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:['tablelamp', 'chair', 'walllamp', 'orchid', 'drawing', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'television', 'doorjamb', 'kettle', 'mouse', 'dresser', 'hair', 'door', 'coffee']
Task:Browse internet
response:
{
"thoughts": walk to living room. look at computer. switch on computer. sit in chair. watch computer. switch off computer.,
"actions": ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[SWITCHON] <computer>', '[FIND] <chair>', '[SIT] <chair>', '[WATCH] <computer>', '[SWITCHOFF] <computer>']
}
|
Scene_Objects:['sheets', 'walllamp', 'drawing', 'cpuscreen', 'character', 'desk', 'keyboard', 'bookshelf', 'computer', 'button', 'alcohol', 'laptop', 'plate', 'faucet', 'homework', 'mousepad', 'dining_room', 'check', 'food_food', 'television', 'tray', 'wooden_spoon', 'mouse', 'shoes', 'conditioner', 'maindoor', 'napkin', 'home_office', 'soap', 'instrument_violin']
Task:Browse internet
response:
| {
"thoughts": "I turn on computer. I use keyboard to type. I open browser. I search.",
"actions": [
"[WALK] <bedroom>",
"[WALK] <computer>",
"[FIND] <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:['dry_pasta', 'sheets', 'mop', 'microwave', 'chair', 'freezer', 'blow_dryer', 'nail_polish', 'orchid', 'knife', 'floor', 'keyboard', 'stovefan', 'stereo', 'foundation', 'couch', 'soap', 'food_orange', 'pillow', 'wall', 'powersocket', 'check', 'toilet_paper', 'coffe_maker', 'curtain', 'pencil', 'shoes', 'vacuum_cleaner', 'colander', 'shoe_rack']
Task:Pet cat
response:
{
"thoughts": Petting the cat,
"actions": ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[TOUCH] <cat>']
}
|
Scene_Objects:['sheets', 'jelly', 'freezer', 'chair', 'blow_dryer', 'bathroom', 'walllamp', 'knife', 'phone', 'keyboard', 'stovefan', 'homework', 'couch', 'food_jam', 'bench', 'oven', 'toy', 'box', 'food_cheese', 'oven_mitts', 'food_rice', 'tray', 'curtain', 'after_shave', 'dresser', 'clothes_dress', 'conditioner', 'hairdryer', 'vase', 'board_game']
Task:Pet cat
response:
| {
"thoughts": "I walk to my living room, find my cat, scrub it using my hand.",
"actions": [
"[WALK] <home_office>",
"[WALK] <cat>",
"[FIND] <cat>",
"[SCRUB] <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', 'water_glass', 'food_ice_cream', 'microwave', 'freezer', 'drawing', 'floor', 'ceiling', 'toaster', 'stovefan', 'mat', 'shower', 'closetdrawer', 'couch', 'food_orange', 'pillow', 'wall', 'oven', 'powersocket', 'cutting_board', 'coffe_maker', 'television', 'water', 'tray', 'towel_rack', 'kitchen_counter', 'cupboard', 'hair', 'door', 'dishwasher']
Task:Drink
response:
{
"thoughts": I enter the kitchen and grab a waterglass from the cupboard. I open the fridge and grap some water. I pour the water into the cup and drink it.,
"actions": ['[WALK] <dining_room>', '[WALK] <cupboard>', '[FIND] <cupboard>', '[OPEN] <cupboard>', '[FIND] <water_glass>', '[GRAB] <water_glass>', '[WALK] <freezer>', '[OPEN] <freezer>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <water_glass>', '[DRINK] <water_glass>']
}
|
Scene_Objects:['toilet', 'cat', 'floor', 'character', 'stamp', 'table_cloth', 'piano_bench', 'mat', 'window', 'couch', 'food_jam', 'pillow', 'wall', 'nightstand', 'bench', 'toy', 'cup', 'mouthwash', 'television', 'coffee_filter', 'tray', 'curtain', 'doorjamb', 'towel_rack', 'clothes_dress', 'door', 'food_steak', 'bathtub', 'bag', 'table']
Task:Pet cat
response:
| {
"thoughts": "I see my cat on the couch so I walk over, sit down and pet the cat.",
"actions": [
"[WALK] <home_office>",
"[WALK] <cat>",
"[FIND] <cat>",
"[TURNTO] <cat>",
"[LOOKAT] <cat>",
"[FIND] <couch>",
"[SIT] <couch>",
"[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:['bathroom', 'ceilingfan', 'food_carrot', 'drawing', 'orchid', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'computer', 'tvstand', 'faucet', 'shower', 'window', 'wall', 'photoframe', 'novel', 'toilet_paper', 'curtain', 'doorjamb', 'diary', 'towel_rack', 'clothes_dress', 'sink', 'bathroom_cabinet', 'instrument_guitar', 'table', 'vase', 'soap', 'hands_both']
Task:Wash hands
response:
{
"thoughts": I walk in to the bathroom. I find the soap. I find the faucet. I turn on the faucet. I wash my hands. I put the soap back. I rinse my hands. I turn the faucet off.,
"actions": ['[WALK] <bathroom>', '[WALK] <faucet>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <soap>', '[GRAB] <soap>', '[FIND] <hands_both>', '[WASH] <hands_both>', '[PUTOBJBACK] <soap>', '[RINSE] <hands_both>', '[SWITCHOFF] <faucet>']
}
|
Scene_Objects:['fork', 'blender', 'chair', 'walllamp', 'orchid', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'keyboard', 'mat', 'laptop', 'tvstand', 'picture', 'window', 'clothes_socks', 'couch', 'pillow', 'food_kiwi', 'wall', 'wall_clock', 'cutting_board', 'bed', 'television', 'toothbrush_holder', 'curtain', 'food_onion', 'doorjamb', 'door', 'table']
Task:Relax on sofa
response:
| {
"thoughts": "I walk into the living room. I cross the room to the couch. I sit down and relax.",
"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:['fork', 'drawing', 'wallshelf', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'character', 'desk', 'tea_bag', 'mat', 'closetdrawer', 'couch', 'pillow', 'wall', 'powersocket', 'toy', 'photoframe', 'check', 'mouthwash', 'food_food', 'food_donut', 'wine', 'curtain', 'doorjamb', 'console', 'dresser', 'door', 'light']
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:['pot', 'filing_cabinet', 'bathroom', 'detergent', 'food_butter', 'drawing', 'wallshelf', 'floor', 'desk', 'bookshelf', 'plate', 'faucet', 'picture', 'iron', 'window', 'dish_soap', 'food_jam', 'wall', 'nightstand', 'toy', 'cutting_board', 'food_food', 'television', 'curtain', 'pajamas', 'conditioner', 'light', 'dishwasher', 'tooth_paste', 'shoe_rack']
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>"
]
} |
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', 'mop', 'toilet', 'chair', 'trashcan', 'knifeblock', 'hanger', 'longboard', 'floor', 'phone', 'keyboard', 'balanceball', 'foundation', 'pillow', 'wall', 'powersocket', 'box', 'photoframe', 'bed', 'check', 'rag', 'doorjamb', 'kitchen_counter', 'dresser', 'cupboard', 'door', 'maindoor', 'light', 'colander']
Task:Sit
response:
{
"thoughts": We sit at the dining room table,
"actions": ['[WALK] <dining_room>', '[WALK] <chair>', '[FIND] <chair>', '[PULL] <chair>', '[SIT] <chair>']
}
|
Scene_Objects:['filing_cabinet', 'orchid', 'hanger', 'ceiling', 'keyboard', 'piano_bench', 'tvstand', 'shower', 'electric_shaver', 'clothes_socks', 'couch', 'wall', 'powersocket', 'bench', 'cutting_board', 'toy', 'photoframe', 'bed', 'razor', 'wooden_spoon', 'after_shave', 'coffee_pot', 'dresser', 'clothes_dress', 'bathtub', 'bathroom_cabinet', 'light', 'clothes_shirt', 'washing_machine', 'shoe_rack']
Task:Wash clothes
response:
| {
"thoughts": "walk to kitchen. grab clothes_dress. look at washing machine. open washing machine. put clothes_dress on washing machine. close washing machine. switch on washing machine. switch off washing machine.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <clothes_dress>",
"[FIND] <clothes_dress>",
"[GRAB] <clothes_dress>",
"[FIND] <washing_machine>",
"[TURNTO] <washing_machine>",
"[LOOKAT] <washing_machine>",
"[OPEN] <washing_machine>",
"[PUTBACK] <clothes_dress> <washing_machine>",
"[CLOSE] <washing_machine>",
"[SWITCHON] <washing_machine>",
"[SWITCHOFF] <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:['sponge', 'pot', 'fork', 'beer', 'walllamp', 'bathroom', 'orchid', 'kitchen_cabinet', 'floor', 'phone', 'toaster', 'mat', 'plate', 'tvstand', 'window', 'dish_soap', 'couch', 'bowl', 'wall', 'oven', 'bench', 'coffe_maker', 'tray', 'rag', 'console', 'kitchen_counter', 'dishrack', 'hair', 'maindoor', '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>']
}
|
Scene_Objects:['sponge', 'pot', 'detergent', 'cpuscreen', 'ceiling', 'character', 'thread', 'food_bacon', 'mat', 'shower', 'window', 'candle', 'pillow', 'dining_room', 'oven', 'powersocket', 'tape', 'cutting_board', 'clothes_gloves', 'coffe_maker', 'check', 'television', 'food_onion', 'cards', 'towel_rack', 'pencil', 'maindoor', 'home_office', 'table', 'teeth']
Task:Pick up phone
response:
| {
"thoughts": "go to living room, find phone, pick up 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:['tea', 'microwave', 'walllamp', 'detergent', 'drawing', 'wallshelf', 'floor', 'ceiling', 'computer', 'button', 'food_bacon', 'bookmark', 'mat', 'tvstand', 'ceilinglamp', 'couch', 'pillow', 'dining_room', 'wall', 'powersocket', 'food_cheese', 'photoframe', 'coffee_table', 'novel', 'mouthwash', 'television', 'doorjamb', 'diary', 'clothes_scarf', 'sink']
Task:Read book
response:
{
"thoughts": Sit down in recliner. Pick up novel off of coffee table. Open novel to last read page. Begin reading,
"actions": ['[WALK] <home_office>', '[WALK] <coffee_table>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <bookmark>', '[READ] <novel>']
}
|
Scene_Objects:['dry_pasta', 'shoe_rack', 'filing_cabinet', 'beer', 'microwave', 'freezer', 'nail_polish', 'drawing', 'stamp', 'keyboard', 'computer', 'bookmark', 'plate', 'tvstand', 'dish_soap', 'form', 'wall_clock', 'bench', 'toy', 'newspaper', 'novel', 'coffe_maker', 'food_donut', 'curtain', 'kitchen_counter', 'headset', 'cd', 'door', 'dishwasher', 'creditcard']
Task:Wash dishes with dishwasher
response:
| {
"thoughts": "Go to kitchen to put dirty dishs into dishwasher with soap to clean the dirty dishes",
"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] <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:['tablelamp', 'walllamp', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'folder', 'bookshelf', 'remote_control', 'button', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'photoframe', 'television', 'curtain', 'doorjamb', 'towel_rack', 'mouse', 'door', 'sink', 'table', 'light']
Task:Change TV channel
response:
{
"thoughts": I go the living room, look for my tv remote control, take the control and then sit down on the couch and turn on the TV and push the buttons on the remote control to change the channel.,
"actions": ['[WALK] <home_office>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <button>', '[PUSH] <button>']
}
|
Scene_Objects:['food_pizza', 'beer', 'microwave', 'freezer', 'walllamp', 'blow_dryer', 'detergent', 'cat', 'milk', 'drawing', 'wallshelf', 'floor', 'ceiling', 'phone', 'envelope', 'stovefan', 'couch', 'food_orange', 'food_kiwi', 'wall', 'oven', 'cutting_board', 'toy', 'shelf', 'coffe_maker', 'food_food', 'tray', 'kitchen_counter', 'maindoor', 'vase']
Task:Put groceries in Fridge
response:
| {
"thoughts": "I walk to the kitchen, open the fridge and put the groceries in the fridge. Then 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:['sheets', 'spectacles', 'filing_cabinet', 'walllamp', 'ceilingfan', 'food_carrot', 'toothbrush', 'drawing', 'desk', 'bookshelf', 'stovefan', 'balanceball', 'shower', 'window', 'candle', 'clothes_pants', 'food_orange', 'dining_room', 'bench', 'bed', 'keys', 'food_food', 'diary', 'mouse', 'shoes', 'sink', 'vase', 'tooth_paste', 'scrabble', 'teeth']
Task:Brush teeth
response:
{
"thoughts": EARLY MORNING AND BEFORE GOING TO BED,
"actions": ['[WALK] <bathroom>', '[WALK] <tooth_paste>', '[FIND] <tooth_paste>', '[GRAB] <tooth_paste>', '[FIND] <toothbrush>', '[GRAB] <toothbrush>']
}
|
Scene_Objects:['juice', 'nail_polish', 'wallshelf', 'clothes_underwear', 'bathroom_counter', 'floor', 'ceiling', 'computer', 'piano_bench', 'stovefan', 'mat', 'plate', 'faucet', 'picture', 'tvstand', 'dish_soap', 'food_noodles', 'pillow', 'food_kiwi', 'wall', 'wall_clock', 'oven', 'tape', 'shelf', 'coin', 'tray', 'curtain', 'sink', 'napkin', 'bathroom_cabinet']
Task:Wash dishes by hand
response:
| {
"thoughts": "Make some dish water, grab a dish rag, put dishes in dish water and wash.",
"actions": [
"[RUN] <sink>",
"[FIND] <dish_soap>",
"[GRAB] <dish_soap>",
"[FIND] <plate>",
"[PUTBACK] <dish_soap> <plate>",
"[RINSE] <dish_soap>",
"[FIND] <plate>",
"[WASH] <plate>"
]
} |
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:['ground_coffee', 'nail_polish', 'ceilingfan', 'drawing', 'knifeblock', 'cpuscreen', 'floor', 'ceiling', 'phone', 'remote_control', 'computer', 'button', 'mail', 'ceilinglamp', 'tvstand', 'balanceball', 'shower', 'window', 'couch', 'pillow', 'dining_room', 'wall', 'bench', 'tape', 'television', 'curtain', 'food_onion', 'cupboard', 'table', 'shoe_rack']
Task:Watch TV
response:
{
"thoughts": Go to the living room, sit on the couch, find the remote, switch on the TV and watch,
"actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>', '[TURNTO] <television>', '[WATCH] <television>']
}
|
Scene_Objects:['filing_cabinet', 'freezer', 'bathroom', 'drawing', 'orchid', 'cpuscreen', 'shampoo', 'bedroom', 'bookshelf', 'thread', 'mop_bucket', 'tvstand', 'faucet', 'mousepad', 'towel', 'powersocket', 'bed', 'coffe_maker', 'television', 'oven_mitts', 'tray', 'mouse', 'kitchen_counter', 'dresser', 'door', 'bathtub', 'maindoor', 'home_office', 'bathroom_cabinet', 'table']
Task:Pick up phone
response:
| {
"thoughts": "Enter living room. Walk to telephone. Pick up from hook.",
"actions": [
"[WALK] <home_office>",
"[WALK] <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:['filing_cabinet', 'chair', 'band-aids', 'walllamp', 'nail_polish', 'drawing', 'bills', 'wallshelf', 'orchid', 'hanger', 'knife', 'floor', 'ceiling', 'desk', 'alcohol', 'mat', 'foundation', 'closetdrawer', 'couch', 'pillow', 'wall', 'bed', 'novel', 'check', 'oven_mitts', 'rag', 'kitchen_counter', 'dresser', 'bag', 'napkin']
Task:Read book
response:
{
"thoughts": I go to the book case, I select a book, I go back and sit down, then I read.,
"actions": ['[WALK] <filing_cabinet>', '[FIND] <novel>', '[GRAB] <novel>', '[WALK] <couch>', '[READ] <novel>']
}
|
Scene_Objects:['pot', 'toilet', 'freezer', 'walllamp', 'drawing', 'hanger', 'floor', 'mat', 'tvstand', 'window', 'couch', 'food_peanut_butter', 'pillow', 'wall', 'cutting_board', 'cup', 'novel', 'food_food', 'television', 'wine', 'curtain', 'doorjamb', 'towel_rack', 'pencil', 'shoes', 'bathtub', 'bathroom_cabinet', 'table', 'soap', 'board_game']
Task:Relax on sofa
response:
| {
"thoughts": "lie in the sofa, relax",
"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:['dry_pasta', 'tablelamp', 'toilet', 'freezer', 'walllamp', 'drawing', 'character', 'bedroom', 'toaster', 'deck_of_cards', 'faucet', 'shower', 'plate', 'window', 'mousepad', 'couch', 'candle', 'clothes_hat', 'nightstand', 'photoframe', 'coffe_maker', 'coffee_filter', 'tray', 'mouse', 'pencil', 'bathtub', 'bathroom_cabinet', 'table', 'dishwasher', 'board_game']
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:['pot', 'food_ice_cream', 'chair', 'food_carrot', 'hanger', 'bathroom_counter', 'floor', 'keyboard', 'mat', 'plate', 'ceilinglamp', 'window', 'mousepad', 'couch', 'food_orange', 'pillow', 'broom', 'wall', 'toy', 'bed', 'toilet_paper', 'television', 'wine', 'curtain', 'food_onion', 'doorjamb', 'dresser', 'spoon', 'home_office', 'table']
Task:Relax on sofa
response:
| {
"thoughts": "Walk to living room. Sit on sofa. Lie down on sofa.",
