input
stringlengths 1.39k
2.78k
| thoughts
stringlengths 11
442
|
|---|---|
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:['freezer', 'toothbrush', 'cpuscreen', 'clothes_underwear', 'wallshelf', 'floor', 'phone', 'ceiling', 'character', 'bookshelf', 'computer', 'button', 'pillow', 'dining_room', 'bench', 'food_food', 'television', 'tray', 'curtain', 'doorjamb', 'towel_rack', 'mouse', 'cd', 'dresser', 'cupboard', 'pajamas', 'clothes_dress', 'sink', 'home_office', 'laser_pointer'] Task:Browse internet response: { thoughts : Walk to home office. Walk to computer. Switch on Computer., actions : ['[WALK] <home_office>', '[WALK] <computer>', '[SWITCHON] <computer>'] } Scene_Objects:['tablelamp', 'chair', 'bathroom', 'milk', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'oil', 'pillow', 'wall', 'nightstand', 'pasta', 'newspaper', 'television', 'towel_rack', 'mouse', 'headset', 'chessboard', 'door', 'sink'] Task:Read news response: | { Read news articles in a newspaper } |
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', 'measuring_cup', 'mop', 'microwave', 'toilet', 'bathroom', 'drawing', 'orchid', 'floor', 'ceiling', 'bedroom', 'computer', 'piano_bench', 'ceilinglamp', 'plate', 'deck_of_cards', 'mat', 'mousepad', 'couch', 'pillow', 'wall', 'bed', 'novel', 'television', 'doorjamb', 'door', 'coffee_cup', 'table', 'light'] Task:Relax on sofa response: { thoughts : you walk to the living room, open the door, find a comfy sofa, sit on it, read a book or sip a cup of coffee and relax., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[FIND] <coffee_cup>', '[GRAB] <coffee_cup>', '[SIT] <couch>', '[FIND] <novel>', '[GRAB] <novel>', '[READ] <novel>', '[DRINK] <coffee_cup>'] } Scene_Objects:['jelly', 'walllamp', 'drawing', 'wallshelf', 'floor', 'ceiling', 'bedroom', 'keyboard', 'bookshelf', 'envelope', 'computer', 'toaster', 'mat', 'tvstand', 'shower', 'mousepad', 'closetdrawer', 'couch', 'pillow', 'wall', 'newspaper', 'photoframe', 'check', 'television', 'doorjamb', 'hairbrush', 'pajamas', 'table', 'clothes_shirt', 'dirt'] Task:Read newspaper response: | { Read the newspaper on the 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', 'toilet', 'freezer', 'walllamp', 'bathroom', 'knifeblock', 'wallshelf', 'cpuscreen', 'floor', 'phone', 'character', 'desk', 'food_cake', 'toaster', 'ceilinglamp', 'couch', 'pillow', 'powersocket', 'basket_for_clothes', 'cup', 'newspaper', 'food_food', 'check', 'oven_mitts', 'wooden_spoon', 'centerpiece', 'kitchen_counter', 'door', 'light'] Task:Pick up phone response: { thoughts : I walk to the home office, find where the phone is and lift the reciever., actions : ['[WALK] <home_office>', '[WALK] <phone>', '[FIND] <phone>', '[GRAB] <phone>'] } Scene_Objects:['glue', 'filing_cabinet', 'tea', 'walllamp', 'bathroom', 'drawing', 'orchid', 'wallshelf', 'clothes_underwear', 'food_egg', 'floor', 'ceiling', 'bedroom', 'keyboard', 'computer', 'bookmark', 'mat', 'tvstand', 'couch', 'pillow', 'wall', 'cup', 'photoframe', 'bed', 'toilet_paper', 'television', 'doorjamb', 'dresser', 'light', 'creditcard'] Task:Read book response: | { Pick up a book and open to the last page you were on. Read the 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:['tablelamp', 'toilet', 'chair', 'walllamp', 'trashcan', 'ceilingfan', 'drawing', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'balanceball', 'mousepad', 'oil', 'wall', 'nightstand', 'photoframe', 'doorjamb', 'mouse', 'dresser', 'cupboard', 'clothes_dress', 'door', 'light'] Task:Browse internet response: { thoughts : I want to surf the internet and look around at funny pictures., actions : ['[WALK] <home_office>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>', '[FIND] <keyboard>', '[GRAB] <keyboard>', '[FIND] <desk>', '[OPEN] <desk>', '[PUTBACK] <keyboard> <desk>', '[FIND] <mouse>', '[GRAB] <mouse>', '[FIND] <mousepad>', '[PUTBACK] <mouse> <mousepad>', '[PLUGIN] <keyboard>', '[PLUGIN] <mouse>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <chair>', '[SIT] <chair>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[GRAB] <mouse>', '[TOUCH] <mouse>', '[TYPE] <keyboard>', '[TURNTO] <computer>', '[LOOKAT] <computer>'] } Scene_Objects:['tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'mail', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'television', 'doorjamb', 'mouse', 'dresser', 'conditioner', 'door', 'table'] Task:Check email response: | { I log onto my computer and then go to the e-mail app, I click on each new email and read them } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['microwave', 'toilet', 'detergent', 'food_butter', 'dough', 'orchid', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'purse', 'faucet', 'stereo', 'picture', 'dustpan', 'bowl', 'dining_room', 'wall', 'oven', 'powersocket', 'photoframe', 'wine', 'tray', 'console', 'pencil', 'sink', 'bathroom_cabinet', 'dishwasher', 'hands_both', 'shoe_rack'] Task:Wash hands response: { thoughts : I go to the bathroom, walk to the sink, turn on the faucet and then wash my hands under the water., actions : ['[WALK] <bathroom>', '[WALK] <sink>', '[FIND] <faucet>', '[TURNTO] <faucet>', '[FIND] <hands_both>', '[WASH] <hands_both>'] } Scene_Objects:['chair', 'walllamp', 'woman', 'toothbrush', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'stamp', 'bookshelf', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'stereo', 'closetdrawer', 'couch', 'pillow', 'wall', 'child', 'box', 'photoframe', 'television', 'oven_mitts', 'doorjamb', 'cd', 'dresser', 'table'] Task:Watch movie response: | { Sitting and watching a movie with family } |
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', 'trashcan', 'ceilingfan', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'balanceball', 'mousepad', 'dustpan', 'dining_room', 'wall', 'nightstand', 'pasta', 'tape', 'photoframe', 'tray', 'rag', 'doorjamb', 'towel_rack', 'mouse', 'bathroom_cabinet', 'light'] Task:Turn on computer response: { thoughts : Press the power button on the computer to turn it on, actions : ['[WALK] <home_office>', '[WALK] <computer>', '[SWITCHON] <computer>'] } Scene_Objects:['filing_cabinet', 'tablelamp', 'freezer', 'orchid', 'floor', 'bedroom', 'keyboard', 'stovefan', 'stereo', 'shower', 'closetdrawer', 'couch', 'dining_room', 'tape', 'cup', 'bed', 'novel', 'television', 'toothbrush_holder', 'doorjamb', 'mouse', 'kitchen_counter', 'chessboard', 'cupboard', 'door', 'spoon', 'instrument_guitar', 'table', 'clothes_shirt', 'shoe_rack'] Task:Look out window response: | { I head into my child's room and look out the window to view the neighborhood from a different area in the house. } |
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_bread', 'crayon', 'measuring_cup', 'chair', 'walllamp', 'trashcan', 'bedroom', 'bookshelf', 'purse', 'table_cloth', 'faucet', 'clothes_socks', 'pillow', 'wall', 'oven', 'newspaper', 'photoframe', 'coffe_maker', 'food_food', 'check', 'coffee_filter', 'shaving_cream', 'pencil', 'headset', 'dishrack', 'comb', 'dresser', 'spoon', 'instrument_guitar'] 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:['scissors', 'tablelamp', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'bookshelf', 'alcohol', 'mat', 'tvstand', 'stereo', 'closetdrawer', 'couch', 'clothes_pants', 'food_jam', 'pillow', 'microphone', 'dining_room', 'wall', 'powersocket', 'photoframe', 'television', 'doorjamb', 'dresser', 'door', 'hairdryer', 'light', 'instrument_violin', 'clothes_shirt'] Task:Getting dresses response: | { Putting on undergarments and clothes } |
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_ice_cream', 'blow_dryer', 'detergent', 'ceilingfan', 'drawing', 'hanger', 'longboard', 'floor', 'ceiling', 'phone', 'bedroom', 'keyboard', 'remote_control', 'ceilinglamp', 'tvstand', 'balanceball', 'faucet', 'window', 'shoe-shine_kit', 'couch', 'food_orange', 'wall', 'tape', 'television', 'curtain', 'kitchen_counter', 'conditioner', 'bathroom_cabinet', 'table'] Task:Relax on sofa response: { thoughts : For relaxing walk to living room. Find the sofa to relax. Arrange the sofa to relax. Sit on the sofa to relaxing., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[FIND] <conditioner>', '[FIND] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>', '[LIE] <couch>'] } 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: | { Sit at my computer desk, Turn on Computer. Get online. Work. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['walllamp', 'ceilingfan', 'drawing', 'needle', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'homework', 'clothes_socks', 'couch', 'pillow', 'wall', 'powersocket', 'food_cheese', 'bed', 'television', 'wooden_spoon', 'curtain', 'doorjamb', 'bathroom_cabinet', 'table', 'laser_pointer'] Task:Watch TV response: { thoughts : Walk into the living room. Sit down on the sofa. Pick up the remote control. Turn on the television with the remote control. Put down the remote control. Watch the television., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>', '[PUTOBJBACK] <remote_control>', '[TURNTO] <television>', '[WATCH] <television>'] } Scene_Objects:['glue', 'pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'novel', 'check', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'door', 'light'] Task:Work response: | { I sit at my desk and work on the 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', 'band-aids', 'trashcan', 'dough', 'knifeblock', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'shampoo', 'dvd_player', 'desk', 'bookshelf', 'keyboard', 'computer', 'stovefan', 'mat', 'tvstand', 'shower', 'mousepad', 'food_orange', 'wall', 'oven', 'keys', 'mouse', 'shoes', 'hair', 'dishwasher', 'vase', 'coffee'] Task:Read book response: { thoughts : find a book to read. sit down. read the book., actions : ['[WALK] <home_office>', '[WALK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[WALK] <chair>', '[SIT] <chair>', '[READ] <novel>'] } Scene_Objects:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'stamp', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'picture', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'door', 'light'] Task:Pay bills response: | { Check my bills, on the computer, open the appropriate sites, pay my due bills } |
