room', 'wall_clock', 'bench', 'food_food', 'coffe_maker', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'cupboard', 'home_office', 'instrument_guitar']
Task:Turn on light
response:
| {
"thoughts": "I walk into the living room and then I walk to the light switch in there and turn the lights on",
"actions": [
"[WALK] <home_office>",
"[WALK] <floor_lamp>",
"[SWITCHON] <floor_lamp>"
]
} |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.