"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:['pot', 'tablelamp', 'food_salt', 'microwave', 'freezer', 'drawing', 'floor', 'ceiling', 'desk', 'alcohol', 'stovefan', 'mat', 'plate', 'shower', 'couch', 'food_orange', 'pillow', 'wall', 'oven', 'food_food', 'television', 'tray', 'towel_rack', 'kitchen_counter', 'sauce_pan', 'cupboard', 'spoon', 'napkin', 'light', 'dishwasher']
Task:Cook some food
response:
{
"thoughts": I pull a sauce pan from the cupboard. I turn the stove on. I take my ingredients from the pantry and fridge. I put the ingredients in the pan and I mix them with a spoon. I cook until the food is finished and transfer my food to a plate.,
"actions": ['[WALK] <dining_room>', '[WALK] <food_food>', '[FIND] <food_food>', '[FIND] <pot>', '[GRAB] <pot>', '[FIND] <spoon>', '[GRAB] <spoon>', '[FIND] <sauce_pan>', '[PUTBACK] <spoon> <sauce_pan>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <plate>', '[PUTBACK] <pot> <plate>']
}
|
Scene_Objects:['food_pizza', 'juice', 'food_salt', 'microwave', 'ground_coffee', 'nail_polish', 'drawing', 'food_egg', 'bathroom_counter', 'shampoo', 'purse', 'stovefan', 'shower', 'stereo', 'window', 'mousepad', 'towel', 'nightstand', 'oven', 'powersocket', 'curtain', 'after_shave', 'doorjamb', 'coffee_pot', 'mouse', 'dresser', 'hair', 'door', 'bathtub', 'sink']
Task:Pick up phone
response:
| {
"thoughts": "walk to living room , find phone ,pick up phone 3",
"actions": [
"[WALK] <home_office>",
"[WALK] <phone>",
"[FIND] <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', 'filing_cabinet', 'freezer', 'detergent', 'drawing', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'man', 'bookshelf', 'clothes_jacket', 'piano_bench', 'toaster', 'stereo', 'mousepad', 'couch', 'pillow', 'wall', 'powersocket', 'coffe_maker', 'doorjamb', 'cupboard', 'door', 'sink', 'home_office', 'table', 'light']
Task:Have conversation with boyfriend
response:
{
"thoughts": Sit on sofa, talk,
"actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[WALK] <couch>', '[SIT] <couch>', '[FIND] <man>', '[GREET] <man>']
}
|
Scene_Objects:['tablelamp', 'chair', 'walllamp', 'detergent', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'character', 'desk', 'keyboard', 'computer', 'button', 'toaster', 'ceilinglamp', 'tvstand', 'mousepad', 'closetdrawer', 'broom', 'wall', 'pasta', 'powersocket', 'shelf', 'check', 'television', 'doorjamb', 'mouse', 'dresser', 'light', 'table']
Task:Work
response:
| {
"thoughts": "I walk to the living room. I find the computer and turn it on. I look at the computer screen. I move and click the mouse to select buttons on the screen.",
"actions": [
"[WALK] <home_office>",
"[WALK] <computer>",
"[FIND] <computer>",
"[SWITCHON] <computer>",
"[TURNTO] <computer>",
"[LOOKAT] <computer>",
"[FIND] <mouse>",
"[PUSH] <mouse>",
"[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:['food_bread', 'tablelamp', 'walllamp', 'ground_coffee', 'ceilingfan', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'desk', 'mat', 'faucet', 'couch', 'pillow', 'wall', 'pasta', 'wall_clock', 'cup', 'photoframe', 'bed', 'television', 'water', 'wine', 'curtain', 'paper_towel', 'sink', 'bathroom_cabinet', '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>']
}
|
Scene_Objects:['mop', 'microwave', 'bathroom', 'detergent', 'wallshelf', 'clothes_underwear', 'hanger', 'ceiling', 'bookshelf', 'tvstand', 'faucet', 'deck_of_cards', 'window', 'clothes_socks', 'clothes_pants', 'cup', 'standingmirror', 'photoframe', 'check', 'tray', 'kitchen_counter', 'hair', 'laundry_detergent', 'door', 'bathroom_cabinet', 'tooth_paste', 'clothes_shirt', 'washing_machine', 'coffee', 'shoe_rack']
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>"
]
} |
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', 'detergent', 'orchid', 'wallshelf', 'floor', 'ceiling', 'tea_bag', 'stovefan', 'toaster', 'faucet', 'shower', 'foundation', 'tooth_paste', 'closetdrawer', 'candle', 'nightstand', 'cup', 'coffe_maker', 'food_food', 'television', 'coffee_filter', 'tray', 'curtain', 'rag', 'clothes_scarf', 'table', 'soap', 'instrument_violin', 'dirt', 'hands_both']
Task:Wash hands
response:
{
"thoughts": Wash hands with soap,
"actions": ['[WALK] <bathroom>', '[WALK] <soap>', '[FIND] <soap>', '[GRAB] <soap>', '[FIND] <hands_both>', '[SCRUB] <hands_both>', '[WASH] <hands_both>', '[RINSE] <hands_both>']
}
|
Scene_Objects:['pot', 'scissors', 'tablelamp', 'food_ice_cream', 'toilet', 'bathroom', 'toothbrush', 'orchid', 'hanger', 'bathroom_counter', 'floor', 'ceilinglamp', 'faucet', 'clothes_socks', 'closetdrawer', 'tape', 'cup', 'check', 'food_food', 'razor', 'food_onion', 'centerpiece', 'mouse', 'dresser', 'bathtub', 'bathroom_cabinet', 'light', 'clothes_skirt', 'tooth_paste', 'shoe_rack']
Task:Brush teeth
response:
| {
"thoughts": "EARLY MORNING AND BEFORE GOING TO BED",
"actions": [
"[WALK] <bathroom>",
"[WALK] <tooth_paste>",
"[FIND] <tooth_paste>",
"[GRAB] <tooth_paste>",
"[FIND] <toothbrush>",
"[GRAB] <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', 'filing_cabinet', 'microwave', 'ground_coffee', 'knifeblock', 'wallshelf', 'ceiling', 'phone', 'character', 'desk', 'piano_bench', 'stovefan', 'toaster', 'couch', 'clothes_hat', 'pillow', 'bench', 'oven', 'tape', 'cutting_board', 'doorjamb', 'cards', 'mouse', 'dishrack', 'cupboard', 'hairdryer', 'sink', 'clothes_scarf', 'table', 'dishwasher']
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>']
}
|
Scene_Objects:['sheets', 'spectacles', 'sponge', 'beer', 'chair', 'freezer', 'detergent', 'food_butter', 'cpuscreen', 'hanger', 'bedroom', 'desk', 'bookshelf', 'table_cloth', 'toaster', 'ceilinglamp', 'shower', 'iron', 'window', 'wall', 'oven', 'food_food', 'razor', 'food_rice', 'curtain', 'kitchen_counter', 'food_steak', 'door', 'spoon', 'bathroom_cabinet']
Task:Listen to music
response:
| {
"thoughts": "I pull up my online classes on the computer to look at what the assigned reading is. I get my textbook, notebook, and mechanical pencil. As I'm reading, I take notes over important points. I then use those notes to complete the assignment for the week. Frequently that involves writing a post on an online discussion board that answers a question related to things from the reading.",
"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', 'chair', 'band-aids', 'walllamp', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'iron', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'novel', 'television', 'doorjamb', 'coffee_pot', 'mouse', 'dresser', 'door']
Task:Browse internet
response:
{
"thoughts": Go to home office, turn on the computer, open the internet and browse around the internet.,
"actions": ['[WALK] <home_office>', '[WALK] <computer>', '[SWITCHON] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>']
}
|
Scene_Objects:['beer', 'toilet', 'chair', 'walllamp', 'blow_dryer', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'mousepad', 'closetdrawer', 'food_orange', 'wall', 'powersocket', 'cup', 'standingmirror', 'keys', 'television', 'curtain', 'doorjamb', 'mouse', 'dresser', 'door', 'light', 'table']
Task:Work
response:
| {
"thoughts": "turn computer on, open application to work with",
"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:['chair', 'walllamp', 'bathroom', 'detergent', 'dough', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'character', 'desk', 'keyboard', 'thread', 'computer', 'ceilinglamp', 'mousepad', 'closetdrawer', 'wall', 'powersocket', 'photoframe', 'toilet_paper', 'television', 'razor', 'coin', 'doorjamb', 'mouse', 'kitchen_counter', 'dresser', 'light', 'table']
Task:Turn on computer
response:
{
"thoughts": Push power button.,
"actions": ['[WALK] <home_office>', '[WALK] <computer>', '[SWITCHON] <computer>']
}
|
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>"
]
} |
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', 'walllamp', 'drawing', 'wallshelf', 'food_egg', 'hanger', 'cpuscreen', 'floor', 'ceiling', 'character', 'keyboard', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'faucet', 'window', 'toaster', 'closetdrawer', 'couch', 'pillow', 'wall', 'nightstand', 'bed', 'television', 'curtain', 'doorjamb', 'dresser', 'light', 'table']
Task:Relax on sofa
response:
{
"thoughts": I walk into the living room and turn on the light. I walk to the couch then sit on the couch.,
"actions": ['[WALK] <home_office>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>', '[WALK] <couch>', '[SIT] <couch>']
}
|
Scene_Objects:['pot', 'food_salt', 'microwave', 'toilet', 'chair', 'blow_dryer', 'hanger', 'bathroom_counter', 'ceiling', 'phone', 'desk', 'mail', 'shoe-shine_kit', 'mousepad', 'food_noodles', 'cutting_board', 'cup', 'photoframe', 'bed', 'coffe_maker', 'television', 'curtain', 'centerpiece', 'comb', 'pajamas', 'clothes_dress', 'door', 'home_office', 'light', 'table']
Task:Pet cat
response:
| {
"thoughts": "Walk into the living room, sit down by the cat, put out hand, stroke the cat from head to tail",
"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:['microwave', 'walllamp', 'orchid', 'drawing', 'floor', 'ceiling', 'toaster', 'food_noodles', 'mousepad', 'food_peanut_butter', 'wall', 'oven', 'cup', 'bed', 'photoframe', 'coffe_maker', 'toilet_paper', 'television', 'coffee_filter', 'ice', 'curtain', 'console', 'kitchen_counter', 'cupboard', 'sink', 'clothes_scarf', 'dishwasher', 'soap', 'dirt', 'coffee']
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', 'filing_cabinet', 'toilet', 'freezer', 'bathroom', 'detergent', 'bathroom_counter', 'floor', 'bedroom', 'toaster', 'plate', 'shower', 'dining_room', 'nightstand', 'oven', 'cup', 'coffe_maker', 'food_food', 'television', 'tray', 'kitchen_counter', 'dresser', 'door', 'sink', 'bathtub', 'home_office', 'table', 'dishwasher', 'soap', 'board_game']
Task:Wash dishes with dishwasher
response:
| {
"thoughts": "Walk to Kitchen, find dishwasher. Find vessels to be washed. Open dishwasher, put vessels in dish washer, close dish washer and switch it on.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <dishwasher>",
"[FIND] <dishwasher>",
"[OPEN] <dishwasher>",
"[FIND] <cup>",
"[GRAB] <cup>",
"[PUTBACK] <cup> <dishwasher>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[GRAB] <cup>",
"[PUTBACK] <cup> <plate>",
"[GRAB] <cup>",
"[PUTBACK] <cup> <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', 'microwave', 'toilet', 'jelly', 'freezer', 'ground_coffee', 'food_carrot', 'drawing', 'wallshelf', 'floor', 'ceiling', 'phone', 'button', 'mat', 'shower', 'picture', 'dustpan', 'food_orange', 'form', 'nightstand', 'wall', 'powersocket', 'food_cheese', 'photoframe', 'light_bulb', 'food_food', 'doorjamb', 'cd', 'door', 'light']
Task:Added meat to freezer
response:
{
"thoughts": After shopping for groceries, i returned home, i walked to the dining room and placed meat items in freezer located in the dining room. I opened up the bags from the grocery store, removed all the meat items, and after opening the freezer door, i placed the meat items into the freezer, and closed the door.,
"actions": ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <food_food>', '[GRAB] <food_food>', '[PUTBACK] <food_food> <freezer>', '[CLOSE] <freezer>']
}
|
Scene_Objects:['sheets', 'spectacles', 'scissors', 'knife', 'hanger', 'bathroom_counter', 'floor', 'bedroom', 'desk', 'keyboard', 'piano_bench', 'stovefan', 'stereo', 'window', 'wall', 'powersocket', 'cutting_board', 'cup', 'bed', 'console', 'pencil', 'shoes', 'door', 'bathtub', 'bag', 'instrument_guitar', 'table', 'home_office', 'light', 'board_game']
Task:Listen to music
response:
| {
"thoughts": "I walk into my room and turn the radio on so that I can listen to music.",
"actions": [
"[WALK] <bedroom>",
"[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', 'drawing', 'wallshelf', 'floor', 'ceiling', 'shampoo', 'character', 'desk', 'bookshelf', 'mat', 'deck_of_cards', 'couch', 'pillow', 'wall', 'powersocket', 'cup', 'food_cheese', 'photoframe', 'bed', 'coffee_filter', 'wine', 'curtain', 'doorjamb', 'kitchen_counter', 'pajamas', 'door', 'food_steak', 'bag', 'light', 'electrical_outlet']
Task:Turn on light
response:
{
"thoughts": I walk to the living room. I find the electric outlet. I switch on the light.,
"actions": ['[WALK] <home_office>', '[WALK] <electrical_outlet>', '[FIND] <electrical_outlet>', '[FIND] <light>', '[SWITCHON] <light>']
}
|
Scene_Objects:['spectacles', 'pot', 'filing_cabinet', 'beer', 'crayon', 'walllamp', 'drawing', 'food_egg', 'bathroom_counter', 'floor', 'bookshelf', 'mat', 'iron', 'electric_shaver', 'window', 'closetdrawer', 'couch', 'pillow', 'wall', 'toy', 'cup', 'light_bulb', 'novel', 'food_food', 'check', 'toothbrush_holder', 'television', 'curtain', 'doorjamb', 'table']
Task:Read book
response:
| {
"thoughts": "I go to the book case, I select a book, I go back and sit down, then I read.",
"actions": [
"[WALK] <filing_cabinet>",
"[FIND] <novel>",
"[GRAB] <novel>",
"[WALK] <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:['tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'toaster', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'television', 'doorjamb', 'mouse', 'dresser', 'door', 'dishwasher']
Task:Work
response:
{
"thoughts": Sit at my computer desk, Turn on Computer. Get online. Work.,
"actions": ['[WALK] <home_office>', '[WALK] <chair>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[FIND] <keyboard>', '[TYPE] <keyboard>']
}
|
Scene_Objects:['chair', 'toothbrush', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'desk', 'keyboard', 'computer', 'table_cloth', 'toaster', 'laptop', 'shower', 'mousepad', 'closetdrawer', 'dustpan', 'dining_room', 'wall', 'powersocket', 'food_cheese', 'coffe_maker', 'check', 'wooden_spoon', 'doorjamb', 'mouse', 'dresser', 'door', 'maindoor', 'food_steak', 'light']
Task:Work
response:
| {
"thoughts": "first ill go to my home office adn ill switch on my laptop and with the use of mouse and keyboard il run my computer",
"actions": [
"[WALK] <home_office>",
"[WALK] <laptop>",
"[FIND] <laptop>",
"[SWITCHON] <laptop>",
"[FIND] <keyboard>",
"[GRAB] <keyboard>",
"[FIND] <mouse>",
"[TOUCH] <mouse>",
"[RUN] <laptop>"
]
} |
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', 'milk', 'toothbrush', 'drawing', 'orchid', 'cpuscreen', 'character', 'bedroom', 'stovefan', 'toaster', 'mousepad', 'clothes_pants', 'food_kiwi', 'wall_clock', 'bed', 'television', 'toothbrush_holder', 'water', 'tray', 'curtain', 'pencil', 'kitchen_counter', 'shoes', 'hairbrush', 'cupboard', 'bathroom_cabinet', 'home_office', 'tooth_paste', 'dirt']
Task:Brush teeth
response:
{
"thoughts": today morning i went to bathroom and took my toothbrush and paste from tooth brush holder and brushed and cleaned my teeth well,
"actions": ['[WALK] <bathroom>', '[WALK] <toothbrush_holder>', '[FIND] <toothbrush_holder>', '[FIND] <tooth_paste>', '[GRAB] <tooth_paste>', '[FIND] <toothbrush>', '[GRAB] <toothbrush>', '[PUTBACK] <tooth_paste> <toothbrush_holder>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <toothbrush>']
}
|
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>"
]
} |