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', 'walllamp', 'ground_coffee', 'nail_polish', 'orchid', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'keyboard', 'bookshelf', 'computer', 'alcohol', 'toaster', 'ceilinglamp', 'mat', 'faucet', 'stovefan', 'mousepad', 'oil', 'wall', 'bed', 'mouse', 'cupboard', 'door', 'hairdryer', 'table'] Task:Work response: { thoughts : Go to office, find computer, switch on computer, type on keyboard, use mouse, switch off computer, actions : ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <keyboard>', '[TYPE] <keyboard>', '[FIND] <mouse>', '[PUSH] <mouse>', '[SWITCHOFF] <computer>'] } Scene_Objects:['sheets', 'microwave', 'chair', 'walllamp', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'shampoo', 'desk', 'keyboard', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'stereo', 'closetdrawer', 'couch', 'pillow', 'wall', 'child', 'photoframe', 'food_food', 'television', 'after_shave', 'doorjamb', 'dresser', 'sink', 'bathroom_cabinet'] Task:Watch TV response: | { Turn on tv. Sit with kids. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['walllamp', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'phone', 'bookshelf', 'remote_control', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'photoframe', 'coffee_table', 'television', 'wooden_spoon', 'curtain', 'doorjamb', 'centerpiece', 'door', 'bathroom_cabinet', 'table', 'light', 'board_game'] 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:['filing_cabinet', 'microwave', 'chair', 'walllamp', 'drawing', 'wallshelf', 'floor', 'ceiling', 'bookshelf', 'computer', 'bookmark', 'stovefan', 'mat', 'tvstand', 'faucet', 'couch', 'food_jam', 'pillow', 'dining_room', 'wall', 'nightstand', 'photoframe', 'television', 'doorjamb', 'coffee_pot', 'dresser', 'bathroom_cabinet', 'dishwasher', 'laser_pointer', 'shoe_rack'] Task:Read book response: | { Bring book, lie on the sofa, read book } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'filing_cabinet', 'tablelamp', 'microwave', 'freezer', 'detergent', 'drawing', 'floor', 'ceiling', 'stamp', 'bedroom', 'thread', 'computer', 'toaster', 'faucet', 'mousepad', 'food_peanut_butter', 'wall', 'powersocket', 'toy', 'cup', 'newspaper', 'doorjamb', 'chessboard', 'comb', 'door', 'sink', 'bag', 'light', 'board_game'] Task:Clean response: { thoughts : Enter inside kid's room, begin picking up toys from the floor and putting them in a toy box, leave once once., actions : ['[WALK] <bedroom>', '[WALK] <toy>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <filing_cabinet>', '[OPEN] <filing_cabinet>', '[PUTBACK] <toy> <filing_cabinet>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <filing_cabinet>', '[PUTBACK] <toy> <filing_cabinet>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <filing_cabinet>', '[PUTBACK] <toy> <filing_cabinet>', '[CLOSE] <filing_cabinet>'] } Scene_Objects:['tablelamp', 'chair', 'orchid', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'food_cake', 'thread', 'computer', 'laptop', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'wall', 'nightstand', 'oven', 'pasta', 'television', 'tray', 'doorjamb', 'mouse', 'headset', 'chessboard', 'cupboard', 'door'] Task:Watch movie response: | { Sit in my deck chair with my laptop, find a good movie on You Tube to watch, plug in earphones and listen to movie quietly so I don't disturb my upstairs neighbor. } |
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_bread', 'filing_cabinet', 'tablelamp', 'chair', 'trashcan', 'ceilingfan', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'deck_of_cards', 'balanceball', 'mousepad', 'food_noodles', 'pillow', 'wall', 'nightstand', 'oven', 'basket_for_clothes', 'doorjamb', 'towel_rack', 'mouse', 'light'] Task:Work response: { thoughts : walk to home office ,find computer ,switch on computer and work, actions : ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>'] } Scene_Objects:['pot', 'filing_cabinet', 'tablelamp', 'crayon', 'chair', 'walllamp', 'drawing', 'orchid', 'wallshelf', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'bookshelf', 'keyboard', 'computer', 'bookmark', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'powersocket', 'oven', 'photoframe', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'kitchen_counter', 'door', 'clothes_scarf', 'light'] Task:Re arrange office response: | { Walk in.Turn on light.Move furniture. Change the room } |
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', 'tea', 'toilet', 'walllamp', 'drawing', 'orchid', 'floor', 'desk', 'bedroom', 'computer', 'ceilinglamp', 'tvstand', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'food_cheese', 'bed', 'food_donut', 'curtain', 'food_onion', 'mouse', 'pajamas', 'controller', 'table', 'dishwasher', 'light', '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:['sheets', 'pot', 'microwave', 'bathroom', 'drawing', 'wallshelf', 'floor', 'ceiling', 'bedroom', 'toaster', 'stovefan', 'deck_of_cards', 'shower', 'pillow', 'wall', 'powersocket', 'cup', 'coffe_maker', 'check', 'wine', 'food_onion', 'curtain', 'lighter', 'kitchen_counter', 'cupboard', 'hair', 'controller', 'table', 'dishwasher', 'colander'] Task:Take dishes out of dishwasher response: | { Take clean dishes out of the dishwasher and put away } |
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', 'freezer', 'walllamp', 'bathroom', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'dvd_player', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'television', 'doorjamb', 'mouse', 'dresser', 'door'] 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>'] } Scene_Objects:['sheets', 'filing_cabinet', 'measuring_cup', 'toilet', 'chair', 'cat', 'milk', 'orchid', 'phone', 'video_game_console', 'bookshelf', 'keyboard', 'purse', 'table_cloth', 'brush', 'mat', 'iron', 'couch', 'cup', 'basket_for_clothes', 'video_game_controller', 'oven_mitts', 'food_donut', 'doorjamb', 'console', 'dresser', 'laundry_detergent', 'sink', 'bathroom_cabinet', 'home_office'] Task:Playing video game response: | { Playing video games on various video game systems such as wii u and xbox } |
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_oatmeal', 'microwave', 'freezer', 'bathroom', 'nail_polish', 'dough', 'food_carrot', 'orchid', 'drawing', 'knife', 'kitchen_cabinet', 'floor', 'ceiling', 'desk', 'brush', 'mat', 'couch', 'pillow', 'food_cereal', 'wall', 'food_vegetable', 'food_food', 'television', 'console', 'cards', 'kitchen_counter', 'cupboard', 'hair', 'door', 'light'] Task:Put groceries in Fridge response: { thoughts : Walk to kitchen, find groceries in cabinet and move them to fridge and close fridge., actions : ['[WALK] <dining_room>', '[WALK] <kitchen_cabinet>', '[FIND] <kitchen_cabinet>', '[FIND] <food_vegetable>', '[GRAB] <food_vegetable>', '[FIND] <freezer>', '[OPEN] <freezer>', '[PUTIN] <food_vegetable> <freezer>', '[FIND] <food_carrot>', '[GRAB] <food_carrot>', '[PUTIN] <food_carrot> <freezer>', '[FIND] <food_cereal>', '[GRAB] <food_cereal>', '[PUTIN] <food_cereal> <freezer>', '[FIND] <food_oatmeal>', '[GRAB] <food_oatmeal>', '[PUTIN] <food_oatmeal> <freezer>', '[FIND] <food_food>', '[GRAB] <food_food>', '[PUTIN] <food_food> <freezer>', '[FIND] <freezer>', '[CLOSE] <freezer>'] } Scene_Objects:['tablelamp', 'mop', 'chair', 'walllamp', 'orchid', 'drawing', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'photoframe', 'television', 'doorjamb', 'mouse', 'dresser', 'door', 'home_office'] Task:Social media checks response: | { Logging on to things like facebook and twitter } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['spectacles', 'tablelamp', 'juice', 'microwave', 'toilet', 'chair', 'walllamp', 'dough', 'drawing', 'cpuscreen', 'floor', 'folder', 'desk', 'bookshelf', 'keyboard', 'computer', 'mail', 'shower', 'picture', 'mousepad', 'wall', 'nightstand', 'bench', 'oven', 'photoframe', 'novel', 'check', 'food_food', 'centerpiece', 'mouse'] Task:Arrange folders response: { thoughts : Go through all my folders and re-arrange in alfabetaical order and put on computer desk, actions : ['[WALK] <home_office>', '[WALK] <desk>', '[FIND] <folder>', '[GRAB] <folder>', '[OPEN] <desk>', '[PUTBACK] <folder> <desk>', '[FIND] <folder>', '[GRAB] <folder>', '[PUTBACK] <folder> <desk>', '[FIND] <folder>', '[GRAB] <folder>', '[PUTBACK] <folder> <desk>', '[FIND] <folder>', '[GRAB] <folder>', '[PUTBACK] <folder> <desk>', '[FIND] <folder>', '[GRAB] <folder>', '[PUTBACK] <folder> <desk>'] } Scene_Objects:['tablelamp', 'chair', 'cloth_napkin', 'walllamp', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'television', 'doorjamb', 'mouse', 'pencil', 'headset', 'dresser', 'door', 'sink'] Task:Clean response: | { Use a cloth to wipe away any marks on the computer screen. } |
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', 'beer', 'mop', 'chair', 'freezer', 'orchid', 'floor', 'ceiling', 'character', 'bedroom', 'desk', 'keyboard', 'toaster', 'shower', 'window', 'food_orange', 'wall', 'oven', 'cup', 'photoframe', 'food_food', 'curtain', 'towel_rack', 'kitchen_counter', 'cupboard', 'door', 'spoon', 'table', 'light', 'coffee'] Task:Put groceries in Fridge response: { thoughts : I take the groceries out of the grocery bags, throw away grocery bags, categorize the food so that I know where it goes in the fridge, open the fridge, and place each item in the fridge before closing the fridge., actions : ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <food_food>', '[GRAB] <food_food>', '[PUTIN] <food_food> <freezer>', '[CLOSE] <freezer>'] } Scene_Objects:['tablelamp', 'walllamp', 'food_butter', 'toothbrush', 'drawing', 'hanger', 'floor', 'ceiling', 'bookshelf', 'ceilinglamp', 'mousepad', 'closetdrawer', 'oil', 'microphone', 'pillow', 'dining_room', 'broom', 'wall', 'nightstand', 'powersocket', 'bed', 'photoframe', 'razor', 'television', 'doorjamb', 'kettle', 'mouse', 'dresser', 'door', 'light'] Task:Turn off light response: | { Hit the switch. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'walllamp', 'orchid', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'bedroom', 'bookshelf', 'remote_control', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'mousepad', 'pillow', 'wall', 'powersocket', 'photoframe', 'bed', 'coffe_maker', 'television', 'curtain', 'doorjamb', 'mouse', 'door', 'sink', 'light', 'coffee'] Task:Watch TV response: { thoughts : walk to living room ,find television , switch on remote control, actions : ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[FIND] <remote_control>', '[SWITCHON] <remote_control>'] } Scene_Objects:['tablelamp', 'scissors', 'microwave', 'chair', 'drawing', 'orchid', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'keyboard', 'bookshelf', 'computer', 'brush', 'mat', 'ceilinglamp', 'tvstand', 'window', 'mousepad', 'wall', 'nightstand', 'powersocket', 'food_food', 'television', 'curtain', 'lighter', 'mouse', 'door', 'clothes_scarf'] Task:Enjoy view out window response: | { Sitting in teak deck chair, gaze out window at the view. } |
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', 'toilet', 'walllamp', 'ground_coffee', 'trashcan', 'desk', 'bedroom', 'purse', 'mop_bucket', 'shower', 'picture', 'homework', 'mousepad', 'form', 'wall', 'oven', 'bed', 'keys', 'video_game_controller', 'wine', 'food_onion', 'after_shave', 'console', 'mouse', 'cd', 'comb', 'dresser', 'door', 'clothes_skirt', 'dirt'] Task:Pet cat response: { thoughts : Find the cat; pet the cat by touching it, actions : ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[TOUCH] <cat>'] } Scene_Objects:['fork', 'pot', 'food_pizza', 'juice', 'microwave', 'freezer', 'drawing', 'orchid', 'floor', 'ceiling', 'tea_bag', 'keyboard', 'toaster', 'mat', 'stovefan', 'shower', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'food_food', 'coffe_maker', 'television', 'tray', 'towel_rack', 'kitchen_counter', 'cupboard', 'food_snack', 'dishwasher'] Task:Have snack response: | { Pour soda into a glass. Get pretzels out of bag. Eat and drink } |
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', 'pot', 'measuring_cup', 'jelly', 'chair', 'freezer', 'hanger', 'ceiling', 'thread', 'computer', 'mail', 'bookmark', 'deck_of_cards', 'faucet', 'mousepad', 'dining_room', 'broom', 'wall', 'wall_clock', 'box', 'razor', 'doorjamb', 'mouse', 'pencil', 'hairbrush', 'door', 'napkin', 'table', 'light', 'dirt'] Task:Pick up phone response: { thoughts : Enter the Home office, then walk to the phone, pickup the phone., actions : ['[WALK] <home_office>', '[WALK] <phone>', '[GRAB] <phone>'] } Scene_Objects:['pot', 'filing_cabinet', 'tablelamp', 'toilet', 'bathroom', 'drawing', 'hanger', 'floor', 'bedroom', 'stovefan', 'mat', 'tvstand', 'stereo', 'faucet', 'couch', 'wall', 'nightstand', 'powersocket', 'oven', 'bed', 'photoframe', 'coffe_maker', 'check', 'kettle', 'kitchen_counter', 'dresser', 'home_office', 'light', 'dishwasher', 'teeth'] Task:Listen to music response: | { Put iPhone into speaker holder, open up the Pandora app, listen to music. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'dry_pasta', 'ceilingfan', 'trashcan', 'drawing', 'longboard', 'floor', 'ceiling', 'bedroom', 'stovefan', 'ceilinglamp', 'tvstand', 'balanceball', 'laptop', 'window', 'shower', 'deck_of_cards', 'couch', 'food_kiwi', 'wall', 'tape', 'basket_for_clothes', 'keys', 'coffe_maker', 'toilet_paper', 'television', 'curtain', 'cd', 'controller', 'table'] Task:Watch TV response: { thoughts : Sit on the couch. Get comfortable. Switch on the television. Stare at the television., actions : ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <couch>', '[SIT] <couch>', '[TURNTO] <television>', '[WATCH] <television>'] } Scene_Objects:['pot', 'filing_cabinet', 'chair', 'walllamp', 'drawing', 'wallshelf', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'remote_control', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'closetdrawer', 'couch', 'pillow', 'wall', 'powersocket', 'oven', 'photoframe', 'television', 'doorjamb', 'towel_rack', 'dresser', 'pajamas', 'sink', 'dishwasher'] Task:Watch TV response: | { We sit on the couch facing the tv turn on the television with the remote and watch programs } |