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', 'walllamp', 'bathroom', 'knife', 'cpuscreen', 'hanger', 'floor', 'phone', 'desk', 'keyboard', 'thread', 'computer', 'piano_bench', 'toaster', 'laptop', 'ceilinglamp', 'mousepad', 'closetdrawer', 'pillow', 'wall', 'wall_clock', 'box', 'console', 'mouse', 'dresser', 'maindoor', 'hairdryer', 'board_game']
Task:Write an email
response:
{
"thoughts": I open my laptop and then login to Windows. Then I open Google Chrome, and type gmail.com into the address bar. My email automatically logs in, then I click the Compose button, type in the address of the recipient, then the subject of the email, and then start typing my email,
"actions": ['[WALK] <laptop>', '[SWITCHON] <laptop>', '[FIND] <keyboard>', '[TYPE] <keyboard>']
}
|
Scene_Objects:['chair', 'walllamp', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'desk', 'keyboard', 'computer', 'button', 'bookmark', 'mat', 'picture', 'window', 'mousepad', 'closetdrawer', 'couch', 'pillow', 'dining_room', 'wall', 'powersocket', 'novel', 'check', 'television', 'curtain', 'doorjamb', 'mouse', 'dresser', 'light', 'table']
Task:Read book
response:
| {
"thoughts": "Find book, grab book, fin bookmark, sit down somewhere comfortable, open book, read book, close book after reading.",
"actions": [
"[WALK] <desk>",
"[FIND] <novel>",
"[FIND] <bookmark>",
"[GRAB] <bookmark>",
"[FIND] <couch>",
"[SIT] <couch>",
"[GRAB] <novel>",
"[READ] <novel>",
"[PUTBACK] <bookmark> <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:['dry_pasta', 'scissors', 'chair', 'hanger', 'phone', 'keyboard', 'bookshelf', 'plate', 'faucet', 'window', 'mousepad', 'food_noodles', 'oil', 'food_peanut_butter', 'clothes_pants', 'dining_room', 'bench', 'oven', 'cutting_board', 'toy', 'basket_for_clothes', 'cup', 'photoframe', 'keys', 'food_food', 'laundry_detergent', 'bathroom_cabinet', 'instrument_violin', '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:['tablelamp', 'jelly', 'drawing', 'floor', 'bedroom', 'table_cloth', 'stovefan', 'mat', 'plate', 'window', 'couch', 'wall', 'nightstand', 'wall_clock', 'cutting_board', 'bed', 'novel', 'tray', 'curtain', 'doorjamb', 'diary', 'mouse', 'pencil', 'cd', 'clothes_dress', 'bathroom_cabinet', 'table', 'light', 'vase', 'laser_pointer']
Task:Read book
response:
| {
"thoughts": "I would go lie down in my bed and open the book and start reading.",
"actions": [
"[WALK] <bedroom>",
"[WALK] <bed>",
"[FIND] <bed>",
"[LIE] <bed>",
"[FIND] <novel>",
"[GRAB] <novel>",
"[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:['sheets', 'filing_cabinet', 'crayon', 'dog', 'freezer', 'knife', 'orchid', 'bathroom_counter', 'character', 'bedroom', 'faucet', 'couch', 'food_orange', 'towel', 'nightstand', 'oven', 'powersocket', 'photoframe', 'check', 'video_game_controller', 'food_donut', 'food_rice', 'food_onion', 'diary', 'dresser', 'hairbrush', 'clothes_scarf', 'napkin', 'bathroom_cabinet', 'colander']
Task:Pet cat
response:
{
"thoughts": Walk into the living room. Walk up to the cat. Pet the cat with your hand.,
"actions": ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[TOUCH] <cat>']
}
|
Scene_Objects:['filing_cabinet', 'toilet', 'chair', 'dog', 'cat', 'dough', 'clothes_underwear', 'folder', 'closetdrawer', 'couch', 'food_orange', 'broom', 'oven', 'powersocket', 'toy', 'photoframe', 'bed', 'check', 'razor', 'curtain', 'lighter', 'mouse', 'pencil', 'kitchen_counter', 'dresser', 'door', 'sink', 'clothes_scarf', 'napkin', 'shoe_rack']
Task:Wash dishes with dishwasher
response:
| {
"thoughts": "I walk to the kitchen. I take plate. I open the dishwasher. I put plate in the dishwasher. I switch on the dishwasher.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <plate>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[WALK] <dishwasher>",
"[OPEN] <dishwasher>",
"[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:['food_salt', 'microwave', 'trashcan', 'hanger', 'floor', 'bedroom', 'computer', 'button', 'brush', 'mat', 'shower', 'faucet', 'window', 'clothes_hat', 'wall', 'child', 'oven', 'bed', 'newspaper', 'novel', 'curtain', 'centerpiece', 'doorjamb', 'mouse', 'cd', 'dresser', 'hairdryer', 'clothes_scarf', 'vase', 'board_game']
Task:Story reading time
response:
{
"thoughts": Sit on bed with child, open mother goose, pick story, read book, point at the pretty pictures,
"actions": ['[WALK] <bedroom>', '[WALK] <child>', '[FIND] <child>', '[GREET] <child>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <bed>', '[SIT] <bed>', '[TURNTO] <child>', '[LOOKAT] <child>', '[TURNTO] <novel>', '[POINTAT] <novel>', '[READ] <novel>']
}
|
Scene_Objects:['glue', 'tablelamp', 'mop', 'toilet', 'chair', 'walllamp', 'bathroom', 'food_carrot', 'hanger', 'floor', 'shampoo', 'bookshelf', 'purse', 'computer', 'stovefan', 'toaster', 'shower', 'mousepad', 'dustpan', 'clothes_pants', 'wall', 'cutting_board', 'standingmirror', 'television', 'oven_mitts', 'curtain', 'doorjamb', 'hairbrush', 'door', 'bathtub']
Task:Go to toilet
response:
| {
"thoughts": "Walk to the bathroom. Pull down pants. Use the toilet.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <clothes_pants>",
"[FIND] <clothes_pants>",
"[PULL] <clothes_pants>",
"[FIND] <toilet>",
"[SIT] <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:['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>']
}
|
Scene_Objects:['tablelamp', 'food_ice_cream', 'toilet', 'chair', 'walllamp', 'floor', 'ceiling', 'phone', 'desk', 'bookshelf', 'shower', 'mousepad', 'food_peanut_butter', 'food_jam', 'wall', 'bench', 'powersocket', 'toy', 'box', 'standingmirror', 'coffe_maker', 'water', 'doorjamb', 'cards', 'kitchen_counter', 'sink', 'bathroom_cabinet', 'light', 'soap', 'board_game']
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>"
]
} |
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', 'toilet', 'walllamp', 'cat', 'orchid', 'floor', 'ceiling', 'remote_control', 'computer', 'food_bacon', 'tvstand', 'window', 'mousepad', 'closetdrawer', 'couch', 'pillow', 'nightstand', 'wall', 'mouthwash', 'television', 'coin', 'food_rice', 'tray', 'curtain', 'doorjamb', 'kitchen_counter', 'dresser', 'table', 'soap']
Task:Watch TV
response:
{
"thoughts": Walk into the living room/den. Turn on the television. Switch channels to find a program with remote. I find a program and look at the screen.,
"actions": ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <remote_control>', '[TURNTO] <remote_control>', '[TURNTO] <television>', '[LOOKAT] <television>']
}
|
Scene_Objects:['food_ice_cream', 'band-aids', 'dough', 'food_carrot', 'drawing', 'bookshelf', 'stovefan', 'shower', 'oil', 'towel', 'dining_room', 'wall', 'bench', 'toy', 'shelf', 'box', 'cup', 'bed', 'photoframe', 'check', 'coffe_maker', 'food_food', 'food_rice', 'kettle', 'shoes', 'door', 'bathtub', 'home_office', 'vase', 'soap']
Task:Wash hands
response:
| {
"thoughts": "BEFORE EATING",
"actions": [
"[WALK] <bathroom>",
"[WALK] <soap>",
"[FIND] <soap>",
"[GRAB] <soap>",
"[FIND] <towel>",
"[WIPE] <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:['filing_cabinet', 'juice', 'walllamp', 'food_carrot', 'knife', 'orchid', 'cpuscreen', 'phone', 'dvd_player', 'desk', 'mop_bucket', 'toaster', 'laptop', 'tvstand', 'closetdrawer', 'food_jam', 'pillow', 'dining_room', 'food_food', 'television', 'oven_mitts', 'water', 'after_shave', 'pencil', 'hairbrush', 'clothes_dress', 'door', 'table', 'dishwasher', 'light']
Task:Drink
response:
{
"thoughts": I go to the kitchen. I get a glass. I fill it with water. I take a drink from the glass.,
"actions": ['[WALK] <dining_room>', '[WALK] <cup>', '[FIND] <cup>', '[GRAB] <cup>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <cup>', '[DRINK] <cup>']
}
|
Scene_Objects:['walllamp', 'toothbrush', 'wallshelf', 'cpuscreen', 'bathroom_counter', 'floor', 'phone', 'bedroom', 'thread', 'stovefan', 'mat', 'ceilinglamp', 'faucet', 'plate', 'dining_room', 'wall', 'wall_clock', 'oven', 'toothbrush_holder', 'tray', 'doorjamb', 'towel_rack', 'chessboard', 'dresser', 'door', 'sink', 'bathroom_cabinet', 'clothes_skirt', 'tooth_paste', 'teeth']
Task:Brush teeth
response:
| {
"thoughts": "getting ready for bed",
"actions": [
"[WALK] <bathroom_counter>",
"[FIND] <toothbrush>",
"[GRAB] <toothbrush>",
"[PUTBACK] <toothbrush> <bathroom_counter>",
"[FIND] <tooth_paste>",
"[SQUEEZE] <tooth_paste>",
"[GRAB] <toothbrush>",
"[SCRUB] <toothbrush>",
"[RINSE] <toothbrush>",
"[FIND] <toothbrush_holder>",
"[PUTBACK] <toothbrush> <toothbrush_holder>"
]
} |
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', 'toilet', 'trashcan', 'ceilingfan', 'drawing', 'hanger', 'floor', 'ceiling', 'bookshelf', 'thread', 'computer', 'piano_bench', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'foundation', 'clothes_pants', 'pillow', 'dining_room', 'wall', 'oven', 'bed', 'novel', 'check', 'television', 'curtain', 'towel_rack', 'dresser', 'vase']
Task:Read book
response:
{
"thoughts": Put child in bed, sit down,read book.,
"actions": ['[WALK] <bedroom>', '[WALK] <dresser>', '[OPEN] <dresser>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <bed>', '[SIT] <bed>', '[READ] <novel>']
}
|
Scene_Objects:['fork', 'glue', 'food_ice_cream', 'food_salt', 'tea', 'drawing', 'knife', 'cpuscreen', 'phone', 'desk', 'computer', 'button', 'plate', 'iron', 'dish_soap', 'mousepad', 'nightstand', 'powersocket', 'curtain', 'kitchen_counter', 'dishrack', 'dresser', 'spoon', 'napkin', 'table', 'dishwasher', 'home_office', 'vase', 'bathroom_cabinet', 'coffee']
Task:Wash dishes with dishwasher
response:
| {
"thoughts": "put forks, spoons, plates, knife in dishwasher, add dish soap, turn diswaser on",
"actions": [
"[WALK] <dining_room>",
"[WALK] <dishwasher>",
"[FIND] <dishwasher>",
"[OPEN] <dishwasher>",
"[FIND] <dish_soap>",
"[GRAB] <dish_soap>",
"[PUTBACK] <dish_soap> <dishwasher>",
"[FIND] <fork>",
"[GRAB] <fork>",
"[FIND] <dishrack>",
"[PUTBACK] <fork> <dishrack>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[PUTBACK] <plate> <dishrack>",
"[FIND] <spoon>",
"[GRAB] <spoon>",
"[PUTBACK] <spoon> <dishrack>",
"[FIND] <knife>",
"[GRAB] <knife>",
"[PUTBACK] <knife> <dishrack>",
"[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', 'microwave', 'toilet', 'jelly', 'ceilingfan', 'food_carrot', 'drawing', 'knife', 'clothes_underwear', 'floor', 'phone', 'ceilinglamp', 'tvstand', 'stereo', 'window', 'mousepad', 'couch', 'food_jam', 'wall', 'nightstand', 'cup', 'television', 'ice', 'mouse', 'kitchen_counter', 'home_office', 'table', 'soap', 'board_game', 'shoe_rack']
Task:Listen to music
response:
{
"thoughts": sitting down to listen to music on the radio,
"actions": ['[WALK] <home_office>', '[WALK] <stereo>', '[FIND] <stereo>', '[SWITCHON] <stereo>', '[FIND] <couch>', '[SIT] <couch>']
}
|
Scene_Objects:['drawing', 'orchid', 'wallshelf', 'hanger', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'computer', 'mat', 'ceilinglamp', 'deck_of_cards', 'window', 'homework', 'closetdrawer', 'couch', 'pillow', 'wall', 'standingmirror', 'newspaper', 'photoframe', 'food_food', 'television', 'food_donut', 'curtain', 'doorjamb', 'towel_rack', 'bag', 'table', 'light']
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>"
]
} |
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', 'microwave', 'toilet', 'chair', 'freezer', 'walllamp', 'detergent', 'hanger', 'floor', 'ceiling', 'phone', 'keyboard', 'computer', 'food_bacon', 'alcohol', 'ceilinglamp', 'pillow', 'wall', 'powersocket', 'bed', 'curtain', 'doorjamb', 'kettle', 'mouse', 'dresser', 'cupboard', 'door', 'maindoor', 'light', 'creditcard']
Task:Turn on light
response:
{
"thoughts": I open the room door and press the light button on,
"actions": ['[WALK] <home_office>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>']
}
|
Scene_Objects:['bathroom', 'detergent', 'milk', 'floor', 'folder', 'bedroom', 'tea_bag', 'remote_control', 'button', 'mat', 'plate', 'shower', 'closetdrawer', 'pillow', 'nightstand', 'toy', 'standingmirror', 'clothes_gloves', 'keys', 'food_food', 'tray', 'after_shave', 'towel_rack', 'shoes', 'maindoor', 'bathtub', 'sink', 'light', 'table', 'scrabble']
Task:Change TV channel
response:
| {
"thoughts": "Walk into living room. Find television remote control. Pick up remote control. Press button.",
"actions": [
"[WALK] <home_office>",
"[WALK] <remote_control>",
"[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:['fork', 'pot', 'blender', 'crayon', 'microwave', 'cat', 'drawing', 'orchid', 'needle', 'phone', 'stovefan', 'ceilinglamp', 'tvstand', 'shower', 'food_jam', 'dining_room', 'powersocket', 'bed', 'photoframe', 'coffe_maker', 'television', 'diary', 'shoes', 'comb', 'controller', 'food_steak', 'instrument_violin', 'sink', 'dishwasher', 'board_game']
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>']
}
|
Scene_Objects:['filing_cabinet', 'band-aids', 'freezer', 'orchid', 'drawing', 'cpuscreen', 'bills', 'floor', 'ceiling', 'character', 'bookshelf', 'mop_bucket', 'mat', 'deck_of_cards', 'faucet', 'window', 'electric_shaver', 'couch', 'pillow', 'wall', 'nightstand', 'cup', 'television', 'coffee_filter', 'curtain', 'doorjamb', 'mouse', 'conditioner', 'bathroom_cabinet', 'table']
Task:Relax on sofa
response:
| {
"thoughts": "walk to living room ,find sofa ,sit on 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', 'toilet', 'jelly', 'band-aids', 'chair', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'shampoo', 'ceiling', 'desk', 'keyboard', 'purse', 'brush', 'toaster', 'shoe-shine_kit', 'plate', 'faucet', 'mousepad', 'towel', 'dining_room', 'wall', 'photoframe', 'newspaper', 'coffe_maker', 'toothbrush_holder', 'mouse', 'door', 'home_office']
Task:Go to toilet
response:
{
"thoughts": I walk into the bathroom. I walk over to the toilet. I sit on the toilet.,
"actions": ['[WALK] <bathroom>', '[WALK] <toilet>', '[SIT] <toilet>']
}
|
Scene_Objects:['beer', 'tea', 'chair', 'walllamp', 'ground_coffee', 'bills', 'orchid', 'bathroom_counter', 'floor', 'phone', 'ceiling', 'mail', 'ceilinglamp', 'mat', 'iron', 'stereo', 'faucet', 'clothes_socks', 'clothes_hat', 'basket_for_clothes', 'food_rice', 'curtain', 'lighter', 'doorjamb', 'towel_rack', 'vacuum_cleaner', 'dishrack', 'cd', 'napkin', 'home_office']
Task:Turn on light
response:
| {
"thoughts": "I go to bedroom and locate a lamp. This lamp can be turned on by touch, as it has capacitive sensing. So I do it.",
"actions": [
"[WALK] <bedroom>",
"[WALK] <floor_lamp>",
"[FIND] <floor_lamp>",
"[TOUCH] <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:['knife', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'folder', 'desk', 'keyboard', 'computer', 'mat', 'stereo', 'mousepad', 'closetdrawer', 'clothes_pants', 'wall', 'powersocket', 'cup', 'newspaper', 'novel', 'tray', 'mouse', 'kitchen_counter', 'dresser', 'bathtub', 'spoon', 'light', 'soap', 'board_game', 'clothes_shirt', 'scrabble']
Task:Get dressed
response:
{
"thoughts": Pick out the clothes you are going to wear and put them on your body,
"actions": ['[WALK] <bedroom>', '[WALK] <dresser>', '[OPEN] <dresser>', '[FIND] <clothes_pants>', '[GRAB] <clothes_pants>', '[PUTON] <clothes_pants>', '[FIND] <clothes_shirt>', '[GRAB] <clothes_shirt>', '[PUTON] <clothes_shirt>', '[CLOSE] <dresser>']
}
|
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>"
]
} |
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', 'mop', 'chair', 'bathroom', 'drawing', 'wallshelf', 'character', 'bedroom', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'shower', 'faucet', 'floor_lamp', 'mousepad', 'closetdrawer', 'nightstand', 'wall', 'oven', 'bench', 'photoframe', 'bed', 'coffe_maker', 'food_food', 'check', 'conditioner', 'light', 'table', 'tooth_paste']
Task:Turn on light
response:
{
"thoughts": walk to living room, find lamp, switch on.,
"actions": ['[WALK] <home_office>', '[WALK] <floor_lamp>', '[FIND] <floor_lamp>']
}
|
Scene_Objects:['jelly', 'freezer', 'dog', 'chair', 'nail_polish', 'bathroom', 'orchid', 'bills', 'food_egg', 'hanger', 'character', 'bedroom', 'thread', 'toaster', 'faucet', 'mousepad', 'oil', 'nightstand', 'cup', 'photoframe', 'standingmirror', 'bed', 'video_game_controller', 'wine', 'doorjamb', 'maindoor', 'bathtub', 'vase', 'clothes_shirt', 'coffee']
Task:Read book
response:
| {
"thoughts": "pick up the book open the book and read",
"actions": [
"[WALK] <bedroom>",
"[WALK] <novel>",
"[GRAB] <novel>",
"[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', '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:['scissors', 'toilet', 'freezer', 'bathroom', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'bedroom', 'thread', 'stovefan', 'mat', 'faucet', 'towel', 'dining_room', 'wall', 'wall_clock', 'oven', 'bench', 'nightstand', 'check', 'coffee_filter', 'tray', 'shaving_cream', 'towel_rack', 'pencil', 'mouse', 'sink', 'bathroom_cabinet', 'soap']
Task:Wash hands
response:
| {
"thoughts": "I walk into the bathroom. Walk to the sink. Turn on tap. Get soap. Wash and rinse hands. Turn off tap. Dry hands.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <sink>",
"[FIND] <sink>",
"[TURNTO] <sink>",
"[LOOKAT] <sink>",
"[WALK] <sink>",
"[FIND] <faucet>",
"[SWITCHON] <faucet>",
"[FIND] <soap>",
"[GRAB] <soap>",
"[RINSE] <soap>",
"[SWITCHOFF] <faucet>",
"[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:['sponge', 'toilet', 'freezer', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'keyboard', 'ceilinglamp', 'mat', 'shower', 'food_noodles', 'couch', 'towel', 'wall', 'powersocket', 'oven', 'cutting_board', 'photoframe', 'newspaper', 'water', 'food_donut', 'curtain', 'doorjamb', 'headset', 'door', 'bathroom_cabinet', 'light', 'soap', 'tooth_paste']
Task:Take shower
response:
{
"thoughts": Walk into bathroom. Turn on shower. Take off clothing. Climb into shower. Rinse with water. Soap up body. Rinse off with water. Turn off shower. Climb out of shower. Dry off with towel.,
"actions": ['[WALK] <bathroom>', '[WALK] <shower>', '[FIND] <shower>', '[TURNTO] <shower>', '[FIND] <water>', '[RINSE] <water>', '[FIND] <soap>', '[WASH] <soap>', '[RINSE] <water>', '[FIND] <towel>', '[GRAB] <towel>', '[SCRUB] <towel>']
}
|
Scene_Objects:['scissors', 'dog', 'walllamp', 'drawing', 'hanger', 'floor', 'ceiling', 'remote_control', 'envelope', 'computer', 'table_cloth', 'mat', 'ceilinglamp', 'window', 'food_noodles', 'closetdrawer', 'couch', 'pillow', 'wall', 'bench', 'standingmirror', 'television', 'tray', 'curtain', 'doorjamb', 'console', 'cd', 'napkin', 'table', 'clothes_shirt']
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>"
]
} |
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', 'beer', 'walllamp', 'knifeblock', 'cpuscreen', 'floor', 'bookshelf', 'mail', 'computer', 'button', 'toaster', 'plate', 'shower', 'dish_soap', 'mousepad', 'pillow', 'wall', 'oven', 'photoframe', 'clothes_gloves', 'coffe_maker', 'tray', 'food_onion', 'doorjamb', 'dresser', 'hairdryer', 'sink', 'dishwasher', 'clothes_shirt']
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>']
}
|
Scene_Objects:['microwave', 'chair', 'freezer', 'walllamp', 'bathroom', 'floor', 'ceiling', 'keyboard', 'stovefan', 'electric_shaver', 'clothes_socks', 'form', 'wall', 'nightstand', 'oven', 'cutting_board', 'coffe_maker', 'food_food', 'oven_mitts', 'food_donut', 'tray', 'doorjamb', 'kettle', 'mouse', 'kitchen_counter', 'laundry_detergent', 'home_office', 'table', 'bathroom_cabinet', 'instrument_guitar']
Task:Put groceries in Fridge
response:
| {
"thoughts": "go to the kitchen and put the groceries in the fridge",
"actions": [
"[WALK] <dining_room>",
"[WALK] <freezer>",
"[FIND] <freezer>",
"[OPEN] <freezer>",
"[FIND] <food_food>",
"[GRAB] <food_food>",
"[PUTIN] <food_food> <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:['dry_pasta', 'food_pizza', 'filing_cabinet', 'scissors', 'chair', 'ceilingfan', 'dough', 'drawing', 'orchid', 'floor', 'ceiling', 'phone', 'bookshelf', 'remote_control', 'stovefan', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'couch', 'food_orange', 'wall', 'powersocket', 'coffee_table', 'television', 'coin', 'wooden_spoon', 'curtain', 'maindoor', 'table']
Task:Watch TV
response:
{
"thoughts": I walk into the living room and sit on the couch. I pick up the remote to turn on the television. I put down the remote on the coffee table and look at the television.,
"actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <coffee_table>', '[PUTBACK] <remote_control> <coffee_table>', '[TURNTO] <television>', '[LOOKAT] <television>']
}
|
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>"
]
} |
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', 'orchid', 'wallshelf', 'floor', 'ceiling', 'shampoo', 'computer', 'mail', 'table_cloth', 'mat', 'tvstand', 'plate', 'couch', 'pillow', 'dining_room', 'food_kiwi', 'wall', 'nightstand', 'photoframe', 'check', 'television', 'curtain', 'after_shave', 'doorjamb', 'cards', 'mouse', 'shoes', 'sink']
Task:Relax on sofa
response:
{
"thoughts": I walk to the living room. I sit in the sofa and I relax.,
"actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>']
}
|
Scene_Objects:['crayon', 'walllamp', 'blow_dryer', 'detergent', 'orchid', 'bathroom_counter', 'ceiling', 'phone', 'computer', 'clothes_jacket', 'table_cloth', 'stovefan', 'faucet', 'shower', 'couch', 'clothes_pants', 'wall', 'wall_clock', 'oven', 'bench', 'bed', 'toothbrush_holder', 'tray', 'curtain', 'dresser', 'clothes_dress', 'sink', 'spoon', 'bathroom_cabinet', 'washing_machine']
Task:Wash clothes
response:
| {
"thoughts": "Walk to bathroom, open cabinet and collect clothes and put them into washing machine and wash clothes",
"actions": [
"[WALK] <bathroom>",
"[WALK] <bathroom_cabinet>",
"[FIND] <bathroom_cabinet>",
"[OPEN] <bathroom_cabinet>",
"[FIND] <clothes_dress>",
"[GRAB] <clothes_dress>",
"[FIND] <washing_machine>",
"[OPEN] <washing_machine>",
"[PUTBACK] <clothes_dress> <washing_machine>",
"[FIND] <clothes_pants>",
"[GRAB] <clothes_pants>",
"[PUTBACK] <clothes_pants> <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:['filing_cabinet', 'microwave', 'chair', 'walllamp', 'orchid', 'cpuscreen', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'mousepad', 'pillow', 'dining_room', 'wall', 'nightstand', 'powersocket', 'cutting_board', 'television', 'curtain', 'doorjamb', 'mouse', 'door', 'table']
Task:Watch youtube
response:
{
"thoughts": Go to youtube.Com watch videos,
"actions": ['[WALK] <home_office>', '[WALK] <chair>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>']
}
|
Scene_Objects:['dog', 'food_carrot', 'toothbrush', 'orchid', 'knife', 'hanger', 'floor', 'ceiling', 'bedroom', 'bookshelf', 'computer', 'ceilinglamp', 'tvstand', 'faucet', 'stereo', 'mousepad', 'pillow', 'towel', 'wall', 'nightstand', 'bench', 'cutting_board', 'cup', 'food_food', 'coffe_maker', 'television', 'food_donut', 'coffee_pot', 'towel_rack', 'soap']
Task:Listen to music
response:
| {
"thoughts": "walk into living room, walk to stereo, turn on stereo, 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:['microwave', 'dog', 'freezer', 'walllamp', 'cat', 'knifeblock', 'bills', 'desk', 'bookshelf', 'keyboard', 'computer', 'ceilinglamp', 'faucet', 'clothes_hat', 'broom', 'powersocket', 'bench', 'coffe_maker', 'food_food', 'television', 'mirror', 'rag', 'lighter', 'towel_rack', 'mouse', 'dresser', 'sink', 'table', 'clothes_skirt', 'shoe_rack']
Task:Clean mirror
response:
{
"thoughts": Spray glass cleaner on mirror. Wipe with a clean cloth.,
"actions": ['[WALK] <bathroom>', '[WALK] <cleaning_solution>', '[FIND] <cleaning_solution>', '[GRAB] <cleaning_solution>', '[WALK] <mirror>', '[PUTOBJBACK] <cleaning_solution>', '[FIND] <rag>', '[GRAB] <rag>', '[WALK] <mirror>', '[WIPE] <mirror>', '[WIPE] <mirror>', '[WIPE] <mirror>', '[PUTOBJBACK] <rag>']
}
|
Scene_Objects:['food_pizza', 'blender', 'beer', 'toilet', 'detergent', 'food_butter', 'phone', 'bookshelf', 'remote_control', 'alcohol', 'button', 'table_cloth', 'piano_bench', 'toaster', 'tvstand', 'pillow', 'nightstand', 'pasta', 'wall_clock', 'tape', 'coffe_maker', 'doorjamb', 'cards', 'pencil', 'controller', 'clothes_dress', 'maindoor', 'sink', 'home_office', 'light']
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>"
]
} |
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', 'scissors', 'tea', 'freezer', 'walllamp', 'knifeblock', 'knife', 'bills', 'floor', 'toaster', 'mat', 'plate', 'stereo', 'picture', 'tvstand', 'dish_soap', 'microphone', 'wall', 'oven', 'cup', 'light_bulb', 'coffe_maker', 'drinking_glass', 'tray', 'mouse', 'cupboard', 'controller', 'maindoor', 'spoon', 'dishwasher']
Task:Wash dishes with dishwasher
response:
{
"thoughts": Walk to the kitchen and turn to the dishwasher, put the knife, glass, fork and plate into the dishwasher. Turn on the dishwasher.,
"actions": ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[TURNTO] <dishwasher>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[OPEN] <dishwasher>', '[PUTBACK] <dish_soap> <dishwasher>', '[FIND] <drinking_glass>', '[GRAB] <drinking_glass>', '[PUTBACK] <drinking_glass> <dishwasher>', '[FIND] <fork>', '[GRAB] <fork>', '[PUTBACK] <fork> <dishwasher>', '[FIND] <knife>', '[GRAB] <knife>', '[PUTBACK] <knife> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>']
}
|
Scene_Objects:['tablelamp', 'food_salt', 'microwave', 'freezer', 'band-aids', 'walllamp', 'food_carrot', 'drawing', 'floor', 'ceiling', 'stovefan', 'ceilinglamp', 'tvstand', 'faucet', 'wall', 'nightstand', 'oven', 'cutting_board', 'cup', 'food_cheese', 'coffe_maker', 'coffee_filter', 'drinking_glass', 'tray', 'shaving_cream', 'kitchen_counter', 'dresser', 'sink', 'light', 'table']
Task:Drink
response:
| {
"thoughts": "Robot Drinks the water",
"actions": [
"[WALK] <dining_room>",
"[WALK] <freezer>",
"[FIND] <freezer>",
"[OPEN] <freezer>",
"[FIND] <drinking_glass>",
"[GRAB] <drinking_glass>",
"[DRINK] <drinking_glass>",
"[PUTOBJBACK] <drinking_glass>",
"[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:['cd_player', 'freezer', 'ground_coffee', 'bathroom', 'milk', 'orchid', 'cpuscreen', 'hanger', 'dvd_player', 'character', 'ceilinglamp', 'stereo', 'faucet', 'dustpan', 'clothes_hat', 'nightstand', 'wall', 'newspaper', 'check', 'mouthwash', 'video_game_controller', 'food_food', 'tray', 'doorjamb', 'pencil', 'cupboard', 'door', 'sink', 'home_office', 'dishwasher']
Task:Listen to music
response:
{
"thoughts": I walk in the living room, then I go the the stereo and the cd player and turn them on.,
"actions": ['[WALK] <home_office>', '[WALK] <stereo>', '[FIND] <stereo>', '[SWITCHON] <stereo>', '[FIND] <cd_player>', '[SWITCHON] <cd_player>']
}
|
Scene_Objects:['tablelamp', 'juice', 'toilet', 'chair', 'food_egg', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'character', 'desk', 'bookshelf', 'piano_bench', 'shower', 'faucet', 'stereo', 'electric_shaver', 'food_jam', 'wall', 'nightstand', 'wall_clock', 'shelf', 'bed', 'photoframe', 'novel', 'light_bulb', 'coffee_filter', 'board_game', 'laser_pointer', 'shoe_rack']
Task:Go to toilet
response:
| {
"thoughts": "Travel through the house and locate the bathroom, and proceed to the toilet.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <toilet>",
"[FIND] <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:['microwave', 'walllamp', 'orchid', 'ceiling', 'desk', 'computer', 'food_bacon', 'stovefan', 'ceilinglamp', 'plate', 'shower', 'faucet', 'window', 'form', 'dining_room', 'oven', 'basket_for_clothes', 'keys', 'novel', 'food_food', 'coffe_maker', 'food_rice', 'tray', 'doorjamb', 'cards', 'mouse', 'pajamas', 'home_office', 'light', 'bathroom_cabinet']
Task:Listen to music
response:
{
"thoughts": Find the playback device you want to listen to. turn on. press play. enjoyu music.,
"actions": ['[WALK] <bedroom>', '[WALK] <cd_player>', '[FIND] <cd_player>', '[SWITCHON] <cd_player>']
}
|
Scene_Objects:['fork', 'food_salt', 'food_butter', 'food_carrot', 'drawing', 'food_egg', 'floor', 'phone', 'ceiling', 'character', 'purse', 'mat', 'plate', 'window', 'mousepad', 'closetdrawer', 'couch', 'food_orange', 'bed', 'photoframe', 'tray', 'coffee_pot', 'kitchen_counter', 'shoes', 'pajamas', 'sink', 'spoon', 'bathtub', 'table', 'vase']
Task:Set up table
response:
| {
"thoughts": "Place your plate on the placemat. The forks will be placed on the left side of the plate and the knife and spoon on the right and place the spoon to the right of the knife. If you want to set out food, place them above the plate.",
"actions": [
"[WALK] <table>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[DROP] <plate>",
"[FIND] <fork>",
"[GRAB] <fork>",
"[DROP] <fork>",
"[FIND] <spoon>",
"[GRAB] <spoon>",
"[DROP] <spoon>"
]
} |
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', 'walllamp', 'knifeblock', 'orchid', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'bookshelf', 'bookmark', 'ceilinglamp', 'tvstand', 'balanceball', 'picture', 'mousepad', 'couch', 'wall', 'bed', 'food_food', 'tray', 'after_shave', 'rag', 'doorjamb', 'maindoor', 'bathroom_cabinet', 'dishwasher', 'vase']
Task:Put away groceries
response:
{
"thoughts": Place groceries in refrigerator from shopping at the grocery store.,
"actions": ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <food_food>', '[GRAB] <food_food>', '[PUTIN] <food_food> <freezer>', '[CLOSE] <freezer>']
}
|
Scene_Objects:['pot', 'microwave', 'freezer', 'walllamp', 'orchid', 'wallshelf', 'floor', 'ceiling', 'character', 'bedroom', 'mail', 'stovefan', 'faucet', 'stereo', 'couch', 'wall', 'oven', 'cutting_board', 'bed', 'newspaper', 'coffe_maker', 'food_food', 'tray', 'lighter', 'doorjamb', 'kitchen_counter', 'home_office', 'bathroom_cabinet', 'vase', 'soap']
Task:Put groceries in Fridge
response:
| {
"thoughts": "Walk to kitchen. Open fridge. Put groceries in fridge.",
"actions": [
"[WALK] <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:['pot', 'chair', 'freezer', 'walllamp', 'bathroom', 'food_butter', 'knifeblock', 'floor', 'ceiling', 'character', 'desk', 'food_cake', 'computer', 'bookmark', 'toaster', 'stovefan', 'mat', 'faucet', 'food_kiwi', 'wall', 'oven', 'powersocket', 'food_vegetable', 'bed', 'food_food', 'oven_mitts', 'tray', 'towel_rack', 'kitchen_counter', 'cupboard']
Task:Cook some food
response:
{
"thoughts": I prepare meals and cook them on the stove.,
"actions": ['[WALK] <dining_room>', '[WALK] <freezer>', '[OPEN] <freezer>', '[FIND] <food_vegetable>', '[GRAB] <food_vegetable>', '[CLOSE] <freezer>', '[FIND] <oven>', '[SWITCHON] <oven>', '[SWITCHOFF] <oven>']