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_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>'] } Scene_Objects:['dry_pasta', 'pot', 'filing_cabinet', 'food_pizza', 'chair', 'walllamp', 'detergent', 'food_carrot', 'drawing', 'floor', 'desk', 'alcohol', 'computer', 'brush', 'mat', 'stovefan', 'toaster', 'tvstand', 'foundation', 'pillow', 'wall', 'toy', 'tape', 'bed', 'keys', 'food_rice', 'curtain', 'pencil', 'comb', 'dresser'] Task:Pick up toys response: | { Grab toys off floor. Put it in a container. } |
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', 'dough', 'orchid', 'knife', 'clothes_underwear', 'phone', 'tea_bag', 'envelope', 'mat', 'faucet', 'clothes_socks', 'clothes_pants', 'clothes_hat', 'bench', 'powersocket', 'basket_for_clothes', 'food_food', 'food_rice', 'tray', 'curtain', 'after_shave', 'doorjamb', 'pencil', 'laundry_detergent', 'bathroom_cabinet', 'table', 'light', '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>'] } Scene_Objects:['scissors', 'tablelamp', 'chair', 'freezer', 'walllamp', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'faucet', 'shower', 'closetdrawer', 'couch', 'pillow', 'wall', 'nightstand', 'photoframe', 'newspaper', 'television', 'doorjamb', 'dresser', 'soap', 'instrument_violin'] Task:Watch TV response: | { I sit on my couch and watch TV in my living room } |
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', 'blender', 'milk', 'orchid', 'bathroom_counter', 'floor', 'phone', 'keyboard', 'thread', 'stovefan', 'mat', 'toaster', 'faucet', 'plate', 'couch', 'food_jam', 'pillow', 'dining_room', 'wall', 'wall_clock', 'oven', 'tray', 'curtain', 'mouse', 'sink', 'napkin', 'bathroom_cabinet', 'soap'] Task:Wash hands response: { thoughts : walk to bathroom, find sink, turn on faucet, put soap in hands, wash and rinse hands,, actions : ['[WALK] <bathroom>', '[WALK] <sink>', '[FIND] <sink>', '[FIND] <soap>', '[WASH] <soap>', '[RINSE] <soap>'] } Scene_Objects:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'stamp', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'television', 'fax_machine', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'door', 'light'] Task:Write report response: | { Sit at a desk, turn on a computer. Open an existing document and revise it. Print a hard copy for mailing. Email a copy to the client. } |
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', 'chair', 'jelly', 'trashcan', 'toothbrush', 'orchid', 'cpuscreen', 'character', 'bookshelf', 'button', 'mat', 'deck_of_cards', 'faucet', 'shower', 'pillow', 'powersocket', 'bench', 'photoframe', 'bed', 'novel', 'coin', 'kitchen_counter', 'headset', 'chessboard', 'comb', 'dresser', 'table', 'coffee', 'creditcard'] Task:Pick up phone response: { thoughts : Walk to the entrance hall. Find the telephone. Grab the telephone., actions : ['[WALK] <home_office>', '[WALK] <phone>', '[FIND] <phone>', '[WALK] <phone>', '[GRAB] <phone>'] } Scene_Objects:['tablelamp', 'chair', 'orchid', 'drawing', 'cpuscreen', 'bills', 'floor', 'ceiling', 'phone', 'character', 'desk', 'keyboard', 'computer', 'mail', 'mat', 'ceilinglamp', 'tvstand', 'laptop', 'mousepad', 'clothes_socks', 'wall', 'nightstand', 'oven', 'powersocket', 'television', 'mouse', 'shoes', 'comb', 'door', 'light'] Task:Check email response: | { Turn on laptop. Connect to Internet. Type in the url. Check for new email messages. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'tablelamp', 'chair', 'walllamp', 'knifeblock', 'cpuscreen', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'ceilinglamp', 'faucet', 'couch', 'dustpan', 'pillow', 'towel', 'wall', 'nightstand', 'oven', 'box', 'bed', 'keys', 'check', 'toilet_paper', 'television', 'kitchen_counter', 'dresser', 'instrument_guitar', 'soap', 'tooth_paste'] Task:Relax on sofa response: { thoughts : Go to living room. Find sofa. Sit on sofa., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>'] } Scene_Objects:['sheets', 'chair', 'drawing', 'wallshelf', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'purse', 'brush', 'mat', 'stereo', 'clothes_socks', 'closetdrawer', 'couch', 'mousepad', 'pillow', 'bowl', 'wall', 'powersocket', 'photoframe', 'tray', 'doorjamb', 'pencil', 'shoes', 'cd', 'dresser', 'door', 'bathroom_cabinet', 'light'] Task:Take off shoes response: | { Bend down to reach your feet. Shift balance to one leg. Grab the shoe of the foot of the other leg, it is best to use one hand to grip near the front, and one towards the heel. Pull the shoe down toward the ground while also pushing on the heel away from the body. Repeat with other shoe. Place shoes in a designated area. } |
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', 'walllamp', 'bathroom', 'drawing', 'orchid', 'knifeblock', 'floor', 'ceiling', 'bookshelf', 'stovefan', 'couch', 'pillow', 'wall', 'nightstand', 'powersocket', 'toy', 'novel', 'coffe_maker', 'television', 'wooden_spoon', 'doorjamb', 'kitchen_counter', 'shoes', 'cupboard', 'door', 'home_office', 'table', 'light'] Task:Read book response: { thoughts : Go to the living room and find the book you want to read. Take it and then go to the couch. Sit on it, open the book and start reading., actions : ['[WALK] <home_office>', '[WALK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <couch>', '[SIT] <couch>', '[READ] <novel>'] } Scene_Objects:['tablelamp', 'beer', 'chair', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'purse', 'computer', 'food_bacon', 'bookmark', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'wall', 'nightstand', 'television', 'food_donut', 'wine', 'tray', 'mouse', 'kitchen_counter', 'door', 'hairdryer'] Task:Read book response: | { Sitting and reading a hardcover book in a recliner } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'toilet', 'chair', 'freezer', 'walllamp', 'bathroom', 'nail_polish', 'detergent', 'trashcan', 'drawing', 'floor', 'ceiling', 'desk', 'stamp', 'keyboard', 'computer', 'table_cloth', 'stereo', 'mousepad', 'broom', 'wall', 'nightstand', 'powersocket', 'oven', 'television', 'rag', 'mouse', 'headset', 'door', 'shoe_rack'] Task:Listen to music response: { thoughts : I walk to my bedroom. I locate my stereo and turn it on. I put on my headphones and sit to listen., actions : ['[WALK] <bedroom>', '[WALK] <stereo>', '[FIND] <stereo>', '[WALK] <stereo>', '[SWITCHON] <stereo>', '[FIND] <headset>', '[GRAB] <headset>', '[PUTON] <headset>', '[FIND] <chair>', '[SIT] <chair>'] } Scene_Objects:['filing_cabinet', 'chair', 'walllamp', 'bathroom', 'drawing', 'orchid', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'bedroom', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'closetdrawer', 'couch', 'pillow', 'dining_room', 'wall', 'box', 'cup', 'photoframe', 'television', 'doorjamb', 'coffee_pot', 'dresser', 'light'] Task:Watch TV response: | { Sit on the couch. Get comfortable. Switch on the television. Stare at the 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:['water_glass', 'scissors', 'blender', 'chair', 'walllamp', 'drawing', 'wallshelf', 'clothes_underwear', 'floor', 'ceiling', 'character', 'desk', 'computer', 'food_bacon', 'mat', 'tvstand', 'mousepad', 'closetdrawer', 'couch', 'pillow', 'wall', 'cup', 'photoframe', 'newspaper', 'television', 'ice', 'doorjamb', 'diary', 'console', 'towel_rack'] Task:Relax on sofa response: { thoughts : Drink a glass of water in the sofa, actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <water_glass>', '[GRAB] <water_glass>', '[DRINK] <water_glass>'] } Scene_Objects:['food_salt', 'freezer', 'walllamp', 'drawing', 'orchid', 'floor', 'ceiling', 'stamp', 'bookshelf', 'clothes_jacket', 'mop_bucket', 'toaster', 'mat', 'brush', 'shoe-shine_kit', 'laptop', 'couch', 'pillow', 'wall', 'oven', 'cup', 'food_cheese', 'photoframe', 'check', 'television', 'tray', 'food_onion', 'kitchen_counter', 'cupboard', 'bathroom_cabinet'] Task:Eat cheese response: | { Open fridge. Get cheese. Eat it. } |
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', 'filing_cabinet', 'tablelamp', 'crayon', 'woman', 'wallshelf', 'shampoo', 'floor', 'phone', 'desk', 'man', 'bookshelf', 'closetdrawer', 'couch', 'dining_room', 'nightstand', 'child', 'bed', 'photoframe', 'standingmirror', 'toilet_paper', 'oven_mitts', 'towel_rack', 'kitchen_counter', 'dresser', 'sink', 'bathroom_cabinet', 'clothes_skirt', 'vase'] Task:Say goodbye to guests leaving response: { thoughts : Tell them bye, actions : ['[WALK] <home_office>', '[WALK] <child>', '[FIND] <child>', '[TOUCH] <child>', '[FIND] <man>', '[TOUCH] <man>', '[FIND] <woman>', '[TOUCH] <woman>'] } Scene_Objects:['food_pizza', 'chair', 'walllamp', 'dough', 'woman', 'drawing', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'bedroom', 'man', 'keyboard', 'computer', 'mat', 'tvstand', 'couch', 'pillow', 'wall', 'nightstand', 'photoframe', 'coffe_maker', 'television', 'coin', 'wooden_spoon', 'doorjamb', 'clothes_dress', 'clothes_scarf', 'table', 'coffee'] Task:Hang with friends response: | { Sit with friends. Talk } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'toilet', 'freezer', 'cat', 'drawing', 'orchid', 'floor', 'ceiling', 'phone', 'bedroom', 'bookshelf', 'table_cloth', 'ceilinglamp', 'faucet', 'couch', 'clothes_hat', 'pillow', 'wall', 'oven', 'bed', 'photoframe', 'television', 'doorjamb', 'pencil', 'kitchen_counter', 'door', 'bathtub', 'bathroom_cabinet', 'table', 'light'] Task:Pet cat response: { thoughts : I would walk into the living room. Then sit on the couch and pet the cat., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[SIT] <couch>', '[FIND] <cat>', '[TOUCH] <cat>'] } Scene_Objects:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'check', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'door', 'light'] Task:Do homework response: | { I do my online homework on the computer. I use Pearson My Math Lab for math class and excel for my engineering class. } |
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', 'orchid', 'bills', 'cpuscreen', 'knifeblock', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'mat', 'mousepad', 'microphone', 'form', 'towel', 'wall', 'oven', 'food_food', 'television', 'ice', 'cards', 'mouse', 'pencil', 'cupboard', 'door', 'clothes_scarf', 'table'] Task:Clean response: { thoughts : Wipe down computer desk and monitor, actions : ['[WALK] <home_office>', '[WALK] <rag>', '[FIND] <rag>', '[GRAB] <rag>', '[WALK] <desk>', '[FIND] <computer>', '[WIPE] <computer>', '[WIPE] <desk>', '[PUTOBJBACK] <rag>'] } Scene_Objects:['tablelamp', 'chair', 'walllamp', 'bathroom', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'laptop', 'mousepad', 'oil', 'couch', 'pillow', 'wall', 'nightstand', 'television', 'doorjamb', 'mouse', 'dresser', 'door'] Task:Write school paper response: | { Writing and drafting a paper for class work } |
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', 'fork', 'filing_cabinet', 'tablelamp', 'blender', 'mop', 'bathroom', 'detergent', 'toothbrush', 'bills', 'hanger', 'floor', 'bedroom', 'envelope', 'toaster', 'stovefan', 'clothes_socks', 'mousepad', 'powersocket', 'basket_for_clothes', 'coffe_maker', 'toilet_paper', 'towel_rack', 'clothes_dress', 'bag', 'home_office', 'light', 'vase', 'soap', 'washing_machine'] Task:Wash clothes response: { thoughts : Walk to Bathroom. Find basket for clothes. Lift clothes dress from basket. Find washing machine. Walk to washing machine. Put clothes in washing machine. Put soap in washing machine. Switch on washing machine., actions : ['[WALK] <bathroom>', '[WALK] <basket_for_clothes>', '[FIND] <basket_for_clothes>', '[FIND] <clothes_dress>', '[GRAB] <clothes_dress>', '[FIND] <washing_machine>', '[WALK] <washing_machine>', '[OPEN] <washing_machine>', '[PUTBACK] <clothes_dress> <washing_machine>', '[FIND] <soap>', '[GRAB] <soap>', '[PUTBACK] <soap> <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>'] } Scene_Objects:['microwave', 'walllamp', 'food_carrot', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'shampoo', 'computer', 'food_bacon', 'mat', 'tvstand', 'stereo', 'foundation', 'mousepad', 'couch', 'pillow', 'wall', 'photoframe', 'check', 'video_game_controller', 'television', 'doorjamb', 'kitchen_counter', 'dresser', 'hairdryer', 'bag', 'home_office', 'dishwasher'] Task:Relax response: | { Lie down on the 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', 'chair', 'freezer', 'knife', 'drawing', 'needle', 'wallshelf', 'floor', 'phone', 'ceiling', 'dvd_player', 'food_bacon', 'ceilinglamp', 'laptop', 'plate', 'shower', 'tvstand', 'tooth_paste', 'wall', 'tape', 'cup', 'novel', 'food_food', 'television', 'coffee_filter', 'hair', 'cupboard', 'table', 'board_game', 'clothes_shirt'] Task:Eat response: { thoughts : I get my prepared dinner set on the dining table, sit down on chair, pick up utensils, eat food, actions : ['[WALK] <dining_room>', '[WALK] <food_food>', '[FIND] <food_food>', '[GRAB] <food_food>', '[WALK] <dining_room>', '[WALK] <table>', '[FIND] <table>', '[PUTBACK] <food_food> <table>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <fork>', '[GRAB] <fork>', '[FIND] <knife>', '[GRAB] <knife>', '[FIND] <plate>', '[EAT] <plate>'] } Scene_Objects:['microwave', 'toilet', 'bathroom', 'orchid', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'character', 'purse', 'computer', 'food_bacon', 'toaster', 'mat', 'closetdrawer', 'candle', 'wall', 'nightstand', 'television', 'curtain', 'doorjamb', 'centerpiece', 'cards', 'shoes', 'dresser', 'hairbrush', 'bathroom_cabinet', 'clothes_shirt', 'shoe_rack'] Task:Put on coat response: | { Open closet and grab coat. Put on coat and fasten the front closed. Close closet. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'food_pizza', 'tablelamp', 'chair', 'detergent', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'desk', 'bookshelf', 'stovefan', 'ceilinglamp', 'mat', 'faucet', 'shower', 'mousepad', 'dustpan', 'dining_room', 'wall', 'powersocket', 'oven', 'check', 'television', 'doorjamb', 'hairbrush', 'controller', 'sink', 'home_office', 'light'] Task:Turn on light response: { thoughts : Walk to living room. Find light switch. Switch on light switch., actions : ['[WALK] <home_office>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>'] } Scene_Objects:['sponge', 'filing_cabinet', 'cat', 'food_butter', 'hanger', 'floor', 'ceiling', 'food_cake', 'ceilinglamp', 'deck_of_cards', 'tvstand', 'homework', 'mousepad', 'closetdrawer', 'teeth', 'food_jam', 'nightstand', 'powersocket', 'bed', 'check', 'video_game_controller', 'mouthwash', 'towel_rack', 'mouse', 'console', 'cd', 'cupboard', 'instrument_guitar', 'coffee', 'shoe_rack'] Task:Clean response: | { Clean the welcome mat } |
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', 'band-aids', 'bathroom', 'trashcan', 'phone', 'bedroom', 'bookshelf', 'computer', 'stovefan', 'picture', 'window', 'couch', 'bowl', 'broom', 'wall', 'oven', 'bench', 'cup', 'food_food', 'oven_mitts', 'colander', 'curtain', 'pencil', 'kitchen_counter', 'clothes_dress', 'sink', 'dishwasher', 'soap', 'instrument_violin'] 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:['pot', 'filing_cabinet', 'mop', 'measuring_cup', 'dog', 'walllamp', 'bathroom', 'food_butter', 'woman', 'cpuscreen', 'floor', 'ceiling', 'character', 'desk', 'man', 'table_cloth', 'electric_shaver', 'dining_room', 'child', 'mouthwash', 'razor', 'rag', 'doorjamb', 'lighter', 'towel_rack', 'mouse', 'shoes', 'hair', 'food_steak', 'soap'] Task:Greet guests response: | { Greet guests when they knock on the door and invite them to enter my home } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'chair', 'walllamp', 'orchid', 'drawing', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'button', 'ceilinglamp', 'tvstand', 'mat', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'food_food', 'television', 'doorjamb', 'mouse', 'dresser', 'door', 'sink'] Task:Work response: { thoughts : working on computer, actions : ['[WALK] <home_office>', '[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <button>', '[TURNTO] <button>', '[LOOKAT] <button>', '[FIND] <mouse>', '[GRAB] <mouse>', '[GRAB] <button>', '[FIND] <chair>', '[SIT] <chair>', '[SWITCHOFF] <computer>'] } Scene_Objects:['blender', 'chair', 'walllamp', 'detergent', 'milk', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'bedroom', 'remote_control', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'faucet', 'shower', 'closetdrawer', 'couch', 'pillow', 'wall', 'photoframe', 'television', 'doorjamb', 'diary', 'kitchen_counter', 'dresser', 'napkin'] Task:Watch TV response: | { Find the remote, turn on the TV, watch. } |
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', 'trashcan', 'drawing', 'floor', 'character', 'toaster', 'plate', 'tvstand', 'foundation', 'dish_soap', 'tooth_paste', 'wall', 'cup', 'coffe_maker', 'food_food', 'food_onion', 'centerpiece', 'cards', 'kettle', 'kitchen_counter', 'vacuum_cleaner', 'cupboard', 'door', 'sink', 'light', 'dishwasher', 'board_game', 'clothes_shirt', 'creditcard'] Task:Wash dishes with dishwasher response: { thoughts : Wash a plate using the dishwasher in the kitchen., actions : ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[PUTBACK] <dish_soap> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>'] } Scene_Objects:['sponge', 'fork', 'pot', 'chair', 'detergent', 'floor', 'ceiling', 'dvd_player', 'toaster', 'mat', 'faucet', 'dish_soap', 'food_peanut_butter', 'form', 'bowl', 'dining_room', 'wall', 'nightstand', 'cup', 'bed', 'coffe_maker', 'mouthwash', 'check', 'pencil', 'kitchen_counter', 'dishrack', 'cupboard', 'controller', 'sink', 'clothes_shirt'] Task:Wash dishes response: | { Fill sink with warm, sudsy water. Place dirty dishes in soapy water. With a washcloth or sponge scrub dishes clean. Rinse under clean warm water. Place in dish rack to dry. } |
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', 'walllamp', 'ceilingfan', 'orchid', 'hanger', 'longboard', 'floor', 'ceiling', 'character', 'bedroom', 'folder', 'bookshelf', 'toaster', 'ceilinglamp', 'plate', 'dish_soap', 'candle', 'wall', 'oven', 'bench', 'box', 'cup', 'clothes_gloves', 'coffe_maker', 'tray', 'console', 'maindoor', 'door', 'napkin', 'dishwasher'] Task:Wash dishes with dishwasher response: { thoughts : I go to the kitchen and open the dishwasher. I fill it up with dirty dishes and glasses. Then I put dish soap in the dishwasher, close it and turn it on., actions : ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <cup>', '[GRAB] <cup>', '[PUTBACK] <cup> <dishwasher>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[PUTBACK] <dish_soap> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>'] } Scene_Objects:['sheets', 'filing_cabinet', 'juice', 'measuring_cup', 'walllamp', 'detergent', 'drawing', 'wallshelf', 'cpuscreen', 'floor', 'ceiling', 'character', 'bedroom', 'purse', 'computer', 'mat', 'tvstand', 'shower', 'ceilinglamp', 'couch', 'pillow', 'dining_room', 'wall', 'cup', 'photoframe', 'television', 'doorjamb', 'shaving_cream', 'mouse', 'home_office'] Task:Arrange furniture response: | { Move furniture where you want it. } |
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:['dog', 'freezer', 'bathroom', 'food_carrot', 'knifeblock', 'food_egg', 'hanger', 'floor', 'phone', 'stovefan', 'mat', 'plate', 'stereo', 'dish_soap', 'food_noodles', 'closetdrawer', 'mousepad', 'dustpan', 'cup', 'food_food', 'coffe_maker', 'check', 'oven_mitts', 'water', 'food_rice', 'curtain', 'mouse', 'hairbrush', 'sink', 'home_office'] Task:Wash dishes by hand response: { thoughts : walk to kitchen, fins soap, arrange dishes, wash dishes, actions : ['[WALK] <dining_room>', '[WALK] <plate>', '[FIND] <plate>', '[FIND] <dish_soap>', '[FIND] <water>', '[GRAB] <plate>', '[GRAB] <dish_soap>', '[WASH] <plate>', '[RINSE] <plate>', '[DROP] <plate>'] } Scene_Objects:['glue', 'sheets', 'filing_cabinet', 'food_bread', 'food_salt', 'microwave', 'chair', 'orchid', 'drawing', 'bathroom_counter', 'floor', 'mail', 'stovefan', 'ceilinglamp', 'mat', 'stereo', 'couch', 'wall', 'powersocket', 'cup', 'check', 'mouthwash', 'food_donut', 'tray', 'kitchen_counter', 'cd', 'cupboard', 'controller', 'table', 'teeth'] Task:Play games response: | { I either bring out monopoly, uno, chess, checkers or playing cards and lay them out on the dining room table. We then play the games for a couple of hours. } |
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', 'blender', 'chair', 'walllamp', 'blow_dryer', 'detergent', 'orchid', 'knife', 'hanger', 'floor', 'ceiling', 'thread', 'ceilinglamp', 'laptop', 'faucet', 'mousepad', 'couch', 'candle', 'food_jam', 'pillow', 'wall', 'nightstand', 'tape', 'television', 'tray', 'after_shave', 'food_onion', 'shoes', 'cupboard'] 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:['milk', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'character', 'bedroom', 'desk', 'brush', 'mat', 'ceilinglamp', 'closetdrawer', 'couch', 'dustpan', 'pillow', 'wall', 'powersocket', 'cup', 'photoframe', 'coffee_filter', 'food_rice', 'doorjamb', 'towel_rack', 'dresser', 'clothes_dress', 'door', 'light', 'table'] Task:Change clothes response: | { Switch your clothes. } |
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', 'wallshelf', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'laptop', 'mat', 'tvstand', 'mousepad', 'closetdrawer', 'couch', 'pillow', 'dining_room', 'wall', 'oven', 'cup', 'photoframe', 'television', 'doorjamb', 'mouse', 'door', 'creditcard'] Task:Play on laptop response: { thoughts : Sit down on the couch. Place laptop on lap. Open laptop. Turn on laptop. Choose selected program. Play selected program. Close game. Close laptop., actions : ['[WALK] <home_office>', '[WALK] <laptop>', '[FIND] <laptop>', '[GRAB] <laptop>', '[FIND] <couch>', '[SIT] <couch>', '[SWITCHON] <laptop>', '[FIND] <keyboard>', '[TYPE] <keyboard>', '[SWITCHOFF] <laptop>', '[PUTOBJBACK] <laptop>'] } Scene_Objects:['dry_pasta', 'pot', 'tablelamp', 'juice', 'microwave', 'freezer', 'dough', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'stovefan', 'mat', 'shower', 'couch', 'pillow', 'wall', 'pasta', 'oven', 'powersocket', 'food_vegetable', 'food_food', 'television', 'ice', 'tray', 'doorjamb', 'towel_rack', 'kitchen_counter', 'cupboard', 'door', 'light'] Task:Cook some food response: | { I prepare meals and cook them on the stove. } |