}
|
Scene_Objects:['filing_cabinet', 'tablelamp', 'toilet', 'freezer', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'stovefan', 'mat', 'tvstand', 'faucet', 'toaster', 'teeth', 'towel', 'wall', 'wall_clock', 'oven', 'powersocket', 'food_food', 'tray', 'headset', 'comb', 'sink', 'clothes_scarf', 'bathroom_cabinet', 'instrument_guitar', 'soap', 'hands_both', 'creditcard']
Task:Wash hands
response:
| {
"thoughts": "Go to bathroom, turn on faucet, wet hands, apply soap, rub hands, rinse hands, turn off faucet, dry hands",
"actions": [
"[WALK] <bathroom>",
"[WALK] <faucet>",
"[FIND] <faucet>",
"[SWITCHON] <faucet>",
"[FIND] <hands_both>",
"[RINSE] <hands_both>",
"[FIND] <soap>",
"[GRAB] <soap>",
"[SCRUB] <hands_both>",
"[RINSE] <hands_both>",
"[SWITCHOFF] <faucet>",
"[FIND] <towel>",
"[GRAB] <towel>",
"[WIPE] <hands_both>",
"[PUTOBJBACK] <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:['glue', 'filing_cabinet', 'tablelamp', 'microwave', 'toilet', 'dog', 'walllamp', 'bathroom', 'knifeblock', 'food_egg', 'food_bacon', 'brush', 'mat', 'deck_of_cards', 'balanceball', 'tvstand', 'ceilinglamp', 'picture', 'couch', 'wall', 'tape', 'cup', 'toilet_paper', 'food_food', 'video_game_controller', 'water', 'cupboard', 'bathroom_cabinet', 'table', 'vase']
Task:Drink
response:
{
"thoughts": I go to the kitchen. I get a glass. I fill it with water. I take a drink from the glass.,
"actions": ['[WALK] <dining_room>', '[WALK] <cup>', '[FIND] <cup>', '[GRAB] <cup>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <cup>', '[DRINK] <cup>']
}
|
Scene_Objects:['food_pizza', 'food_salt', 'microwave', 'freezer', 'walllamp', 'floor', 'ceiling', 'bedroom', 'food_cake', 'mail', 'table_cloth', 'stovefan', 'mat', 'shower', 'closetdrawer', 'food_jam', 'wall', 'nightstand', 'oven', 'cutting_board', 'shelf', 'bed', 'photoframe', 'standingmirror', 'coffe_maker', 'food_food', 'tray', 'kitchen_counter', 'dresser', 'instrument_violin']
Task:Put groceries in Fridge
response:
| {
"thoughts": "Put groceries into 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:['food_ice_cream', 'toilet', 'walllamp', 'nail_polish', 'dough', 'orchid', 'wallshelf', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'keyboard', 'computer', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'wall', 'nightstand', 'powersocket', 'photoframe', 'television', 'curtain', 'doorjamb', 'cards', 'dishrack', 'door', 'light']
Task:Change TV channel
response:
{
"thoughts": first i will go to living room and then take the remote and swtitch on television after that il change the channel,
"actions": ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <remote_control>', '[TURNTO] <remote_control>', '[POINTAT] <remote_control>', '[TOUCH] <remote_control>', '[TURNTO] <television>', '[WATCH] <television>']
}
|
Scene_Objects:['sheets', 'food_pizza', 'food_ice_cream', 'crayon', 'toilet', 'chair', 'freezer', 'jelly', 'detergent', 'floor', 'ceiling', 'bookshelf', 'table_cloth', 'deck_of_cards', 'shower', 'picture', 'couch', 'wall', 'shelf', 'newspaper', 'wooden_spoon', 'centerpiece', 'kettle', 'shoes', 'comb', 'conditioner', 'door', 'napkin', 'bathroom_cabinet', 'table']
Task:Go to toilet
response:
| {
"thoughts": "i go to the bathroom. I find the toilet",
"actions": [
"[WALK] <bathroom>",
"[WALK] <toilet>",
"[FIND] <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:['filing_cabinet', 'microwave', 'blow_dryer', 'cat', 'trashcan', 'toothbrush', 'drawing', 'floor', 'character', 'desk', 'wine_glass', 'ceilinglamp', 'plate', 'shower', 'window', 'couch', 'pillow', 'dining_room', 'wall', 'nightstand', 'food_cheese', 'bed', 'food_food', 'check', 'television', 'coffee_filter', 'curtain', 'door', 'spoon', '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:['mop', 'toilet', 'freezer', 'food_carrot', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'piano_bench', 'stovefan', 'mat', 'faucet', 'wall', 'wall_clock', 'oven', 'cutting_board', 'toilet_paper', 'video_game_controller', 'television', 'tray', 'doorjamb', 'towel_rack', 'coffee_pot', 'kitchen_counter', 'dresser', 'conditioner', 'sink', 'bathroom_cabinet', 'light', 'teeth']
Task:Wash teeth
response:
| {
"thoughts": "Walk to bathroom. Find mouthwash or turn on water. Put mouthwash or water in mouth. Swish around for 30 seconds. Spit mouthwash out.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <faucet>",
"[FIND] <faucet>",
"[SWITCHON] <faucet>",
"[FIND] <teeth>",
"[RINSE] <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:['glue', 'pot', 'blow_dryer', 'ceilingfan', 'drawing', 'bathroom_counter', 'floor', 'stovefan', 'ceilinglamp', 'balanceball', 'stereo', 'window', 'shower', 'clothes_socks', 'couch', 'candle', 'broom', 'wall', 'wall_clock', 'bed', 'television', 'curtain', 'pencil', 'kitchen_counter', 'dresser', 'napkin', 'spoon', 'table', 'dirt', 'creditcard']
Task:Relax on sofa
response:
{
"thoughts": Find the sofa and sit on it.,
"actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>']
}
|
Scene_Objects:['filing_cabinet', 'mop', 'microwave', 'toilet', 'chair', 'dog', 'walllamp', 'floor', 'desk', 'bookshelf', 'keyboard', 'mat', 'plate', 'shower', 'window', 'bowl', 'wall', 'nightstand', 'powersocket', 'cutting_board', 'shelf', 'check', 'food_food', 'cards', 'towel_rack', 'kitchen_counter', 'maindoor', 'table', 'vase', 'dirt']
Task:Go to toilet
response:
| {
"thoughts": "Walk to the bathroom. Find the toilet. Lift the top of the toilet. Sit on the toilet.",
"actions": [
"[WALK] <bathroom>",
"[WALK] <toilet>",
"[FIND] <toilet>",
"[OPEN] <toilet>",
"[SIT] <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:['food_bread', 'scissors', 'mop', 'chair', 'ceilingfan', 'milk', 'toothbrush', 'knifeblock', 'phone', 'bookshelf', 'stovefan', 'toaster', 'tvstand', 'shower', 'couch', 'food_peanut_butter', 'dustpan', 'oven', 'photoframe', 'clothes_gloves', 'bed', 'video_game_controller', 'tray', 'towel_rack', 'clothes_scarf', 'table', 'light', 'soap', 'tooth_paste', 'scrabble']
Task:Wash teeth
response:
{
"thoughts": before going to bed or when wake up earily morning brush teeth,
"actions": ['[WALK] <bathroom>', '[WALK] <tooth_paste>', '[FIND] <tooth_paste>', '[GRAB] <tooth_paste>', '[FIND] <toothbrush>', '[GRAB] <toothbrush>']
}
|
Scene_Objects:['chair', 'walllamp', 'bills', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'character', 'desk', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'mousepad', 'closetdrawer', 'wall', 'powersocket', 'shelf', 'cup', 'television', 'doorjamb', 'mouse', 'address_book', 'dresser', 'conditioner', 'bathtub', 'spoon', 'light', 'table', 'soap']
Task:Work
response:
| {
"thoughts": "Walk to home office. Walk to computer. Switch on computer. Open the address book.",
"actions": [
"[WALK] <home_office>",
"[WALK] <computer>",
"[SWITCHON] <computer>",
"[FIND] <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:['dry_pasta', 'food_pizza', 'mop', 'cat', 'knife', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'shampoo', 'dvd_player', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'faucet', 'stereo', 'window', 'couch', 'towel', 'wall', 'novel', 'tray', 'doorjamb', 'hairbrush', 'sink', 'bathroom_cabinet', 'soap', 'hands_both', 'shoe_rack']
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>']
}
|
Scene_Objects:['filing_cabinet', 'tablelamp', 'food_salt', 'freezer', 'orchid', 'drawing', 'wallshelf', 'clothes_underwear', 'floor', 'phone', 'bookshelf', 'stovefan', 'pillow', 'wall', 'wall_clock', 'cutting_board', 'box', 'shelf', 'newspaper', 'bed', 'novel', 'coffe_maker', 'toilet_paper', 'wooden_spoon', 'hairbrush', 'door', 'home_office', 'table', 'light', 'vase']
Task:Read book
response:
| {
"thoughts": "Pick up the book, open to current page, read the words.",
"actions": [
"[WALK] <home_office>",
"[WALK] <novel>",
"[FIND] <novel>",
"[GRAB] <novel>",
"[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', 'microwave', 'freezer', 'dough', 'milk', 'drawing', 'floor', 'ceiling', 'keyboard', 'food_bacon', 'toaster', 'stovefan', 'mat', 'shower', 'couch', 'pillow', 'bowl', 'wall', 'oven', 'cup', 'coffe_maker', 'check', 'television', 'tray', 'curtain', 'towel_rack', 'kitchen_counter', 'cupboard', 'light', 'dishwasher']
Task:Get something to drink
response:
{
"thoughts": Walk into the kitchen and to the cupboard to get a cup, walk to the fridge to look for a beverage to enjoy, open the freezer and get ice, pour beverage and enjoy,
"actions": ['[WALK] <dining_room>', '[WALK] <cupboard>', '[FIND] <cupboard>', '[OPEN] <cupboard>', '[FIND] <cup>', '[GRAB] <cup>', '[CLOSE] <cupboard>', '[WALK] <freezer>', '[OPEN] <freezer>', '[FIND] <milk>', '[GRAB] <milk>', '[CLOSE] <freezer>', '[POUR] <milk> <cup>', '[DRINK] <cup>']
}
|
Scene_Objects:['pot', 'chair', 'freezer', 'drawing', 'needle', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'bookshelf', 'envelope', 'computer', 'ceilinglamp', 'mousepad', 'closetdrawer', 'couch', 'dustpan', 'dining_room', 'wall', 'nightstand', 'powersocket', 'food_food', 'toilet_paper', 'doorjamb', 'coffee_pot', 'mouse', 'kettle', 'dresser', 'light']
Task:Turn on light
response:
| {
"thoughts": "walk into living room, walk to light, turn on light switch.",
"actions": [
"[WALK] <home_office>",
"[WALK] <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', 'chair', 'ground_coffee', 'food_butter', 'toothbrush', 'knifeblock', 'drawing', 'phone', 'keyboard', 'bookshelf', 'table_cloth', 'mat', 'plate', 'electric_shaver', 'window', 'pillow', 'nightstand', 'oven', 'newspaper', 'clothes_gloves', 'photoframe', 'toilet_paper', 'water', 'centerpiece', 'towel_rack', 'kettle', 'pencil', 'clothes_scarf', '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>']
}
|
Scene_Objects:['glue', 'microwave', 'freezer', 'ground_coffee', 'hanger', 'floor', 'ceiling', 'stamp', 'keyboard', 'toaster', 'plate', 'faucet', 'shower', 'mousepad', 'food_kiwi', 'wall', 'wall_clock', 'oven', 'cutting_board', 'standingmirror', 'photoframe', 'coffe_maker', 'video_game_controller', 'razor', 'coffee_filter', 'water', 'coffee_pot', 'kitchen_counter', 'sink', 'home_office']
Task:Make coffee
response:
| {
"thoughts": "Walk to Kitchen and find coffee maker, find coffee filter and place it in coffee maker. Find ground coffee and water. put both in coffee maker. Close the coffee maker and switch it on.",
"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:['beer', 'microwave', 'drawing', 'floor', 'purse', 'computer', 'plate', 'balanceball', 'shower', 'stereo', 'dustpan', 'clothes_hat', 'microphone', 'bench', 'basket_for_clothes', 'cup', 'bed', 'check', 'coffe_maker', 'food_onion', 'after_shave', 'cards', 'pencil', 'chessboard', 'maindoor', 'napkin', 'table', 'board_game', 'clothes_shirt', 'coffee']
Task:Set up table
response:
{
"thoughts": Get dishes. Place dishes neatly around table. Get food. Place food on middle of table.,
"actions": ['[WALK] <dining_room>', '[WALK] <plate>', '[FIND] <plate>', '[GRAB] <plate>', '[WALK] <dining_room>', '[WALK] <table>', '[PUTBACK] <plate> <table>', '[WALK] <dining_room>', '[WALK] <plate>', '[FIND] <plate>', '[GRAB] <plate>', '[WALK] <dining_room>', '[WALK] <table>', '[PUTBACK] <plate> <table>', '[WALK] <dining_room>', '[WALK] <plate>', '[FIND] <plate>', '[GRAB] <plate>', '[WALK] <dining_room>', '[WALK] <table>', '[PUTBACK] <plate> <table>', '[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>']
}
|
Scene_Objects:['tablelamp', 'chair', 'bathroom', 'cat', 'milk', 'orchid', 'floor', 'dvd_player', 'desk', 'keyboard', 'purse', 'table_cloth', 'mat', 'shower', 'window', 'clothes_socks', 'couch', 'clothes_pants', 'pillow', 'wall', 'powersocket', 'mouthwash', 'television', 'curtain', 'food_onion', 'doorjamb', 'kitchen_counter', 'bathtub', 'napkin', 'table']
Task:Pet cat
response:
| {
"thoughts": "I walk into the living room. I see my cat on the couch. I go sit next to the cat on the couch. I pet the cat on the back.",
"actions": [
"[WALK] <home_office>",
"[WALK] <cat>",
"[FIND] <cat>",
"[TURNTO] <cat>",
"[LOOKAT] <cat>",
"[FIND] <couch>",
"[SIT] <couch>",
"[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', 'toilet', 'freezer', 'walllamp', 'drawing', 'hanger', 'floor', 'mat', 'tvstand', 'window', 'couch', 'food_peanut_butter', 'pillow', 'wall', 'cutting_board', 'cup', 'novel', 'food_food', 'television', 'wine', 'curtain', 'doorjamb', 'towel_rack', 'pencil', 'shoes', 'bathtub', 'bathroom_cabinet', 'table', 'soap', 'board_game']
Task:Relax on sofa
response:
{
"thoughts": lie in the sofa, relax,
"actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[LIE] <couch>']
}
|
Scene_Objects:['glue', 'filing_cabinet', 'toilet', 'walllamp', 'nail_polish', 'food_butter', 'drawing', 'orchid', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'character', 'ceilinglamp', 'tvstand', 'shower', 'closetdrawer', 'couch', 'form', 'dining_room', 'wall', 'wall_clock', 'bed', 'toothbrush_holder', 'doorjamb', 'chessboard', 'door', 'napkin', 'bathroom_cabinet', 'shoe_rack']
Task:Pick up phone
response:
| {
"thoughts": "I walk over to the phone and pick it up.",
"actions": [
"[WALK] <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', 'food_bread', 'microwave', 'detergent', 'knifeblock', 'floor', 'ceiling', 'character', 'computer', 'toaster', 'ceilinglamp', 'faucet', 'shower', 'wall', 'cup', 'check', 'mouthwash', 'water', 'wine', 'after_shave', 'curtain', 'food_onion', 'mouse', 'kitchen_counter', 'vacuum_cleaner', 'cupboard', 'conditioner', 'sink', 'napkin', 'bathroom_cabinet']
Task:Drink
response:
{
"thoughts": I go in the kitchen and get the glass near the sink. I open the faucet, then I pour water in it, turn off the faucet and drink it.,
"actions": ['[WALK] <dining_room>', '[WALK] <sink>', '[FIND] <cup>', '[GRAB] <cup>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <water>', '[PUTBACK] <cup> <sink>', '[GRAB] <cup>', '[SWITCHOFF] <faucet>', '[DRINK] <cup>']
}
|
Scene_Objects:['chair', 'walllamp', 'bathroom', 'orchid', 'knife', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'button', 'table_cloth', 'ceilinglamp', 'mousepad', 'closetdrawer', 'dining_room', 'wall', 'powersocket', 'shelf', 'television', 'doorjamb', 'mouse', 'dresser', 'door', 'home_office', 'light', 'table', 'laser_pointer']
Task:Write an email
response:
| {
"thoughts": "Find the computer. Turn on the computer. Open the e-mail program. Create a new message. Write the message.",
"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', 'pot', 'scissors', 'juice', 'drawing', 'bills', 'bathroom_counter', 'floor', 'ceiling', 'character', 'desk', 'faucet', 'towel', 'dining_room', 'wall', 'photoframe', 'food_food', 'razor', 'television', 'food_rice', 'wooden_spoon', 'after_shave', 'headset', 'laundry_detergent', 'conditioner', 'sink', 'bathroom_cabinet', 'table', 'soap', 'hands_both']
Task:Wash hands
response:
{
"thoughts": Turn on the water faucet. Wet my hands and turn off the faucet. Put soap on my hands. Rub hands together, making sure the soap covers all areas of the hands. Scrub hands for about 20 seconds. Turn on the water water faucet. Rinse hands under the running water. Turn off the water faucet. Dry hands with a towel.,