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', 'walllamp', 'trashcan', 'drawing', 'floor', 'ceiling', 'button', 'toaster', 'window', 'mousepad', 'clothes_pants', 'wall', 'basket_for_clothes', 'coffe_maker', 'check', 'television', 'toothbrush_holder', 'ice', 'diary', 'mouse', 'kitchen_counter', 'vacuum_cleaner', 'cupboard', 'pajamas', 'napkin', 'coffee_cup', 'dishwasher', 'soap', 'coffee'] Task:Make coffee response: { thoughts : Walk to the kitchen at the coffee maker, grab coffee, pour coffee into coffee maker, put coffee into coffee maker, push coffee maker's button, wait to complete, grab coffee cup, actions : ['[WALK] <dining_room>', '[WALK] <coffe_maker>', '[FIND] <coffee>', '[GRAB] <coffee>', '[OPEN] <coffe_maker>', '[POUR] <coffee> <coffe_maker>', '[FIND] <coffee_cup>', '[GRAB] <coffee_cup>', '[PUTBACK] <coffee_cup> <coffe_maker>', '[FIND] <button>', '[PUSH] <button>', '[GRAB] <coffee_cup>'] } Scene_Objects:['chair', 'walllamp', 'drawing', 'wallshelf', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'remote_control', 'computer', 'clothes_jacket', 'mat', 'tvstand', 'ceilinglamp', 'closetdrawer', 'couch', 'pillow', 'wall', 'photoframe', 'television', 'tray', 'food_onion', 'doorjamb', 'shoes', 'dresser', 'sink', 'table', 'tooth_paste'] Task:Change TV channel response: | { I go to the living room, I settle on the sofa, I turn on the television, change the channel } |
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:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'door', 'light'] Task:Work response: | { Using desktop computer in home office } |
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', 'ceilingfan', 'drawing', 'cpuscreen', 'floor', 'purse', 'stovefan', 'ceilinglamp', 'stereo', 'faucet', 'window', 'balanceball', 'electric_shaver', 'couch', 'wall', 'bench', 'food_food', 'television', 'curtain', 'diary', 'mouse', 'dresser', 'hair', 'bathroom_cabinet', 'table', 'home_office', 'vase', 'teeth', 'shoe_rack'] Task:Relax on sofa response: { thoughts : Walk into the living room. Walk to the sofa and sit on it. Put your feet up on the sofa and lay down., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[SIT] <couch>', '[LIE] <couch>'] } Scene_Objects:['filing_cabinet', 'tablelamp', 'microwave', 'walllamp', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'bookshelf', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'clothes_socks', 'couch', 'pillow', 'wall', 'powersocket', 'box', 'cup', 'photoframe', 'television', 'food_rice', 'doorjamb', 'towel_rack', 'kitchen_counter', 'door', 'home_office', 'soap'] Task:Relax on sofa response: | { I walk to the living room and stand in front of the sofa. Then I turn and sit on the sofa and lean my back against the pillow and my feet on the floor. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['food_pizza', 'tablelamp', 'toilet', 'chair', 'walllamp', 'trashcan', 'ceilingfan', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'balanceball', 'faucet', 'mousepad', 'wall', 'nightstand', 'cup', 'coffe_maker', 'doorjamb', 'mouse', 'chessboard', 'controller', 'bathroom_cabinet', 'light'] Task:Write an email response: { thoughts : enter office, find computer, turn it on,, actions : ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <keyboard>', '[TOUCH] <keyboard>', '[TYPE] <keyboard>'] } Scene_Objects:['pot', 'mop', 'toilet', 'freezer', 'walllamp', 'bathroom', 'cat', 'food_butter', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'computer', 'mat', 'tvstand', 'iron', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'toy', 'tape', 'photoframe', 'television', 'food_rice', 'doorjamb', 'cards', 'door'] Task:Relax on sofa response: | { walk into living room, look at the sofa which one is available, sit on the sofa, now take relax on the sofa } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['glue', 'tablelamp', 'chair', 'walllamp', 'bathroom', 'trashcan', 'ceilingfan', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'computer', 'laptop', 'balanceball', 'mousepad', 'pillow', 'wall', 'cup', 'bed', 'television', 'razor', 'doorjamb', 'kitchen_counter', 'dresser', 'cupboard', 'door', 'spoon', 'light', 'vase'] Task:Turn on light response: { thoughts : push any ligth button to turn it on, for example in the living room, actions : ['[WALK] <home_office>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>'] } Scene_Objects:['spectacles', 'pot', 'tablelamp', 'chair', 'drawing', 'cpuscreen', 'floor', 'phone', 'desk', 'keyboard', 'computer', 'mat', 'mousepad', 'couch', 'form', 'wall', 'oven', 'powersocket', 'tape', 'cup', 'check', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'vacuum_cleaner', 'shoes', 'door', 'light'] Task:Pick up phone response: | { I go to my home office. I walk towards my desk. I see the phone. I pick it up. } |
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', 'tablelamp', 'toilet', 'chair', 'walllamp', 'floor', 'ceiling', 'phone', 'keyboard', 'envelope', 'toaster', 'ceilinglamp', 'stereo', 'faucet', 'window', 'couch', 'pillow', 'wall', 'nightstand', 'powersocket', 'cup', 'clothes_gloves', 'novel', 'check', 'video_game_controller', 'television', 'kitchen_counter', 'hairdryer', 'light', 'table'] Task:Relax on sofa response: { thoughts : Walk to the living room. Walk to the sofa and sit on the sofa., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[SIT] <couch>'] } Scene_Objects:['pot', 'food_bread', 'tablelamp', 'microwave', 'freezer', 'food_butter', 'drawing', 'wallshelf', 'cpuscreen', 'hanger', 'kitchen_cabinet', 'floor', 'ceiling', 'food_chicken', 'desk', 'keyboard', 'stovefan', 'mat', 'tvstand', 'shower', 'closetdrawer', 'couch', 'pillow', 'wall', 'nightstand', 'powersocket', 'oven', 'food_cheese', 'photoframe', 'food_food', 'television', 'wine', 'tray', 'doorjamb', 'towel_rack', 'kitchen_counter', 'dresser', 'cupboard', 'door', 'light', 'dishwasher'] Task:Cook some food response: | { I walk into the kitchen and walk over the cabinent. I pull out a pan and walk to the stove. I put the pan on the stove and walk over to the fridge. I pull out out meat from the fridge and walk back over the stove. Then I put the meat in the pan. } |
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', 'sheets', 'chair', 'ground_coffee', 'walllamp', 'hanger', 'longboard', 'floor', 'ceiling', 'phone', 'bookshelf', 'keyboard', 'computer', 'stovefan', 'tvstand', 'stereo', 'window', 'clothes_hat', 'wall', 'nightstand', 'bench', 'box', 'food_cheese', 'doorjamb', 'mouse', 'dresser', 'cupboard', 'hair', 'door', 'light'] Task:Turn on light response: { thoughts : Walk to living room. Find light switch. Switch on light switch., actions : ['[WALK] <home_office>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>'] } Scene_Objects:['sheets', 'walllamp', 'drawing', 'needle', 'wallshelf', 'floor', 'ceiling', 'shampoo', 'character', 'computer', 'toaster', 'mat', 'tvstand', 'deck_of_cards', 'stovefan', 'ceilinglamp', 'couch', 'pillow', 'wall', 'nightstand', 'photoframe', 'coffe_maker', 'television', 'tray', 'doorjamb', 'pencil', 'conditioner', 'door', 'table', 'dishwasher'] Task:Relax on sofa response: | { Walk to living room. Find couch. Sit on 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:['toilet', 'walllamp', 'bathroom', 'drawing', 'cpuscreen', 'floor', 'dvd_player', 'desk', 'bedroom', 'bookshelf', 'computer', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'window', 'closetdrawer', 'couch', 'pillow', 'wall', 'nightstand', 'television', 'tray', 'curtain', 'controller', 'sink', 'bathroom_cabinet', 'table', 'home_office', 'light'] Task:Listen to music response: { thoughts : walk to living room, look at the DVD player, switch on the dvd player, look at the sofa, sit on the sofa and listen the music, actions : ['[WALK] <home_office>', '[WALK] <dvd_player>', '[FIND] <dvd_player>', '[TURNTO] <dvd_player>', '[LOOKAT] <dvd_player>', '[SWITCHON] <dvd_player>', '[FIND] <couch>', '[TURNTO] <couch>', '[LOOKAT] <couch>', '[SIT] <couch>'] } Scene_Objects:['tablelamp', 'chair', 'walllamp', 'orchid', 'drawing', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'laptop', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'television', 'doorjamb', 'mouse', 'dresser', 'door', 'soap'] Task:Work response: | { Sit in front of the computer, switch on the computer and start typing (Work) } |
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', 'pot', 'ceilingfan', 'toothbrush', 'knifeblock', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'piano_bench', 'toaster', 'faucet', 'window', 'mousepad', 'clothes_pants', 'wall', 'nightstand', 'pasta', 'photoframe', 'toothbrush_holder', 'shoes', 'dresser', 'clothes_dress', 'door', 'sink', 'bathroom_cabinet', 'clothes_skirt', 'tooth_paste', 'laser_pointer'] Task:Brush teeth response: { thoughts : go to bathroom. grab toothbrush. put toothpaste on toothbrush. brush teeth. turn on faucet. rinse toothbrush and mouth. put toothbrush away., actions : ['[WALK] <bathroom>', '[WALK] <sink>', '[FIND] <toothbrush_holder>', '[TURNTO] <toothbrush_holder>', '[LOOKAT] <toothbrush_holder>', '[FIND] <tooth_paste>', '[GRAB] <tooth_paste>', '[FIND] <toothbrush>', '[GRAB] <toothbrush>', '[PUTBACK] <tooth_paste> <toothbrush_holder>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[RINSE] <toothbrush>', '[PUTBACK] <toothbrush> <toothbrush_holder>'] } Scene_Objects:['measuring_cup', 'chair', 'walllamp', 'food_butter', 'drawing', 'wallshelf', 'floor', 'ceiling', 'character', 'computer', 'mat', 'tvstand', 'couch', 'pillow', 'dining_room', 'wall', 'nightstand', 'oven', 'photoframe', 'bed', 'coffe_maker', 'television', 'food_donut', 'tray', 'curtain', 'doorjamb', 'pencil', 'dresser', 'napkin', 'dirt'] Task:Relax on sofa response: | { move to living room, locate sofa, move to sofa, sit on sofa, lie on sofa } |
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', 'mop', 'cd_player', 'chair', 'knifeblock', 'music_stand', 'floor', 'ceiling', 'character', 'bedroom', 'desk', 'envelope', 'food_bacon', 'mop_bucket', 'stovefan', 'ceilinglamp', 'shower', 'nightstand', 'bed', 'photoframe', 'coffe_maker', 'tray', 'curtain', 'lighter', 'kitchen_counter', 'comb', 'dresser', 'cupboard', 'bathroom_cabinet', 'light'] Task:Listen to music response: { thoughts : Walk to the living and turn to the music stand. Switch on the CD player to listen to music., actions : ['[WALK] <home_office>', '[WALK] <music_stand>', '[FIND] <music_stand>', '[TURNTO] <music_stand>', '[FIND] <cd_player>', '[SWITCHON] <cd_player>'] } Scene_Objects:['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: | { Open coffee maker. Put filter in main basket, put ground coffee in filter, fill reservoir with water, turn on coffee 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:['filing_cabinet', 'juice', 'walllamp', 'bathroom', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'oven', 'cup', 'photoframe', 'coffee_table', 'television', 'curtain', 'doorjamb', 'door', 'table', 'light'] Task:Watch TV response: { thoughts : Sit down, turn on the TV with the remote control that is on the coffee table., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <coffee_table>', '[TURNTO] <coffee_table>', '[LOOKAT] <coffee_table>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[TURNTO] <television>', '[LOOKAT] <television>', '[TURNTO] <television>', '[POINTAT] <television>', '[SWITCHON] <television>'] } Scene_Objects:['chair', 'jelly', 'walllamp', 'drawing', 'knife', 'wallshelf', 'orchid', 'hanger', 'floor', 'ceiling', 'phone', 'character', 'desk', 'remote_control', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'closetdrawer', 'couch', 'candle', 'pillow', 'wall', 'photoframe', 'television', 'tray', 'doorjamb', 'towel_rack', 'dresser', 'sink'] Task:Watch TV response: | { Walk to Living room. Find Television. Walk to sofa. Sit on sofa. Find Remote. Grab remote. Turn to television. Look at television. Switch on 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:['food_bread', 'toilet', 'walllamp', 'bills', 'drawing', 'cpuscreen', 'bathroom_counter', 'ceiling', 'cleaning_solution', 'mop_bucket', 'table_cloth', 'faucet', 'shower', 'iron', 'clothes_socks', 'pillow', 'wall', 'food_food', 'mirror', 'wine', 'doorjamb', 'coffee_pot', 'paper_towel', 'cupboard', 'conditioner', 'door', 'sink', 'bathroom_cabinet', 'dishwasher', 'scrabble'] Task:Clean mirror response: { thoughts : First spray the mirrors with Windex or window type spray. Take paper towels and wipe until sparkly clean. If they have streaks, repeat the process., actions : ['[WALK] <bathroom>', '[WALK] <bathroom_cabinet>', '[OPEN] <bathroom_cabinet>', '[FIND] <paper_towel>', '[GRAB] <paper_towel>', '[CLOSE] <bathroom_cabinet>', '[WALK] <mirror>', '[FIND] <cleaning_solution>', '[RINSE] <cleaning_solution>', '[WIPE] <mirror>'] } Scene_Objects:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'picture', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'tape', 'check', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'pencil', 'comb', 'dresser', 'door', 'light'] Task:Work response: | { Walk to home office, walk to desk, sit in chair, turn on computer, look at computer, click mouse and type on keyboard. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'spectacles', 'glue', 'jelly', 'freezer', 'detergent', 'food_carrot', 'orchid', 'clothes_underwear', 'hanger', 'floor', 'bedroom', 'thread', 'bookmark', 'mat', 'stereo', 'shower', 'mousepad', 'oil', 'nightstand', 'light_bulb', 'coffe_maker', 'television', 'tray', 'pencil', 'shoes', 'bathroom_cabinet', 'dishwasher', 'colander', 'dirt'] Task:Pick up phone response: { thoughts : Go to the living room. Find the telephone. Lift up the receiver., actions : ['[WALK] <home_office>', '[WALK] <phone>', '[FIND] <phone>', '[GRAB] <phone>'] } Scene_Objects:['tablelamp', 'chair', 'ground_coffee', 'drawing', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'table_cloth', 'piano_bench', 'mat', 'ceilinglamp', 'tvstand', 'laptop', 'stereo', 'deck_of_cards', 'mousepad', 'dining_room', 'wall', 'nightstand', 'powersocket', 'television', 'food_rice', 'mouse', 'door', 'table', 'laser_pointer'] Task:Work response: | { Go to the office and sit on the chair, then work on the 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', 'tablelamp', 'microwave', 'ground_coffee', 'food_carrot', 'drawing', 'knifeblock', 'cpuscreen', 'hanger', 'floor', 'toaster', 'plate', 'faucet', 'foundation', 'mousepad', 'food_jam', 'food_kiwi', 'wall', 'pasta', 'powersocket', 'food_food', 'coffe_maker', 'rag', 'shaving_cream', 'kitchen_counter', 'dishrack', 'dresser', 'cupboard', 'sink', 'dishwasher'] Task:Wash dishes with dishwasher response: { thoughts : Take a dish and put it in the dishwasher to be washed, actions : ['[WALK] <dining_room>', '[WALK] <sink>', '[FIND] <plate>', '[GRAB] <plate>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>'] } Scene_Objects:['tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'wallshelf', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'mousepad', 'closetdrawer', 'couch', 'pillow', 'wall', 'nightstand', 'photoframe', 'television', 'oven_mitts', 'tray', 'doorjamb', 'mouse', 'dresser', 'door'] Task:Watch TV response: | { Go to entrance hall, switch on TV, sit back in a chair and using remote watch your favorite program. } |
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', 'band-aids', 'drawing', 'orchid', 'kitchen_cabinet', 'floor', 'bathroom_counter', 'phone', 'bookshelf', 'computer', 'stovefan', 'mat', 'plate', 'ceilinglamp', 'tvstand', 'window', 'couch', 'food_peanut_butter', 'pillow', 'wall', 'nightstand', 'bench', 'powersocket', 'oven', 'cutting_board', 'curtain', 'mouse', 'table', 'dishwasher', 'light'] Task:Set up table response: { thoughts : Walk to the kitchen. Open the kitchen cabinet. Grab the plate and put it on the table., actions : ['[WALK] <dining_room>', '[WALK] <kitchen_cabinet>', '[FIND] <kitchen_cabinet>', '[OPEN] <kitchen_cabinet>', '[FIND] <plate>', '[GRAB] <plate>', '[FIND] <table>', '[PUTBACK] <plate> <table>'] } Scene_Objects:['juice', 'walllamp', 'nail_polish', 'detergent', 'dough', 'drawing', 'food_egg', 'tea_bag', 'bookshelf', 'remote_control', 'alcohol', 'button', 'mop_bucket', 'table_cloth', 'stovefan', 'tvstand', 'shoe-shine_kit', 'shower', 'stereo', 'deck_of_cards', 'mousepad', 'powersocket', 'check', 'rag', 'towel_rack', 'pencil', 'conditioner', 'door', 'bathroom_cabinet', 'soap'] Task:Change TV channel response: | { Take the Tv Remote Control in the Living Room table And Press the Channel Change Button to change the channel } |
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', 'filing_cabinet', 'walllamp', 'drawing', 'floor', 'desk', 'tea_bag', 'computer', 'clothes_jacket', 'toaster', 'mat', 'mousepad', 'closetdrawer', 'towel', 'tape', 'basket_for_clothes', 'bed', 'curtain', 'shaving_cream', 'towel_rack', 'mouse', 'kitchen_counter', 'chessboard', 'dresser', 'hair', 'laundry_detergent', 'bathroom_cabinet', 'light', 'board_game', 'dirt'] Task:Open front door response: { thoughts : Walk over to the front door, turn the knob, and open the door., actions : ['[WALK] <home_office>'] } Scene_Objects:['scissors', 'chair', 'walllamp', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'character', 'desk', 'bookshelf', 'remote_control', 'computer', 'button', 'mat', 'tvstand', 'ceilinglamp', 'food_noodles', 'closetdrawer', 'couch', 'pillow', 'wall', 'photoframe', 'television', 'doorjamb', 'kitchen_counter', 'headset', 'dresser', 'food_steak', 'sink'] Task:Change TV channel response: | { change the tv channel } |
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', 'chair', 'blow_dryer', 'bathroom_counter', 'floor', 'ceiling', 'bedroom', 'toaster', 'laptop', 'deck_of_cards', 'faucet', 'food_noodles', 'closetdrawer', 'food_orange', 'wall', 'nightstand', 'clothes_gloves', 'coffe_maker', 'toilet_paper', 'food_food', 'curtain', 'towel_rack', 'console', 'kitchen_counter', 'shoes', 'cupboard', 'sink', 'spoon', 'dishwasher'] Task:Make coffee response: { thoughts : Making coffee, actions : ['[WALK] <dining_room>', '[WALK] <coffe_maker>', '[FIND] <coffe_maker>', '[SWITCHON] <coffe_maker>'] } Scene_Objects:['glue', 'food_pizza', 'toilet', 'chair', 'bathroom_counter', 'floor', 'ceiling', 'cleaning_solution', 'food_bacon', 'mop_bucket', 'toaster', 'stovefan', 'faucet', 'shower', 'mousepad', 'dustpan', 'pillow', 'wall', 'nightstand', 'powersocket', 'coffe_maker', 'console', 'towel_rack', 'kitchen_counter', 'chessboard', 'cupboard', 'pajamas', 'sink', 'napkin', 'hands_both'] Task:Wash hands response: | { Washing hands } |
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', 'tablelamp', 'scissors', 'freezer', 'ceilingfan', 'knifeblock', 'knife', 'hanger', 'phone', 'desk', 'clothes_jacket', 'toaster', 'ceilinglamp', 'electric_shaver', 'window', 'mousepad', 'couch', 'candle', 'cutting_board', 'food_cheese', 'food_rice', 'food_onion', 'pencil', 'cd', 'comb', 'door', 'maindoor', 'napkin', 'soap'] Task:Pet cat response: { thoughts : You walk to the living room and find the cat. You look at the cat and touch it to pet it., actions : ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[TURNTO] <cat>', '[LOOKAT] <cat>', '[TOUCH] <cat>'] } Scene_Objects:['filing_cabinet', 'microwave', 'toilet', 'bathroom', 'cat', 'drawing', 'cpuscreen', 'hanger', 'bathroom_counter', 'bedroom', 'food_bacon', 'piano_bench', 'bookmark', 'stovefan', 'ceilinglamp', 'laptop', 'shower', 'stereo', 'mat', 'couch', 'nightstand', 'wall', 'photoframe', 'coffee_filter', 'towel_rack', 'dishrack', 'controller', 'table', 'clothes_skirt', 'soap'] Task:Pick up phone response: | { walk into room, 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:['sponge', 'scissors', 'microwave', 'bathroom', 'drawing', 'knifeblock', 'floor', 'bedroom', 'desk', 'toaster', 'mat', 'plate', 'faucet', 'shower', 'closetdrawer', 'wall', 'powersocket', 'newspaper', 'photoframe', 'bed', 'check', 'food_rice', 'ice', 'curtain', 'mouse', 'kitchen_counter', 'cupboard', 'sink', 'instrument_guitar', 'board_game'] Task:Wash dishes by hand response: { thoughts : go into the kitchen, walk to the sink. Turn on the water and rinse of a plate and clean them off fully with a sponge., actions : ['[WALK] <dining_room>', '[WALK] <sink>', '[FIND] <plate>', '[RINSE] <plate>', '[FIND] <sponge>', '[GRAB] <sponge>', '[WASH] <plate>'] } Scene_Objects:['pot', 'food_ice_cream', 'food_salt', 'measuring_cup', 'mop', 'chair', 'walllamp', 'cat', 'wallshelf', 'cpuscreen', 'floor', 'ceiling', 'bookshelf', 'computer', 'mat', 'clothes_pants', 'oven', 'check', 'toilet_paper', 'oven_mitts', 'food_donut', 'after_shave', 'lighter', 'cards', 'headset', 'instrument_violin', 'instrument_guitar', 'light', 'board_game', 'teeth'] Task:Pet cat response: | { I go to the living room then go to the cat and touch it. } |
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', 'chair', 'walllamp', 'food_butter', 'orchid', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'bookshelf', 'computer', 'mat', 'shower', 'picture', 'mousepad', 'pillow', 'wall', 'oven', 'powersocket', 'bed', 'photoframe', 'food_donut', 'tray', 'mouse', 'pencil', 'bag', 'soap'] Task:Read book response: { thoughts : go to living room,find the text book on the self ,sat on the chair ,open and read the book, actions : ['[WALK] <home_office>', '[WALK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[WALK] <home_office>', '[WALK] <chair>', '[FIND] <chair>', '[SIT] <chair>', '[READ] <novel>'] } Scene_Objects:['pot', 'freezer', 'drawing', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'mat', 'ceilinglamp', 'shower', 'clothes_socks', 'mousepad', 'couch', 'food_peanut_butter', 'pillow', 'wall', 'oven', 'food_food', 'television', 'tray', 'wooden_spoon', 'food_onion', 'pencil', 'kitchen_counter', 'vacuum_cleaner', 'cupboard', 'hairdryer', 'door', 'dishwasher', 'clothes_skirt'] Task:Put groceries in Fridge response: | { Open the fridge, put the groceries in the fridge and close it. } |
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', 'freezer', 'bathroom', 'cpuscreen', 'wallshelf', 'floor', 'phone', 'ceiling', 'character', 'desk', 'keyboard', 'computer', 'mat', 'tvstand', 'mousepad', 'dining_room', 'wall', 'light_bulb', 'check', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'pencil', 'kitchen_counter', 'clothes_dress', 'door', 'table', 'clothes_shirt'] Task:Pick up phone response: { thoughts : Walk to living room. Go near telephone. take the receiver and then talk to other person on that side., actions : ['[WALK] <phone>', '[GRAB] <phone>'] } Scene_Objects:['scissors', 'chair', 'freezer', 'band-aids', 'walllamp', 'nail_polish', 'orchid', 'drawing', 'cpuscreen', 'kitchen_cabinet', 'floor', 'keyboard', 'toaster', 'ceilinglamp', 'plate', 'stereo', 'mat', 'iron', 'food_peanut_butter', 'food_jam', 'wall', 'oven', 'check', 'food_food', 'food_rice', 'ice', 'food_onion', 'console', 'kitchen_counter', 'table'] Task:Set up table response: | { Walk to the kitchen. Open the kitchen cabinet. Grab the plate and put it on the table. } |