"actions": ['[WALK] <bathroom>', '[WALK] <sink>', '[FIND] <sink>', '[TURNTO] <sink>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <hands_both>', '[WASH] <hands_both>', '[FIND] <soap>', '[GRAB] <soap>', '[SCRUB] <hands_both>', '[PUTOBJBACK] <soap>', '[RINSE] <hands_both>', '[SWITCHOFF] <faucet>', '[FIND] <towel>', '[GRAB] <towel>', '[WIPE] <hands_both>', '[PUTOBJBACK] <towel>']
}
|
Scene_Objects:['sheets', 'pot', 'microwave', 'chair', 'freezer', 'nail_polish', 'detergent', 'wallshelf', 'floor', 'ceiling', 'bedroom', 'bookshelf', 'food_cake', 'keyboard', 'toaster', 'stovefan', 'window', 'tooth_paste', 'cup', 'check', 'toothbrush_holder', 'doorjamb', 'coffee_pot', 'mouse', 'pencil', 'bathtub', 'light', 'table', 'board_game', 'teeth']
Task:Pet cat
response:
| {
"thoughts": "I go looking for the cat in the living room where he usually sleeps. Once I find the cat I just pet him for a few minutes.",
"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:['food_ice_cream', 'chair', 'walllamp', 'bathroom', 'orchid', 'knifeblock', 'cpuscreen', 'needle', 'floor', 'ceiling', 'desk', 'keyboard', 'bookshelf', 'computer', 'mat', 'ceilinglamp', 'mousepad', 'couch', 'dining_room', 'wall', 'basket_for_clothes', 'light_bulb', 'food_food', 'check', 'toothbrush_holder', 'mouse', 'comb', 'door', 'clothes_scarf', 'table']
Task:Work
response:
{
"thoughts": I walk to the home office. I open the door of the office room and sit on the chair and in front of me is my desktop computer, and I switch on the computer.,
"actions": ['[WALK] <home_office>', '[WALK] <chair>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>']
}
|
Scene_Objects:['sheets', 'pot', 'filing_cabinet', 'cat', 'floor', 'phone', 'dvd_player', 'bedroom', 'stovefan', 'mat', 'window', 'electric_shaver', 'couch', 'pillow', 'towel', 'wall', 'powersocket', 'toy', 'food_cheese', 'photoframe', 'newspaper', 'television', 'curtain', 'doorjamb', 'pencil', 'shoes', 'maindoor', 'bathtub', 'spoon', 'table']
Task:Pet cat
response:
| {
"thoughts": "I walk to the living room. I locate the cat. I walk to the couch and sit down beside the cat. I pet the cat.",
"actions": [
"[WALK] <home_office>",
"[WALK] <cat>",
"[FIND] <cat>",
"[WALK] <couch>",
"[SIT] <couch>",
"[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', 'pot', 'microwave', 'toilet', 'cat', 'wallshelf', 'bathroom_counter', 'floor', 'dvd_player', 'bookshelf', 'stovefan', 'ceilinglamp', 'toaster', 'mat', 'shower', 'faucet', 'tvstand', 'couch', 'towel', 'wall', 'bench', 'cutting_board', 'bed', 'razor', 'television', 'curtain', 'kitchen_counter', 'dresser', 'home_office', 'light']
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:['filing_cabinet', 'mop', 'microwave', 'freezer', 'walllamp', 'detergent', 'toothbrush', 'orchid', 'drawing', 'clothes_underwear', 'floor', 'thread', 'mat', 'closetdrawer', 'wall', 'nightstand', 'toy', 'standingmirror', 'light_bulb', 'novel', 'check', 'tray', 'cards', 'mouse', 'pencil', 'vacuum_cleaner', 'headset', 'maindoor', 'napkin', 'light']
Task:Read book
response:
| {
"thoughts": "Walk to the Living Room. Look at the Cabinet. Find a Textbook. Grab the textbook. Open the Textbook. Read the textbook.",
"actions": [
"[WALK] <home_office>",
"[WALK] <filing_cabinet>",
"[FIND] <filing_cabinet>",
"[TURNTO] <filing_cabinet>",
"[LOOKAT] <filing_cabinet>",
"[FIND] <novel>",
"[GRAB] <novel>",
"[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:['filing_cabinet', 'trashcan', 'food_carrot', 'knifeblock', 'drawing', 'cpuscreen', 'clothes_underwear', 'floor', 'bedroom', 'alcohol', 'laptop', 'tvstand', 'stereo', 'faucet', 'mat', 'couch', 'clothes_hat', 'nightstand', 'bench', 'oven', 'toy', 'coffe_maker', 'television', 'coin', 'kitchen_counter', 'cupboard', 'home_office', 'bathroom_cabinet', 'dishwasher', 'board_game']
Task:Listen to music
response:
{
"thoughts": go to radio. run on radio.,
"actions": ['[WALK] <stereo>', '[SWITCHON] <stereo>']
}
|
Scene_Objects:['scissors', 'detergent', 'orchid', 'wallshelf', 'bedroom', 'tea_bag', 'bookshelf', 'ceilinglamp', 'laptop', 'faucet', 'window', 'couch', 'broom', 'wall', 'oven', 'cutting_board', 'toy', 'cup', 'standingmirror', 'razor', 'television', 'tray', 'after_shave', 'towel_rack', 'mouse', 'kitchen_counter', 'controller', 'bathtub', 'vase', 'soap']
Task:Pick up phone
response:
| {
"thoughts": "walk to living room, walk to the phone reach for the phone and pick up the phone.",
"actions": [
"[WALK] <home_office>",
"[WALK] <phone>",
"[FIND] <phone>",
"[TOUCH] <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', 'tablelamp', 'food_salt', 'microwave', 'freezer', 'drawing', 'floor', 'ceiling', 'desk', 'alcohol', 'stovefan', 'mat', 'plate', 'shower', 'couch', 'food_orange', 'pillow', 'wall', 'oven', 'food_food', 'television', 'tray', 'towel_rack', 'kitchen_counter', 'sauce_pan', 'cupboard', 'spoon', 'napkin', 'light', 'dishwasher']
Task:Cook some food
response:
{
"thoughts": I pull a sauce pan from the cupboard. I turn the stove on. I take my ingredients from the pantry and fridge. I put the ingredients in the pan and I mix them with a spoon. I cook until the food is finished and transfer my food to a plate.,
"actions": ['[WALK] <dining_room>', '[WALK] <food_food>', '[FIND] <food_food>', '[FIND] <pot>', '[GRAB] <pot>', '[FIND] <spoon>', '[GRAB] <spoon>', '[FIND] <sauce_pan>', '[PUTBACK] <spoon> <sauce_pan>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <plate>', '[PUTBACK] <pot> <plate>']
}
|
Scene_Objects:['spectacles', 'fork', 'tablelamp', 'tea', 'band-aids', 'bathroom', 'drawing', 'hanger', 'floor', 'ceiling', 'dvd_player', 'desk', 'remote_control', 'computer', 'food_bacon', 'mat', 'ceilinglamp', 'window', 'mousepad', 'closetdrawer', 'couch', 'clothes_pants', 'pillow', 'wall', 'standingmirror', 'television', 'curtain', 'doorjamb', 'table', 'soap']
Task:Change TV channel
response:
| {
"thoughts": "I push my body to be near to the table in front of me, without stand up. I move my right hand to near the TV remote control on the table. I take the TV remote control. I look the number on the remote control. I touch number 3 button. I put back the remote control to the table. I put my body back to the sofa",
"actions": [
"[WALK] <home_office>",
"[WALK] <television>",
"[FIND] <television>",
"[PLUGIN] <television>",
"[FIND] <couch>",
"[SIT] <couch>",
"[FIND] <remote_control>",
"[TURNTO] <remote_control>",
"[LOOKAT] <remote_control>",
"[GRAB] <remote_control>",
"[TOUCH] <remote_control>",
"[PUTOBJBACK] <remote_control>",
"[TURNTO] <television>",
"[WATCH] <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:['microwave', 'chair', 'freezer', 'detergent', 'food_carrot', 'orchid', 'floor', 'wine_glass', 'food_cake', 'mat', 'picture', 'window', 'mousepad', 'couch', 'clothes_hat', 'pillow', 'wall', 'pasta', 'shelf', 'food_cheese', 'newspaper', 'food_food', 'television', 'curtain', 'doorjamb', 'kitchen_counter', 'dresser', 'bathtub', 'table', 'vase']
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:['blow_dryer', 'drawing', 'knife', 'hanger', 'floor', 'ceiling', 'shampoo', 'desk', 'keyboard', 'remote_control', 'thread', 'computer', 'alcohol', 'bookmark', 'mat', 'ceilinglamp', 'window', 'closetdrawer', 'couch', 'pillow', 'wall', 'wall_clock', 'tape', 'standingmirror', 'bed', 'television', 'curtain', 'doorjamb', 'instrument_guitar', 'table']
Task:Change TV channel
response:
| {
"thoughts": "Changing channel",
"actions": [
"[WALK] <home_office>",
"[WALK] <television>",
"[FIND] <television>",
"[SWITCHON] <television>",
"[FIND] <couch>",
"[SIT] <couch>",
"[FIND] <remote_control>",
"[GRAB] <remote_control>",
"[TURNTO] <television>",
"[POINTAT] <television>",
"[DROP] <remote_control>"
]
} |
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', 'chair', 'walllamp', 'cat', 'wallshelf', 'floor', 'character', 'desk', 'tea_bag', 'toaster', 'plate', 'couch', 'dining_room', 'box', 'newspaper', 'bed', 'toilet_paper', 'curtain', 'coffee_pot', 'mouse', 'kettle', 'cupboard', 'controller', 'clothes_dress', 'sink', 'bathroom_cabinet', 'table', 'dishwasher', 'soap']
Task:Pet cat
response:
{
"thoughts": Find Cat in living room. Walk to cat. Pet cat.,
"actions": ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[TURNTO] <cat>', '[LOOKAT] <cat>', '[TOUCH] <cat>']
}
|
Scene_Objects:['freezer', 'bathroom', 'detergent', 'orchid', 'cpuscreen', 'floor', 'phone', 'desk', 'bedroom', 'purse', 'computer', 'table_cloth', 'bookmark', 'stovefan', 'stereo', 'oil', 'closetdrawer', 'coffe_maker', 'television', 'food_donut', 'food_rice', 'tray', 'centerpiece', 'doorjamb', 'pencil', 'maindoor', 'sink', 'home_office', 'table', 'clothes_skirt']
Task:Read book
response:
| {
"thoughts": "Walk to living room. Find book. Grab book. Open book. Read book.",
"actions": [
"[WALK] <home_office>",
"[WALK] <novel>",
"[FIND] <novel>",
"[GRAB] <novel>",
"[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:['fork', 'toilet', 'trashcan', 'ceilingfan', 'drawing', 'hanger', 'floor', 'ceiling', 'bookshelf', 'thread', 'computer', 'piano_bench', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'foundation', 'clothes_pants', 'pillow', 'dining_room', 'wall', 'oven', 'bed', 'novel', 'check', 'television', 'curtain', 'towel_rack', 'dresser', 'vase']
Task:Read book
response:
{
"thoughts": Put child in bed, sit down,read book.,
"actions": ['[WALK] <bedroom>', '[WALK] <dresser>', '[OPEN] <dresser>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <bed>', '[SIT] <bed>', '[READ] <novel>']
}
|
Scene_Objects:['sponge', 'toilet', 'jelly', 'freezer', 'walllamp', 'bathroom', 'hanger', 'folder', 'bedroom', 'desk', 'tvstand', 'window', 'food_jam', 'microphone', 'dining_room', 'wall_clock', 'powersocket', 'bench', 'shelf', 'bed', 'video_game_controller', 'food_donut', 'water', 'doorjamb', 'cards', 'towel_rack', 'mouse', 'sink', 'colander', 'hands_both']
Task:Wash hands
response:
| {
"thoughts": "walk to bathroom, look at the water, wash hands",
"actions": [
"[WALK] <bathroom>",
"[WALK] <water>",
"[FIND] <water>",
"[TURNTO] <water>",
"[LOOKAT] <water>",
"[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', 'tea', 'chair', 'detergent', 'toothbrush', 'orchid', 'knifeblock', 'cpuscreen', 'kitchen_cabinet', 'floor', 'phone', 'bedroom', 'keyboard', 'ceilinglamp', 'faucet', 'window', 'dish_soap', 'food_jam', 'food_orange', 'pillow', 'wall', 'oven', 'bed', 'novel', 'coffe_maker', 'kitchen_counter', 'dishrack', 'cupboard', 'table', 'dishwasher']
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>']
}
|
Scene_Objects:['microwave', 'walllamp', 'detergent', 'toothbrush', 'drawing', 'cpuscreen', 'food_egg', 'phone', 'character', 'computer', 'piano_bench', 'shoe-shine_kit', 'faucet', 'food_noodles', 'mousepad', 'clothes_hat', 'towel', 'broom', 'cutting_board', 'shelf', 'keys', 'novel', 'food_food', 'check', 'wooden_spoon', 'towel_rack', 'sink', 'table', 'light', 'coffee']
Task:Change TV channel
response:
| {
"thoughts": "I pull up my online classes on the computer to look at what the assigned reading is. I get my textbook, notebook, and mechanical pencil. As I'm reading, I take notes over important points. I then use those notes to complete the assignment for the week. Frequently that involves writing a post on an online discussion board that answers a question related to things from the reading.",
"actions": [
"[WALK] <home_office>",
"[WALK] <remote_control>",
"[GRAB] <remote_control>",
"[TURNTO] <remote_control>",
"[POINTAT] <remote_control>"
]
} |
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', 'food_ice_cream', 'cd_player', 'orchid', 'bedroom', 'purse', 'computer', 'stovefan', 'mat', 'ceilinglamp', 'stereo', 'tvstand', 'balanceball', 'clothes_socks', 'couch', 'food_jam', 'powersocket', 'oven', 'cutting_board', 'photoframe', 'novel', 'check', 'television', 'wine', 'food_onion', 'pencil', 'vacuum_cleaner', 'door', 'sink', 'instrument_violin']
Task:Listen to music
response:
{
"thoughts": I walk in the living room, then I go the the stereo and the cd player and turn them on.,
"actions": ['[WALK] <home_office>', '[WALK] <stereo>', '[FIND] <stereo>', '[SWITCHON] <stereo>', '[FIND] <cd_player>', '[SWITCHON] <cd_player>']
}
|
Scene_Objects:['filing_cabinet', 'scissors', 'freezer', 'nail_polish', 'food_carrot', 'orchid', 'bedroom', 'computer', 'food_bacon', 'toaster', 'plate', 'window', 'clothes_socks', 'closetdrawer', 'oil', 'nightstand', 'basket_for_clothes', 'photoframe', 'check', 'doorjamb', 'towel_rack', 'console', 'dresser', 'door', 'sink', 'table', 'clothes_skirt', 'soap', 'clothes_shirt', '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>"
]
} |
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', 'glue', 'microwave', 'bathroom', 'trashcan', 'toothbrush', 'drawing', 'knifeblock', 'food_egg', 'floor', 'ceiling', 'desk', 'purse', 'food_bacon', 'ceilinglamp', 'plate', 'laptop', 'deck_of_cards', 'window', 'couch', 'food_orange', 'wall', 'powersocket', 'photoframe', 'check', 'television', 'spoon', 'home_office', 'table', 'teeth']
Task:Relax on sofa
response:
{
"thoughts": I walk to the sofa, and lie down on the sofa.,
"actions": ['[WALK] <couch>', '[LIE] <couch>']
}
|
Scene_Objects:['freezer', 'walllamp', 'bathroom', 'cpuscreen', 'clothes_underwear', 'bathroom_counter', 'shampoo', 'tvstand', 'faucet', 'stereo', 'clothes_socks', 'couch', 'clothes_pants', 'cutting_board', 'basket_for_clothes', 'photoframe', 'food_food', 'video_game_controller', 'coffe_maker', 'coffee_filter', 'television', 'tray', 'curtain', 'shaving_cream', 'laundry_detergent', 'maindoor', 'spoon', 'home_office', 'clothes_shirt', 'washing_machine']
Task:Wash clothes
response:
| {
"thoughts": "I go to the bathroom and open the washing machine there. I take my laundry basket and put each item of laundry into the machine. Then I take the laundry detergent and pour some into the machine. Finally I close the machine and switch it on.",
"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>",
"[FIND] <clothes_underwear>",
"[GRAB] <clothes_underwear>",
"[PUTBACK] <clothes_underwear> <washing_machine>",
"[FIND] <clothes_socks>",
"[GRAB] <clothes_socks>",
"[PUTBACK] <clothes_socks> <washing_machine>",
"[PUTOBJBACK] <basket_for_clothes>",
"[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:['sheets', 'pot', 'scissors', 'juice', 'drawing', 'bills', 'bathroom_counter', 'floor', 'ceiling', 'character', 'desk', 'faucet', 'towel', 'dining_room', 'wall', 'photoframe', 'food_food', 'razor', 'television', 'food_rice', 'wooden_spoon', 'after_shave', 'headset', 'laundry_detergent', 'conditioner', 'sink', 'bathroom_cabinet', 'table', 'soap', 'hands_both']
Task:Wash hands
response:
{
"thoughts": Turn on the water faucet. Wet my hands and turn off the faucet. Put soap on my hands. Rub hands together, making sure the soap covers all areas of the hands. Scrub hands for about 20 seconds. Turn on the water water faucet. Rinse hands under the running water. Turn off the water faucet. Dry hands with a towel.,
"actions": ['[WALK] <bathroom>', '[WALK] <sink>', '[FIND] <sink>', '[TURNTO] <sink>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <hands_both>', '[WASH] <hands_both>', '[FIND] <soap>', '[GRAB] <soap>', '[SCRUB] <hands_both>', '[PUTOBJBACK] <soap>', '[RINSE] <hands_both>', '[SWITCHOFF] <faucet>', '[FIND] <towel>', '[GRAB] <towel>', '[WIPE] <hands_both>', '[PUTOBJBACK] <towel>']
}
|
Scene_Objects:['fork', 'pot', 'food_pizza', 'juice', 'board_game', 'dog', 'food_butter', 'orchid', 'drawing', 'bathroom_counter', 'bookshelf', 'stovefan', 'mat', 'laptop', 'tvstand', 'picture', 'window', 'couch', 'nightstand', 'wall_clock', 'toy', 'clothes_gloves', 'toilet_paper', 'television', 'ice', 'bathroom_cabinet', 'table', 'light', 'vase', 'instrument_violin']
Task:Set up table
response:
| {
"thoughts": "Walk into kitchen, find plate, drop plate on table in living room, walk into kitchen, find cup, bring cup to table in living room, walk into kitchen find fork, bring fork to table in living room",
"actions": [
"[WALK] <dining_room>",
"[WALK] <plate>",
"[FIND] <plate>",
"[GRAB] <plate>",
"[WALK] <home_office>",
"[DROP] <plate>",
"[WALK] <dining_room>",
"[WALK] <cup>",
"[FIND] <cup>",
"[GRAB] <cup>",
"[WALK] <home_office>",
"[DROP] <cup>",
"[WALK] <dining_room>",
"[WALK] <fork>",
"[FIND] <fork>",
"[GRAB] <fork>",
"[WALK] <home_office>",
"[DROP] <fork>"
]
} |
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', 'food_salt', 'microwave', 'freezer', 'orchid', 'drawing', 'hanger', 'button', 'table_cloth', 'tvstand', 'homework', 'couch', 'dining_room', 'nightstand', 'keys', 'coffe_maker', 'television', 'oven_mitts', 'curtain', 'doorjamb', 'diary', 'cards', 'kitchen_counter', 'comb', 'dresser', 'food_steak', 'home_office', 'light', 'clothes_skirt']
Task:Pet cat
response:
{
"thoughts": I go to the living room then go to the cat and touch it.,
"actions": ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[TOUCH] <cat>']
}
|
Scene_Objects:['microwave', 'toilet', 'freezer', 'ground_coffee', 'walllamp', 'blow_dryer', 'dough', 'floor', 'ceiling', 'bookshelf', 'toaster', 'faucet', 'wall', 'wall_clock', 'pasta', 'bench', 'powersocket', 'cutting_board', 'box', 'bed', 'coffe_maker', 'coffee_filter', 'water', 'tray', 'doorjamb', 'mouse', 'kitchen_counter', 'sink', 'table', 'clothes_skirt']
Task:Make coffee
response:
| {
"thoughts": "I walk into the kitchen. I find the coffee maker and open it. I find the coffee filter, grab it and put it into the coffee maker. I find ground coffee, grab it and put it into the coffee maker. I find some water, then I pour it into the coffee maker. I close the coffee maker, I plug it in and I switch it on.",
"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>",
"[PLUGIN] <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:['food_salt', 'chair', 'walllamp', 'drawing', 'orchid', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'remote_control', 'computer', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'closetdrawer', 'couch', 'pillow', 'wall', 'photoframe', 'food_food', 'television', 'coin', 'tray', 'doorjamb', 'towel_rack', 'dresser', 'table']
Task:Watch TV
response:
{
"thoughts": Watch the television,
"actions": ['[WALK] <home_office>', '[WALK] <television>', '[TURNTO] <television>', '[LOOKAT] <television>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[SWITCHON] <television>', '[FIND] <couch>', '[TURNTO] <couch>', '[SIT] <couch>', '[TURNTO] <television>', '[WATCH] <television>']
}
|
Scene_Objects:['spectacles', 'toilet', 'chair', 'walllamp', 'bathroom', 'orchid', 'floor', 'ceiling', 'bookshelf', 'table_cloth', 'bookmark', 'ceilinglamp', 'mat', 'stereo', 'shower', 'floor_lamp', 'food_noodles', 'clothes_hat', 'dining_room', 'wall', 'television', 'food_donut', 'doorjamb', 'kitchen_counter', 'dresser', 'door', 'bathtub', 'bathroom_cabinet', 'light', 'coffee']
Task:Turn on light
response:
| {
"thoughts": "walk to wall, find light switch, turn on lights",
"actions": [
"[WALK] <home_office>",
"[WALK] <light>",
"[FIND] <light>",
"[PLUGIN] <light>",
"[FIND] <floor_lamp>",
"[SWITCHON] <floor_lamp>",
"[WALK] <bedroom>",
"[WALK] <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', 'tablelamp', 'microwave', 'walllamp', 'bathroom', 'drawing', 'wallshelf', 'floor', 'ceiling', 'bedroom', 'bookshelf', 'computer', 'brush', 'mat', 'tvstand', 'couch', 'clothes_hat', 'pillow', 'wall', 'nightstand', 'powersocket', 'cup', 'photoframe', 'food_food', 'television', 'doorjamb', 'bag', 'light', 'dishwasher', 'table']
Task:Relax on sofa
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] <couch>', '[FIND] <couch>', '[SIT] <couch>']
}
|
Scene_Objects:['filing_cabinet', 'toilet', 'chair', 'walllamp', 'bathroom', 'drawing', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'mousepad', 'closetdrawer', 'pillow', 'bowl', 'wall', 'powersocket', 'cup', 'novel', 'coffe_maker', 'food_donut', 'doorjamb', 'mouse', 'dresser', 'light']
Task:Read book
response:
| {
"thoughts": "Walk to the living room. Find a desk and grab a book. Walk to the chair, sit in the chair and read a book.",
"actions": [
"[WALK] <home_office>",
"[WALK] <desk>",
"[FIND] <desk>",
"[FIND] <novel>",
"[GRAB] <novel>",
"[WALK] <chair>",
"[SIT] <chair>",
"[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:['blender', 'chair', 'dog', 'bathroom', 'drawing', 'orchid', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'folder', 'desk', 'computer', 'ceilinglamp', 'window', 'mousepad', 'couch', 'towel', 'wall', 'cup', 'television', 'curtain', 'doorjamb', 'dresser', 'cupboard', 'door', 'sink', 'light', 'table']
Task:Relax on sofa
response:
{
"thoughts": I walk into the living room and turn on the light. I walk to the couch then sit on the couch.,
"actions": ['[WALK] <home_office>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>', '[WALK] <couch>', '[SIT] <couch>']
}
|
Scene_Objects:['sheets', 'food_pizza', 'tablelamp', 'blender', 'beer', 'wallshelf', 'floor', 'phone', 'stamp', 'desk', 'stovefan', 'mat', 'laptop', 'stereo', 'window', 'food_noodles', 'couch', 'food_peanut_butter', 'pillow', 'wall', 'cup', 'photoframe', 'clothes_gloves', 'coffe_maker', 'television', 'curtain', 'doorjamb', 'controller', 'bathroom_cabinet', 'table']
Task:Relax on sofa
response:
| {
"thoughts": "walk to living room, walk to sofa, sit on 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:['filing_cabinet', 'tablelamp', 'toilet', 'chair', 'walllamp', 'detergent', 'trashcan', 'food_carrot', 'knifeblock', 'drawing', 'cpuscreen', 'knife', 'bathroom_counter', 'desk', 'keyboard', 'bookshelf', 'table_cloth', 'toaster', 'ceilinglamp', 'faucet', 'mousepad', 'pillow', 'dining_room', 'oven', 'photoframe', 'food_food', 'kitchen_counter', 'dresser', 'sink', 'home_office']
Task:Turn off light
response:
{
"thoughts": Walk to the lamp. Find the switch. Click the switch off.,
"actions": ['[WALK] <bedroom>', '[WALK] <floor_lamp>', '[SWITCHOFF] <floor_lamp>']
}
|
Scene_Objects:['scissors', 'toilet', 'drawing', 'hanger', 'floor', 'ceiling', 'phone', 'bookshelf', 'remote_control', 'envelope', 'computer', 'button', 'bookmark', 'mat', 'ceilinglamp', 'tvstand', 'window', 'closetdrawer', 'couch', 'pillow', 'wall', 'standingmirror', 'clothes_gloves', 'television', 'curtain', 'doorjamb', 'towel_rack', 'coffee_pot', 'table', 'soap']
Task:Change TV channel
response:
| {
"thoughts": "I go to the living room where the TV is located. I plug in the TV to the outlet. I search for the remote control. I point the remote control directly to the TV, turn it on and push the number of the channel that I want.",
"actions": [
"[WALK] <home_office>",
"[WALK] <television>",
"[FIND] <television>",
"[PLUGIN] <television>",
"[FIND] <remote_control>",
"[TURNTO] <television>",
"[POINTAT] <television>",
"[SWITCHON] <television>",
"[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:['filing_cabinet', 'tablelamp', 'freezer', 'detergent', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'desk', 'keyboard', 'mop_bucket', 'shower', 'homework', 'candle', 'clothes_pants', 'pillow', 'wall', 'oven', 'bed', 'keys', 'check', 'coffe_maker', 'tray', 'centerpiece', 'pajamas', 'bag', 'spoon', 'soap', 'laser_pointer', 'scrabble']
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:['filing_cabinet', 'scissors', 'microwave', 'toilet', 'chair', 'walllamp', 'drawing', 'floor', 'ceiling', 'shampoo', 'computer', 'mat', 'food_orange', 'bowl', 'dining_room', 'wall', 'powersocket', 'oven', 'toy', 'shelf', 'cup', 'light_bulb', 'novel', 'coffe_maker', 'tray', 'doorjamb', 'maindoor', 'bathtub', 'light', 'vase']
Task:Turn on light
response:
| {
"thoughts": "I walk into the kitchen, I find the light switch, and then i switch on the lights in the kitchen.",
"actions": [
"[WALK] <dining_room>",
"[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:['glue', 'beer', 'measuring_cup', 'toilet', 'freezer', 'food_carrot', 'drawing', 'food_egg', 'hanger', 'floor', 'ceiling', 'bedroom', 'mat', 'laptop', 'shower', 'tvstand', 'closetdrawer', 'food_orange', 'nightstand', 'wall', 'powersocket', 'food_cheese', 'photoframe', 'bed', 'food_food', 'drinking_glass', 'wine', 'doorjamb', 'door', 'light']
Task:Drink
response:
{
"thoughts": Robot Drinks the water,
"actions": ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <drinking_glass>', '[GRAB] <drinking_glass>', '[DRINK] <drinking_glass>', '[PUTOBJBACK] <drinking_glass>', '[CLOSE] <freezer>']
}
|
Scene_Objects:['glue', 'fork', 'tablelamp', 'tea', 'chair', 'freezer', 'nail_polish', 'detergent', 'milk', 'drawing', 'orchid', 'bathroom_counter', 'floor', 'ceiling', 'character', 'toaster', 'ceilinglamp', 'stovefan', 'iron', 'window', 'wall', 'powersocket', 'oven', 'standingmirror', 'bed', 'food_donut', 'curtain', 'doorjamb', 'door', 'light']
Task:Turn on light
response:
| {
"thoughts": "Turning on lights",
"actions": [
"[WALK] <bedroom>",
"[WALK] <light>",
"[FIND] <light>",
"[SWITCHON] <light>",
"[WALK] <bathroom>"
]
} |
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', 'freezer', 'walllamp', 'bathroom', 'trashcan', 'orchid', 'wallshelf', 'phone', 'desk', 'toaster', 'stovefan', 'mat', 'shower', 'mousepad', 'closetdrawer', 'pillow', 'wall', 'powersocket', 'bench', 'bed', 'photoframe', 'curtain', 'doorjamb', 'towel_rack', 'kitchen_counter', 'bathtub', 'sink', 'bathroom_cabinet', 'light']
Task:Pet cat
response:
{
"thoughts": Walk into the living room. Walk up to the cat. Pet the cat with your hand.,
"actions": ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[TOUCH] <cat>']
}
|
Scene_Objects:['tablelamp', 'scissors', 'drawing', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'button', 'ceilinglamp', 'tvstand', 'shower', 'electric_shaver', 'food_kiwi', 'wall', 'bench', 'food_cheese', 'photoframe', 'newspaper', 'bed', 'food_food', 'standingmirror', 'television', 'curtain', 'doorjamb', 'shaving_cream', 'door', 'soap', 'clothes_shirt', 'scrabble', 'coffee']
Task:Change TV channel
response:
| {
"thoughts": "Walk to TV, grab remote control, press change channel button, repeat pressing change channel button util find the channel wanted, put back remote control",
"actions": [
"[WALK] <television>",
"[FIND] <remote_control>",
"[GRAB] <remote_control>",
"[FIND] <button>",
"[TOUCH] <button>",
"[TURNTO] <television>",
"[WATCH] <television>",
"[TOUCH] <button>",
"[TURNTO] <television>",
"[WATCH] <television>",
"[PUTOBJBACK] <remote_control>"
]
} |
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:['juice', 'toilet', 'chair', 'blow_dryer', 'food_carrot', 'orchid', 'knifeblock', 'cpuscreen', 'desk', 'clothes_jacket', 'toaster', 'deck_of_cards', 'tvstand', 'dining_room', 'bench', 'basket_for_clothes', 'novel', 'television', 'after_shave', 'coffee_pot', 'mouse', 'cupboard', 'clothes_dress', 'hairdryer', 'home_office', 'colander', 'clothes_shirt', 'washing_machine', 'coffee', 'shoe_rack']
Task:Wash clothes
response:
{
"thoughts": Walk to the kitchen. Find the washing machine. Open the washing machine. Find the basket for clothes. Find the clothes_dress. Grab the clothes_dress. Put the clothes_dress into the washing machine. Find the clothes_shirt. Grab the clothes_shirt. Put the clothes_shirt into the washing machine. Close the washing machine. Switch on the washing machine.,
"actions": ['[WALK] <dining_room>', '[WALK] <washing_machine>', '[FIND] <washing_machine>', '[OPEN] <washing_machine>', '[FIND] <basket_for_clothes>', '[FIND] <clothes_dress>', '[GRAB] <clothes_dress>', '[PUTBACK] <clothes_dress> <washing_machine>', '[FIND] <clothes_shirt>', '[GRAB] <clothes_shirt>', '[PUTBACK] <clothes_shirt> <basket_for_clothes>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>']
}
|
Scene_Objects:['spectacles', 'tablelamp', 'chair', 'dog', 'drawing', 'wallshelf', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'bookshelf', 'computer', 'tvstand', 'mousepad', 'closetdrawer', 'couch', 'food_orange', 'wall', 'powersocket', 'shelf', 'cup', 'doorjamb', 'console', 'mouse', 'shoes', 'dresser', 'bathtub', 'light']
Task:Turn on light
response:
| {
"thoughts": "I open the room door and press the light button on",
"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:['toilet', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'bedroom', 'cleaning_solution', 'faucet', 'balanceball', 'window', 'clothes_socks', 'food_orange', 'wall', 'powersocket', 'bench', 'cutting_board', 'photoframe', 'novel', 'check', 'rag', 'lighter', 'mouse', 'kitchen_counter', 'hair', 'sink', 'bathroom_cabinet', 'home_office', 'tooth_paste', 'scrabble', 'dirt']
Task:Wash sink
response:
{
"thoughts": Turn on faucet. Rub down sink.,
"actions": ['[WALK] <bathroom>', '[WALK] <cleaning_solution>', '[FIND] <cleaning_solution>', '[GRAB] <cleaning_solution>', '[FIND] <sink>', '[POUR] <cleaning_solution> <sink>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[SCRUB] <sink>', '[WASH] <sink>']
}
|
Scene_Objects:['pot', 'filing_cabinet', 'toilet', 'needle', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'dvd_player', 'stamp', 'envelope', 'computer', 'mat', 'ceilinglamp', 'oil', 'food_orange', 'wall', 'bench', 'shelf', 'food_cheese', 'photoframe', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'door', 'sink', 'light']
Task:Turn on light
response:
| {
"thoughts": "I walk to room. I enter room. I find where the lightswitch is. I turn on the lights with the lightswitch.",
"actions": [
"[WALK] <bedroom>",
"[WALK] <light>",
"[FIND] <light>",
"[TURNTO] <light>",
"[LOOKAT] <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:['juice', 'crayon', 'walllamp', 'trashcan', 'dough', 'floor', 'phone', 'bedroom', 'tea_bag', 'toaster', 'mat', 'plate', 'ceilinglamp', 'dish_soap', 'wall', 'pasta', 'oven', 'cutting_board', 'food_cheese', 'newspaper', 'coffe_maker', 'check', 'food_food', 'tray', 'towel_rack', 'pencil', 'dresser', 'conditioner', 'home_office', 'dishwasher']
Task:Wash dishes with dishwasher
response:
{
"thoughts": I walk to the kitchen. I search and find dishwasher. I search dishes. I put dishes inside the dishwasher. I put dish soap in dishwasher. I switch on dishwasher and wait for dishes to be washed.,
"actions": ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[OPEN] <dishwasher>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[PUTBACK] <dish_soap> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>']
}
|