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', 'beer', 'toilet', 'dough', 'toothbrush', 'drawing', 'floor', 'ceiling', 'computer', 'ceilinglamp', 'tvstand', 'stereo', 'shower', 'window', 'oil', 'couch', 'bowl', 'wall', 'oven', 'toy', 'cup', 'bed', 'food_food', 'television', 'wooden_spoon', 'towel_rack', 'comb', 'cupboard', 'table', 'dishwasher'] Task:Relax on sofa response: { thoughts : Walk to living room. Find couch. Sit on couch, actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>'] } Scene_Objects:['sponge', 'band-aids', 'detergent', 'food_carrot', 'milk', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'button', 'piano_bench', 'toaster', 'plate', 'faucet', 'drying_rack', 'shower', 'dish_soap', 'closetdrawer', 'clothes_pants', 'wall', 'oven', 'food_cheese', 'newspaper', 'food_food', 'doorjamb', 'kitchen_counter', 'cupboard', 'door', 'sink', 'shoe_rack'] Task:Wash dishes by hand response: | { I walk in to the Kitchen. I find a plate, a sponge, and the dish soap. I find the faucet. I turn the faucet on. I pour water on the sponge and plate. I add dish soap to the sponge. I put the dish soap back. I scrub the plate. I rinse the plate. I place the plate on the drying rack. I rinse the sponge. I turn the faucet off. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['fork', 'filing_cabinet', 'scissors', 'juice', 'food_salt', 'microwave', 'chair', 'food_butter', 'toothbrush', 'drawing', 'wallshelf', 'bathroom_counter', 'floor', 'button', 'brush', 'ceilinglamp', 'plate', 'wall', 'tape', 'food_food', 'check', 'food_donut', 'wooden_spoon', 'rag', 'door', 'clothes_scarf', 'napkin', 'table', 'light', 'dishwasher'] Task:Eat response: { thoughts : Serve food on dinning table in appropriate utensils, sit on the chair, eat, actions : ['[WALK] <dining_room>', '[WALK] <table>', '[FIND] <table>', '[TURNTO] <table>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <food_food>', '[GRAB] <food_food>', '[FIND] <plate>', '[PUTBACK] <food_food> <plate>', '[GRAB] <food_food>', '[PUTOBJBACK] <food_food>', '[FIND] <fork>', '[GRAB] <fork>', '[EAT] <plate>'] } Scene_Objects:['tablelamp', 'chair', 'walllamp', 'ground_coffee', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'photoframe', 'television', 'doorjamb', 'mouse', 'dresser', 'door'] Task:Browse internet response: | { Sit down at desk in home office, turn on computer, open browser on computer, browse internet } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['walllamp', 'drawing', 'orchid', 'wallshelf', 'knifeblock', 'knife', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'photoframe', 'light_bulb', 'television', 'curtain', 'doorjamb', 'cd', 'pajamas', 'door', 'table', 'light', 'dishwasher'] Task:Watch TV response: { thoughts : Sitting on the couch watching my favorite television show., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <television>', '[TURNTO] <television>', '[WATCH] <television>'] } Scene_Objects:['sheets', 'beer', 'freezer', 'walllamp', 'food_carrot', 'drawing', 'hanger', 'floor', 'ceiling', 'keyboard', 'toaster', 'mat', 'tvstand', 'couch', 'food_orange', 'pillow', 'wall', 'basket_for_clothes', 'food_cheese', 'food_food', 'television', 'after_shave', 'towel_rack', 'pencil', 'kitchen_counter', 'cupboard', 'controller', 'bathroom_cabinet', 'table', 'dirt'] Task:Put groceries in Fridge response: | { I leave the bags with groceries near the fridge, open the door and put the groceries in the shelves. } |
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', 'chair', 'walllamp', 'orchid', 'cpuscreen', 'clothes_underwear', 'floor', 'ceiling', 'desk', 'keyboard', 'bookshelf', 'computer', 'mail', 'stovefan', 'ceilinglamp', 'mat', 'mousepad', 'dustpan', 'wall', 'bed', 'coffe_maker', 'lighter', 'coffee_pot', 'mouse', 'hair', 'door', 'napkin', 'home_office', 'table'] Task:Browse internet response: { thoughts : Go find a computer, turn it on, click google, and browse the internet., actions : ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>'] } Scene_Objects:['water_glass', 'scissors', 'blender', 'chair', 'walllamp', 'drawing', 'wallshelf', 'clothes_underwear', 'floor', 'ceiling', 'character', 'desk', 'computer', 'food_bacon', 'mat', 'tvstand', 'mousepad', 'closetdrawer', 'couch', 'pillow', 'wall', 'cup', 'photoframe', 'newspaper', 'television', 'ice', 'doorjamb', 'diary', 'console', 'towel_rack'] Task:Relax on sofa response: | { Drink a glass of water in the sofa } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['fork', 'pot', 'filing_cabinet', 'tablelamp', 'microwave', 'chair', 'bathroom', 'drawing', 'cpuscreen', 'floor', 'phone', 'desk', 'bedroom', 'ceilinglamp', 'shoe-shine_kit', 'faucet', 'clothes_pants', 'dining_room', 'wall', 'tape', 'basket_for_clothes', 'bed', 'coffe_maker', 'chessboard', 'clothes_dress', 'door', 'home_office', 'light', 'soap', 'washing_machine'] Task:Wash clothes response: { thoughts : Walk to Bathroom. Find basket for clothes. Lift clothes dress from basket. Find washing machine. Walk to washing machine. Put clothes in washing machine. Put soap in washing machine. Switch on washing machine., actions : ['[WALK] <bathroom>', '[WALK] <basket_for_clothes>', '[FIND] <basket_for_clothes>', '[FIND] <clothes_dress>', '[GRAB] <clothes_dress>', '[FIND] <washing_machine>', '[WALK] <washing_machine>', '[OPEN] <washing_machine>', '[PUTBACK] <clothes_dress> <washing_machine>', '[FIND] <soap>', '[GRAB] <soap>', '[PUTBACK] <soap> <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>'] } Scene_Objects:['fork', 'tablelamp', 'toilet', 'chair', 'band-aids', 'orchid', 'drawing', 'kitchen_cabinet', 'floor', 'table_cloth', 'ceilinglamp', 'plate', 'mat', 'tvstand', 'electric_shaver', 'candle', 'microphone', 'wall', 'cup', 'photoframe', 'food_food', 'food_rice', 'tray', 'food_onion', 'kitchen_counter', 'chessboard', 'cupboard', 'home_office', 'table', 'laser_pointer'] Task:Set up table response: | { Walk into kitchen. Grab plates and forks. Walk into dining room. Put plates and forks on table. } |
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', 'filing_cabinet', 'food_salt', 'chair', 'walllamp', 'drawing', 'cpuscreen', 'clothes_underwear', 'hanger', 'floor', 'ceiling', 'desk', 'bookshelf', 'keyboard', 'computer', 'mat', 'deck_of_cards', 'window', 'mousepad', 'closetdrawer', 'couch', 'pillow', 'wall', 'pasta', 'powersocket', 'toy', 'tape', 'light_bulb', 'check', 'food_food', 'television', 'curtain', 'doorjamb', 'mouse', 'pencil', 'dresser', 'conditioner', 'spoon', 'light', 'table', 'colander'] Task:Re arrange office response: { thoughts : Walk in.Turn on light.Move furniture. Change the room, actions : ['[WALK] <home_office>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>', '[WALK] <desk>', '[PUSH] <desk>', '[WALK] <chair>', '[PUSH] <chair>', '[WALK] <couch>', '[PUSH] <couch>', '[WALK] <filing_cabinet>', '[PUSH] <filing_cabinet>'] } Scene_Objects:['water_glass', 'pot', 'freezer', 'milk', 'cpuscreen', 'kitchen_cabinet', 'floor', 'ceiling', 'bookshelf', 'keyboard', 'alcohol', 'computer', 'toaster', 'shoe-shine_kit', 'faucet', 'pillow', 'dining_room', 'wall', 'cup', 'bed', 'check', 'toilet_paper', 'mouse', 'pencil', 'kitchen_counter', 'cupboard', 'clothes_dress', 'food_steak', 'sink', 'bathroom_cabinet'] Task:Drink response: | { I walk into the kitchen. I reach into the cabinet and pick up a water glass. Turn on the faucet and place the glass under the water stream. Bring the glass of water to lips and drink. } |
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', 'microwave', 'toilet', 'freezer', 'trashcan', 'drawing', 'floor', 'ceiling', 'computer', 'toaster', 'mat', 'stovefan', 'shower', 'faucet', 'couch', 'wall', 'nightstand', 'oven', 'photoframe', 'food_food', 'coffe_maker', 'tray', 'food_onion', 'curtain', 'doorjamb', 'kitchen_counter', 'cupboard', 'door', 'sink', 'electrical_outlet'] Task:Toast bread response: { thoughts : Place two slices of bread in the toaster. Select medium toast on toaster. Push down button to begin toasting., actions : ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <food_bread>', '[GRAB] <food_bread>', '[CLOSE] <freezer>', '[WALK] <electrical_outlet>', '[FIND] <toaster>', '[PLUGIN] <toaster>', '[PUTBACK] <food_bread> <toaster>', '[SWITCHON] <electrical_outlet>', '[TURNTO] <toaster>', '[LOOKAT] <toaster>', '[SWITCHON] <toaster>'] } Scene_Objects:['sheets', 'microwave', 'chair', 'walllamp', 'bathroom', 'detergent', 'bathroom_counter', 'button', 'toaster', 'brush', 'stereo', 'shower', 'faucet', 'food_orange', 'pillow', 'oven', 'photoframe', 'check', 'television', 'tray', 'kettle', 'mouse', 'cupboard', 'conditioner', 'door', 'home_office', 'table', 'dishwasher', 'clothes_skirt', 'soap'] Task:Listen to music response: | { Walk into living room, look for radio, grab on 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', '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>'] } Scene_Objects:['tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'television', 'wooden_spoon', 'doorjamb', 'mouse', 'dresser', 'door'] Task:Browse internet response: | { I go to my home office. I sit on the chair right in front of my computer. I turn on the computer. Use the mouse to open the web browser. Use the keyboard to type the URL that I want to visit. } |
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', 'food_butter', 'drawing', 'wallshelf', 'floor', 'ceiling', 'character', 'computer', 'mat', 'tvstand', 'couch', 'pillow', 'dining_room', 'wall', 'nightstand', 'oven', 'photoframe', 'bed', 'coffe_maker', 'television', 'food_donut', 'tray', 'curtain', 'doorjamb', 'pencil', 'dresser', 'napkin', 'dirt'] Task:Relax on sofa response: { thoughts : move to living room, locate sofa, move to sofa, sit on sofa, lie on sofa, actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[WALK] <couch>', '[SIT] <couch>', '[LIE] <couch>'] } Scene_Objects:['filing_cabinet', 'tablelamp', 'microwave', 'walllamp', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'desk', 'tea_bag', 'bookshelf', 'mat', 'deck_of_cards', 'clothes_socks', 'closetdrawer', 'couch', 'mousepad', 'wall', 'nightstand', 'powersocket', 'bed', 'television', 'curtain', 'doorjamb', 'coffee_pot', 'towel_rack', 'kitchen_counter', 'door', 'light'] Task:Turn on light response: | { Coming home turning on lights. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['walllamp', 'food_carrot', 'drawing', 'orchid', 'knifeblock', 'cpuscreen', 'floor', 'ceiling', 'bedroom', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'couch', 'microphone', 'pillow', 'wall', 'wall_clock', 'photoframe', 'television', 'toothbrush_holder', 'food_donut', 'doorjamb', 'shaving_cream', 'mouse', 'door', 'sink', 'clothes_scarf', 'napkin', 'table'] Task:Straighten pictures on wall response: { thoughts : Move the pictures/paintings until they are straight., actions : ['[WALK] <home_office>', '[WALK] <drawing>', '[FIND] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>', '[TOUCH] <drawing>', '[PUSH] <drawing>', '[FIND] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>', '[TOUCH] <drawing>', '[PUSH] <drawing>'] } Scene_Objects:['spectacles', 'filing_cabinet', 'juice', 'toilet', 'chair', 'nail_polish', 'needle', 'clothes_underwear', 'phone', 'keyboard', 'bookmark', 'stovefan', 'ceilinglamp', 'toaster', 'shower', 'foundation', 'clothes_hat', 'pillow', 'oven', 'powersocket', 'tape', 'bed', 'coffe_maker', 'television', 'curtain', 'towel_rack', 'mouse', 'cupboard', 'bathroom_cabinet', 'table'] Task:Listen to music response: | { Walk into the living room. Walk up to the radio. Turn on the radio. Listen to the radio. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sponge', 'pot', 'toilet', 'dog', 'freezer', 'walllamp', 'bathroom', 'food_carrot', 'drawing', 'hanger', 'phone', 'ceiling', 'desk', 'computer', 'toaster', 'mat', 'mousepad', 'closetdrawer', 'food_peanut_butter', 'towel', 'cup', 'food_cheese', 'keys', 'tray', 'after_shave', 'towel_rack', 'mouse', 'cupboard', 'sink', 'coffee'] Task:Pet cat response: { thoughts : I walk into the living room and I pet the cat, actions : ['[WALK] <home_office>', '[WALK] <cat>', '[TOUCH] <cat>'] } Scene_Objects:['food_pizza', 'walllamp', 'cat', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'desk', 'bookshelf', 'computer', 'mat', 'tvstand', 'couch', 'pillow', 'wall', 'powersocket', 'photoframe', 'bed', 'food_food', 'check', 'television', 'curtain', 'doorjamb', 'kitchen_counter', 'clothes_dress', 'door', 'conditioner', 'sink', 'light'] Task:Pet cat response: | { My cat looks like it wants attention, so I will go pet it on the 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', 'glue', 'pot', 'toilet', 'walllamp', 'drawing', 'wallshelf', 'floor', 'ceiling', 'keyboard', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'couch', 'pillow', 'dining_room', 'wall', 'cup', 'photoframe', 'food_food', 'television', 'doorjamb', 'kettle', 'shaving_cream', 'kitchen_counter', 'chessboard', 'dresser', 'controller', 'light'] Task:Relax on sofa response: { thoughts : I get home from work and walk into the living room. I see the couch and go to sit on it., actions : ['[WALK] <home_office>', '[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[TURNTO] <couch>', '[LOOKAT] <couch>', '[WALK] <couch>', '[SIT] <couch>', '[LIE] <couch>'] } Scene_Objects:['sheets', 'microwave', 'chair', 'bathroom', 'orchid', 'food_egg', 'cpuscreen', 'floor', 'phone', 'bedroom', 'desk', 'stovefan', 'toaster', 'ceilinglamp', 'shower', 'mat', 'food_peanut_butter', 'wall', 'pasta', 'powersocket', 'oven', 'cup', 'bed', 'after_shave', 'food_onion', 'chessboard', 'dresser', 'cupboard', 'clothes_scarf', 'home_office'] Task:Pet cat response: | { I walk to my living room, find my cat, scrub it using my hand. } |