Scene_Objects:['fork', 'dry_pasta', 'filing_cabinet', 'scissors', 'kitchen_cabinet', 'envelope', 'faucet', 'dish_soap', 'mousepad', 'couch', 'pillow', 'dining_room', 'wall_clock', 'bench', 'toy', 'cutting_board', 'razor', 'food_onion', 'doorjamb', 'towel_rack', 'kitchen_counter', 'pajamas', 'clothes_dress', 'bathtub', 'sink', 'bathroom_cabinet', 'table', 'dishwasher', 'vase', 'light']
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:['food_bread', 'tablelamp', 'blender', 'tea', 'chair', 'freezer', 'drawing', 'orchid', 'hanger', 'floor', 'shampoo', 'stamp', 'bedroom', 'desk', 'computer', 'mat', 'stereo', 'mousepad', 'food_jam', 'dining_room', 'wall', 'wall_clock', 'bench', 'photoframe', 'food_food', 'dresser', 'napkin', 'home_office', 'table', 'spoon']
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:['measuring_cup', 'food_carrot', 'drawing', 'floor', 'thread', 'toaster', 'mat', 'picture', 'oil', 'towel', 'nightstand', 'powersocket', 'toy', 'shelf', 'box', 'cup', 'cutting_board', 'bed', 'photoframe', 'novel', 'toilet_paper', 'check', 'television', 'tray', 'food_onion', 'curtain', 'dresser', 'door', 'hairdryer', 'tooth_paste']
Task:Listen to music
response:
| {
"thoughts": "Find the radio; switch on the radio and 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:['toilet', 'walllamp', 'bathroom', 'drawing', 'orchid', 'wallshelf', 'cpuscreen', 'floor', 'ceiling', 'character', 'bookshelf', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'photoframe', 'bed', 'television', 'curtain', 'doorjamb', 'shoes', 'door', 'table', 'light', 'creditcard']
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] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[WALK] <couch>', '[SIT] <couch>', '[TOUCH] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>', '[TURNTO] <television>', '[WATCH] <television>']
}
|
Scene_Objects:['toilet', 'chair', 'bathroom', 'food_carrot', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'shampoo', 'character', 'stamp', 'keyboard', 'mat', 'faucet', 'picture', 'food_peanut_butter', 'dining_room', 'pasta', 'bench', 'cutting_board', 'cup', 'standingmirror', 'photoframe', 'coin', 'cards', 'kitchen_counter', 'bathtub', 'bathroom_cabinet', 'table', 'vase']
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:['filing_cabinet', 'microwave', 'chair', 'walllamp', 'nail_polish', 'knifeblock', 'drawing', 'cpuscreen', 'wallshelf', 'bathroom_counter', 'desk', 'cleaning_solution', 'bookshelf', 'stovefan', 'mat', 'tvstand', 'shower', 'faucet', 'ceilinglamp', 'pillow', 'bench', 'cup', 'mouse', 'controller', 'laundry_detergent', 'door', 'napkin', 'light', 'dirt', 'hands_both']
Task:Wash hands
response:
{
"thoughts": walk to bathroom , find cleaning solution , squeeze cleaning solution , wash hands,
"actions": ['[WALK] <bathroom>', '[WALK] <cleaning_solution>', '[FIND] <cleaning_solution>', '[SQUEEZE] <cleaning_solution>', '[FIND] <hands_both>', '[WASH] <hands_both>']
}
|
Scene_Objects:['sheets', 'food_bread', 'tablelamp', 'chair', 'freezer', 'walllamp', 'drawing', 'wallshelf', 'bathroom_counter', 'floor', 'stovefan', 'mat', 'tvstand', 'window', 'closetdrawer', 'microphone', 'food_orange', 'pillow', 'wall', 'nightstand', 'bed', 'food_rice', 'curtain', 'kettle', 'dresser', 'pajamas', 'bathtub', 'bathroom_cabinet', 'table', 'vase']
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:['microwave', 'freezer', 'drawing', 'wallshelf', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'dvd_player', 'character', 'keyboard', 'bookshelf', 'computer', 'stovefan', 'toaster', 'window', 'mousepad', 'closetdrawer', 'clothes_pants', 'pillow', 'wall', 'nightstand', 'wall_clock', 'television', 'tray', 'curtain', 'mouse', 'kitchen_counter', 'dresser', 'clothes_shirt']
Task:Organize closet
response:
{
"thoughts": Organize the hanging clothes in my closet by color and type and get rid of clothes I don't wear.,
"actions": ['[WALK] <bedroom>', '[WALK] <dresser>', '[OPEN] <dresser>', '[FIND] <clothes_pants>', '[GRAB] <clothes_pants>', '[PULL] <clothes_pants>', '[PUTIN] <clothes_pants> <dresser>', '[FIND] <clothes_pants>', '[GRAB] <clothes_pants>', '[PULL] <clothes_pants>', '[PUTIN] <clothes_pants> <dresser>', '[FIND] <clothes_shirt>', '[GRAB] <clothes_shirt>', '[PUSH] <clothes_shirt>', '[PUTIN] <clothes_shirt> <dresser>', '[FIND] <clothes_shirt>', '[GRAB] <clothes_shirt>', '[PUSH] <clothes_shirt>', '[PUTIN] <clothes_shirt> <dresser>', '[FIND] <clothes_shirt>', '[GRAB] <clothes_shirt>', '[CLOSE] <dresser>', '[WALK] <basket_for_clothes>', '[PUTBACK] <clothes_shirt> <basket_for_clothes>']
}
|
Scene_Objects:['sheets', 'glue', 'tablelamp', 'mop', 'microwave', 'freezer', 'walllamp', 'needle', 'food_egg', 'floor', 'ceiling', 'tea_bag', 'keyboard', 'stovefan', 'stereo', 'form', 'dining_room', 'wall', 'oven', 'powersocket', 'cutting_board', 'toy', 'keys', 'food_food', 'coffe_maker', 'wine', 'tray', 'kitchen_counter', 'clothes_scarf', 'creditcard']
Task:Put groceries in Fridge
response:
| {
"thoughts": "Open the fridge, and put groceries in the fridge. 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:['sponge', 'pot', 'tablelamp', 'ground_coffee', 'walllamp', 'trashcan', 'knifeblock', 'longboard', 'floor', 'ceiling', 'character', 'bookmark', 'toaster', 'tvstand', 'wall', 'clothes_gloves', 'keys', 'coffe_maker', 'check', 'video_game_controller', 'coffee_filter', 'toilet_paper', 'food_onion', 'curtain', 'kitchen_counter', 'controller', 'hairdryer', 'dishwasher', 'vase', 'soap']
Task:Make coffee
response:
{
"thoughts": You walk into the kitchen and turn to the coffee maker. You grab the coffee filter and put into the coffee machine, you also grab the ground coffee and put it into the coffee machine. You turn on the coffee machine.,
"actions": ['[WALK] <dining_room>', '[WALK] <coffe_maker>', '[FIND] <coffe_maker>', '[TURNTO] <coffe_maker>', '[FIND] <coffee_filter>', '[GRAB] <coffee_filter>', '[OPEN] <coffe_maker>', '[PUTBACK] <coffee_filter> <coffe_maker>', '[FIND] <ground_coffee>', '[GRAB] <ground_coffee>', '[PUTBACK] <ground_coffee> <coffe_maker>', '[SWITCHON] <coffe_maker>']
}
|
Scene_Objects:['tablelamp', 'chair', 'drawing', 'floor', 'character', 'clothes_jacket', 'mop_bucket', 'mat', 'ceilinglamp', 'window', 'mousepad', 'couch', 'dustpan', 'pillow', 'wall', 'oven', 'cutting_board', 'novel', 'coffe_maker', 'television', 'curtain', 'doorjamb', 'shoes', 'hairbrush', 'dresser', 'maindoor', 'sink', 'napkin', 'table', 'soap']
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:['sheets', 'mop', 'microwave', 'ground_coffee', 'walllamp', 'cat', 'trashcan', 'knifeblock', 'cpuscreen', 'floor', 'ceiling', 'bedroom', 'toaster', 'brush', 'tvstand', 'shower', 'faucet', 'food_jam', 'wall', 'nightstand', 'photoframe', 'coffe_maker', 'mouthwash', 'coffee_filter', 'curtain', 'doorjamb', 'kitchen_counter', 'cupboard', 'dishwasher', 'scrabble']
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>']
}
|
Scene_Objects:['sheets', 'glue', 'measuring_cup', 'dog', 'walllamp', 'bathroom', 'floor', 'phone', 'bedroom', 'mat', 'stereo', 'faucet', 'window', 'closetdrawer', 'dining_room', 'food_cheese', 'standingmirror', 'bed', 'check', 'television', 'coffee_filter', 'food_rice', 'ice', 'curtain', 'doorjamb', 'pencil', 'conditioner', 'bathtub', 'napkin', 'vase']
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:['measuring_cup', 'chair', 'walllamp', 'drawing', 'orchid', 'wallshelf', 'floor', 'bookshelf', 'brush', 'mat', 'stereo', 'picture', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'oven', 'shelf', 'cup', 'television', 'wine', 'curtain', 'food_onion', 'doorjamb', 'towel_rack', 'mouse', 'cd', 'home_office', 'table']
Task:Listen to music
response:
{
"thoughts": Walk to living room. Walk to radio. Switch on the radio. Walk to sofa and sit on it.,
"actions": ['[WALK] <home_office>', '[WALK] <stereo>', '[SWITCHON] <stereo>', '[WALK] <couch>', '[SIT] <couch>']
}
|
Scene_Objects:['filing_cabinet', 'tablelamp', 'chair', 'drawing', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'phone', 'character', 'computer', 'stovefan', 'mat', 'faucet', 'window', 'couch', 'pillow', 'wall', 'wall_clock', 'newspaper', 'photoframe', 'television', 'curtain', 'rag', 'doorjamb', 'mouse', 'pencil', 'table', 'vase', 'creditcard']
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:['pot', 'water_glass', 'toilet', 'jelly', 'freezer', 'walllamp', 'drawing', 'floor', 'ceiling', 'stovefan', 'mat', 'shower', 'food_kiwi', 'wall', 'nightstand', 'oven', 'powersocket', 'photoframe', 'food_food', 'coffe_maker', 'water', 'tray', 'doorjamb', 'coffee_pot', 'kitchen_counter', 'cupboard', 'door', 'food_steak', 'spoon', 'light', 'dishwasher']
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>']
}
|
Scene_Objects:['spectacles', 'food_pizza', 'filing_cabinet', 'tablelamp', 'freezer', 'nail_polish', 'cpuscreen', 'desk', 'bookshelf', 'keyboard', 'alcohol', 'computer', 'stovefan', 'ceilinglamp', 'shower', 'mousepad', 'wall', 'wall_clock', 'bed', 'coffe_maker', 'mouthwash', 'video_game_controller', 'television', 'razor', 'check', 'tray', 'curtain', 'cd', 'spoon', 'vase']
Task:Pet cat
response:
| {
"thoughts": "Walk to living room. Find the cat. Walk over to the cat. Touch the cat.",
"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:['toilet', 'ceilingfan', 'drawing', 'floor', 'ceiling', 'bedroom', 'remote_control', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'mousepad', 'couch', 'dining_room', 'wall', 'wall_clock', 'powersocket', 'oven', 'television', 'toothbrush_holder', 'curtain', 'doorjamb', 'console', 'dresser', 'cupboard', 'home_office', 'table', 'clothes_skirt', 'vase']
Task:Watch TV
response:
{
"thoughts": Watch the television,
"actions": ['[WALK] <home_office>', '[WALK] <television>', '[TURNTO] <television>', '[LOOKAT] <television>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[SWITCHON] <television>', '[FIND] <couch>', '[TURNTO] <couch>', '[SIT] <couch>', '[TURNTO] <television>', '[WATCH] <television>']
}
|
Scene_Objects:['blender', 'chair', 'walllamp', 'drawing', 'cpuscreen', 'wallshelf', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'foundation', 'mousepad', 'closetdrawer', 'pillow', 'wall', 'nightstand', 'powersocket', 'toy', 'television', 'doorjamb', 'mouse', 'kitchen_counter', 'dresser', 'bathtub', 'napkin', 'light', 'table', 'dirt']
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:['chair', 'walllamp', 'detergent', 'drawing', 'orchid', 'food_egg', 'clothes_underwear', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'folder', 'remote_control', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'shower', 'window', 'couch', 'food_peanut_butter', 'pillow', 'wall', 'bench', 'box', 'television', 'curtain', 'towel_rack', 'table', 'light']
Task:Change TV channel
response:
{
"thoughts": Changing channel,
"actions": ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[TURNTO] <television>', '[POINTAT] <television>', '[DROP] <remote_control>']
}
|
Scene_Objects:['filing_cabinet', 'food_ice_cream', 'toilet', 'chair', 'freezer', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'dvd_player', 'character', 'bookshelf', 'mat', 'window', 'couch', 'dustpan', 'pillow', 'towel', 'wall', 'bench', 'food_food', 'television', 'coin', 'tray', 'curtain', 'doorjamb', 'bathtub', 'spoon', 'table', 'soap']
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:['sponge', 'chair', 'ceilingfan', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'remote_control', 'food_cake', 'envelope', 'computer', 'ceilinglamp', 'tvstand', 'balanceball', 'faucet', 'window', 'couch', 'wall', 'wall_clock', 'light_bulb', 'television', 'curtain', 'hair', 'food_steak', 'sink', 'bathroom_cabinet', 'table', 'dishwasher']
Task:Watch TV
response:
{
"thoughts": I enter the living room and sit on the couch. I grab the remote and turn on the TV.,
"actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>', '[TURNTO] <television>', '[WATCH] <television>']
}
|
Scene_Objects:['tablelamp', 'chair', 'walllamp', 'ground_coffee', 'drawing', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'bookshelf', 'keyboard', 'computer', 'stovefan', 'ceilinglamp', 'mousepad', 'closetdrawer', 'dining_room', 'wall', 'nightstand', 'powersocket', 'check', 'television', 'doorjamb', 'mouse', 'pencil', 'dresser', 'sink', 'light', 'table']
Task:Work
response:
| {
"thoughts": "I go to the home office to work on my project. I turn on the light and walk to my desk. I turn on the computer. Then I look through the documents. After I'm done, I turn off the computer.",
"actions": [
"[WALK] <home_office>",
"[WALK] <light>",
"[FIND] <light>",
"[SWITCHON] <light>",
"[WALK] <desk>",
"[FIND] <computer>",
"[SWITCHON] <computer>",
"[FIND] <check>",
"[TURNTO] <check>",
"[LOOKAT] <check>",
"[SWITCHOFF] <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', '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:['tea', 'microwave', 'toilet', 'jelly', 'bathroom_counter', 'floor', 'ceiling', 'toaster', 'mat', 'faucet', 'food_noodles', 'clothes_socks', 'mousepad', 'closetdrawer', 'food_kiwi', 'wall', 'cutting_board', 'cup', 'coffe_maker', 'toothbrush_holder', 'television', 'oven_mitts', 'water', 'kitchen_counter', 'dresser', 'cupboard', 'sink', 'home_office', 'soap', 'tooth_paste']
Task:Drink
response:
| {
"thoughts": "Walk to kitchen, walk to cupboard, open cupboard, grab cup, walk to sink, pour water in cup, drink water.",
"actions": [
"[WALK] <dining_room>",
"[WALK] <cupboard>",
"[FIND] <cupboard>",
"[OPEN] <cupboard>",
"[FIND] <cup>",
"[GRAB] <cup>",
"[WALK] <sink>",
"[WALK] <water>",
"[FIND] <water>",
"[GRAB] <water>",
"[POUR] <water> <cup>",
"[DRINK] <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:['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>']
}
|
Scene_Objects:['filing_cabinet', 'blender', 'food_salt', 'toilet', 'walllamp', 'bathroom', 'food_butter', 'drawing', 'hanger', 'shampoo', 'bedroom', 'purse', 'computer', 'stovefan', 'laptop', 'ceilinglamp', 'electric_shaver', 'window', 'homework', 'clothes_socks', 'wall_clock', 'shelf', 'basket_for_clothes', 'bed', 'coffe_maker', 'check', 'wooden_spoon', 'centerpiece', 'lighter', 'kettle']
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>"
]
} |
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:['juice', 'food_salt', 'beer', 'microwave', 'trashcan', 'food_carrot', 'milk', 'ceilingfan', 'drawing', 'hanger', 'floor', 'ceiling', 'phone', 'character', 'ceilinglamp', 'tvstand', 'balanceball', 'deck_of_cards', 'window', 'mousepad', 'couch', 'wall', 'bench', 'television', 'curtain', 'mouse', 'controller', 'clothes_scarf', 'napkin', 'table']
Task:Watch TV
response:
{
"thoughts": I sit on the couch and watch TV.,
"actions": ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <couch>', '[SIT] <couch>', '[TURNTO] <television>', '[LOOKAT] <television>', '[WATCH] <television>']
}
|
Scene_Objects:['tablelamp', 'toilet', 'dog', 'nail_polish', 'orchid', 'drawing', 'floor', 'ceiling', 'character', 'desk', 'computer', 'clothes_jacket', 'stovefan', 'mat', 'tvstand', 'oil', 'wall', 'wall_clock', 'powersocket', 'photoframe', 'newspaper', 'food_food', 'doorjamb', 'shoes', 'maindoor', 'bathtub', 'light', 'tooth_paste', 'clothes_shirt', 'scrabble']
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>"
]
} |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.