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', 'dog', 'chair', 'bathroom', 'drawing', 'floor', 'ceiling', 'bedroom', 'bookshelf', 'purse', 'mat', 'ceilinglamp', 'shower', 'candle', 'wall', 'bed', 'clothes_gloves', 'food_food', 'water', 'food_rice', 'wooden_spoon', 'curtain', 'console', 'dishrack', 'pajamas', 'light', 'clothes_skirt', 'soap', 'dirt'] Task:Take shower response: { thoughts : go to a bathroom, open the shower, let water wash your body, actions : ['[WALK] <bathroom>', '[WALK] <shower>', '[FIND] <soap>', '[SCRUB] <soap>', '[FIND] <water>', '[RINSE] <water>'] } Scene_Objects:['fork', 'pot', 'microwave', 'bathroom', 'knife', 'floor', 'ceiling', 'bedroom', 'toaster', 'plate', 'shower', 'dish_soap', 'closetdrawer', 'dustpan', 'wall', 'powersocket', 'photoframe', 'coffe_maker', 'check', 'drinking_glass', 'curtain', 'centerpiece', 'shaving_cream', 'towel_rack', 'kitchen_counter', 'cupboard', 'sink', 'dishwasher', 'dirt', 'shoe_rack'] Task:Wash dishes with dishwasher response: | { Walk to the kitchen and turn to the dishwasher, put the knife, glass, fork and plate into the dishwasher. Turn on the 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', 'bathroom', 'trashcan', 'orchid', 'drawing', 'wallshelf', 'floor', 'character', 'bedroom', 'tea_bag', 'keyboard', 'toaster', 'mat', 'stovefan', 'tvstand', 'couch', 'dining_room', 'wall', 'nightstand', 'child', 'bed', 'photoframe', 'novel', 'food_onion', 'after_shave', 'cupboard', 'bathtub', 'napkin', 'bathroom_cabinet', '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:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'tape', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'door', 'light'] Task:Work response: | { I go to my home office. I find the computer along with mechanical keyboard on the desk. I sit on chair. I switch on the computer. I type on keyboard and work on the computer. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'toilet', 'chair', 'walllamp', 'bathroom', 'drawing', 'wallshelf', 'floor', 'phone', 'ceiling', 'desk', 'bookshelf', 'computer', 'mat', 'ceilinglamp', 'shower', 'window', 'clothes_hat', 'dining_room', 'wall', 'bench', 'powersocket', 'photoframe', 'doorjamb', 'kitchen_counter', 'dresser', 'cupboard', 'table', 'light', 'tooth_paste'] Task:Pick up phone response: { thoughts : Pick up phone, actions : ['[WALK] <table>', '[FIND] <phone>', '[TURNTO] <phone>', '[LOOKAT] <phone>', '[GRAB] <phone>'] } Scene_Objects:['sheets', 'filing_cabinet', 'microwave', 'band-aids', 'detergent', 'cat', 'drawing', 'orchid', 'ceiling', 'bedroom', 'keyboard', 'thread', 'clothes_jacket', 'toaster', 'iron', 'shower', 'mousepad', 'food_orange', 'broom', 'oven', 'coffee_filter', 'curtain', 'doorjamb', 'centerpiece', 'towel_rack', 'shoes', 'controller', 'door', 'bathroom_cabinet', 'teeth'] Task:Pet cat response: | { Find the cat; pet the cat by touching it } |
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_ice_cream', 'walllamp', 'nail_polish', 'cat', 'orchid', 'drawing', 'floor', 'ceiling', 'purse', 'alcohol', 'mail', 'table_cloth', 'mat', 'tvstand', 'ceilinglamp', 'window', 'couch', 'pillow', 'towel', 'wall', 'oven', 'cup', 'food_cheese', 'television', 'curtain', 'doorjamb', 'door', 'table', 'clothes_shirt'] Task:Straighten paintings on wall response: { thoughts : Go up to the painting and tilt it which ever way it is uneven until it looks straight., actions : ['[WALK] <home_office>', '[WALK] <wall>', '[WALK] <drawing>', '[FIND] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>', '[TOUCH] <drawing>', '[PULL] <drawing>', '[PUSH] <drawing>', '[WALK] <drawing>', '[FIND] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>', '[TOUCH] <drawing>', '[PULL] <drawing>', '[PUSH] <drawing>', '[WALK] <drawing>', '[FIND] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>', '[TOUCH] <drawing>', '[PULL] <drawing>', '[PUSH] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>'] } Scene_Objects:['food_pizza', 'chair', 'freezer', 'walllamp', 'dough', 'drawing', 'wallshelf', 'cpuscreen', 'floor', 'ceiling', 'desk', 'bedroom', 'bookshelf', 'computer', 'button', 'mat', 'tvstand', 'ceilinglamp', 'couch', 'pillow', 'wall', 'photoframe', 'novel', 'television', 'curtain', 'doorjamb', 'towel_rack', 'shoes', 'cupboard', 'table'] Task:Read book response: | { Walk to the couch in the living room, sit on ti and read the 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:['chair', 'walllamp', 'bathroom', 'trashcan', 'orchid', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'folder', 'bedroom', 'bookshelf', 'keyboard', 'ceilinglamp', 'faucet', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'food_food', 'television', 'curtain', 'doorjamb', 'towel_rack', 'dresser', 'bathtub', 'light', 'table', 'instrument_violin'] Task:Straighten pictures on wall response: { thoughts : Move the pictures/paintings until they are straight., actions : ['[WALK] <home_office>', '[WALK] <drawing>', '[FIND] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>', '[TOUCH] <drawing>', '[PUSH] <drawing>', '[FIND] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>', '[TOUCH] <drawing>', '[PUSH] <drawing>'] } Scene_Objects:['pot', 'tablelamp', 'microwave', 'walllamp', 'bathroom', 'wallshelf', 'cpuscreen', 'floor', 'shampoo', 'mop_bucket', 'toaster', 'mat', 'plate', 'shower', 'dish_soap', 'closetdrawer', 'dining_room', 'wall', 'photoframe', 'coffe_maker', 'colander', 'pencil', 'kitchen_counter', 'cupboard', 'clothes_dress', 'food_steak', 'home_office', 'dishwasher', 'soap', 'tooth_paste'] Task:Wash dishes with dishwasher response: | { 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. } |
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', 'beer', 'measuring_cup', 'toilet', 'drawing', 'knife', 'hanger', 'floor', 'desk', 'tea_bag', 'keyboard', 'piano_bench', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'laptop', 'foundation', 'clothes_pants', 'towel', 'wall', 'nightstand', 'novel', 'television', 'tray', 'curtain', 'bag', 'table', 'vase', 'soap'] Task:Wash hands response: { thoughts : BEFORE EATING, actions : ['[WALK] <bathroom>', '[WALK] <soap>', '[FIND] <soap>', '[GRAB] <soap>', '[FIND] <towel>', '[WIPE] <towel>'] } 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: | { I walk to the living room. I sit in the sofa and I relax. } |
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', 'board_game', 'chair', 'ground_coffee', 'detergent', 'knifeblock', 'floor', 'ceiling', 'alcohol', 'toaster', 'faucet', 'picture', 'closetdrawer', 'couch', 'dining_room', 'broom', 'wall', 'coffe_maker', 'check', 'water', 'drinking_glass', 'after_shave', 'rag', 'kitchen_counter', 'shoes', 'cupboard', 'hair', 'sink', 'table', 'tooth_paste'] Task:Drink response: { thoughts : Walk to kitchen. Walk to faucet. Switch on faucet. Pour water into drinking glass. Switch off faucet. Drink water., actions : ['[WALK] <dining_room>', '[WALK] <faucet>', '[SWITCHON] <faucet>', '[FIND] <water>', '[FIND] <drinking_glass>', '[GRAB] <drinking_glass>', '[FIND] <sink>', '[PUTBACK] <drinking_glass> <sink>', '[GRAB] <drinking_glass>', '[SWITCHOFF] <faucet>', '[DRINK] <drinking_glass>'] } Scene_Objects:['tablelamp', 'food_salt', 'chair', 'walllamp', 'toothbrush', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'remote_control', 'computer', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'oil', 'closetdrawer', 'couch', 'food_jam', 'pillow', 'food_kiwi', 'wall', 'photoframe', 'check', 'television', 'doorjamb', 'dresser', 'door'] Task:Change TV channel response: | { Walk to living room. Walk to and sit at the sofa. Grab remote control and switch on TV. } |
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', 'tea', 'microwave', 'chair', 'walllamp', 'blow_dryer', 'bathroom', 'knifeblock', 'wallshelf', 'floor', 'ceiling', 'ceilinglamp', 'plate', 'mousepad', 'food_noodles', 'couch', 'closetdrawer', 'food_jam', 'form', 'pillow', 'wall', 'nightstand', 'razor', 'television', 'shaving_cream', 'kitchen_counter', 'bathroom_cabinet', 'dishwasher', 'soap', 'teeth'] Task:Text friends while sitting on couch response: { thoughts : Text while sitting, actions : ['[WALK] <home_office>', '[WALK] <phone>', '[FIND] <phone>', '[GRAB] <phone>', '[WALK] <couch>', '[SIT] <couch>', '[TURNTO] <phone>', '[LOOKAT] <phone>', '[TOUCH] <phone>'] } Scene_Objects:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'picture', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'check', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'door', 'light'] Task:Browse internet response: | { I walk into my home office and walk up to my desk. I pull out the chair and sit down. I turn on the computer. After the computer is turned on I click on the google icon. I enter Disney Cruise Line into the search bar and browse the internet. } |
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', 'trashcan', 'ceilingfan', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'purse', 'computer', 'ceilinglamp', 'mat', 'balanceball', 'electric_shaver', 'window', 'mousepad', 'dustpan', 'pillow', 'wall', 'nightstand', 'photoframe', 'food_food', 'doorjamb', 'mouse', 'door', 'light'] Task:Browse internet response: { thoughts : turn on the computer and browse the internet, actions : ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>'] } Scene_Objects:['food_pizza', 'filing_cabinet', 'chair', 'band-aids', 'walllamp', 'drawing', 'wallshelf', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'bookshelf', 'remote_control', 'computer', 'button', 'mat', 'tvstand', 'ceilinglamp', 'closetdrawer', 'couch', 'pillow', 'wall', 'cup', 'photoframe', 'television', 'doorjamb', 'shoes', 'dresser', 'soap'] Task:Change TV channel response: | { I go to the livingroom. The TV is on. I pick up the remote and press the next channel button. I look at the television, and see that the channel has changed. } |
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', '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>'] } Scene_Objects:['dry_pasta', 'food_salt', 'toilet', 'walllamp', 'bathroom', 'food_carrot', 'dough', 'milk', 'phone', 'ceiling', 'bedroom', 'desk', 'keyboard', 'table_cloth', 'picture', 'oil', 'candle', 'clothes_pants', 'pillow', 'dining_room', 'wall', 'oven', 'coffe_maker', 'coin', 'towel_rack', 'pencil', 'dresser', 'clothes_dress', 'clothes_scarf', 'instrument_guitar'] Task:Pick up phone response: | { Walk to the entrance hall. Find the telephone. Grab the telephone. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'cup', 'television', 'tray', 'doorjamb', 'mouse', 'dresser', 'door'] 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>', '[FIND] <keyboard>', '[TYPE] <keyboard>', '[TURNTO] <computer>', '[LOOKAT] <computer>'] } Scene_Objects:['tablelamp', 'food_salt', 'toilet', 'chair', 'freezer', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'television', 'doorjamb', 'mouse', 'dresser', 'door'] Task:Work response: | { I need to complete work on my computer, so I will be pulling out my chair, turning on my computer and begin my task. } |
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', 'pot', 'walllamp', 'detergent', 'milk', 'hanger', 'phone', 'toaster', 'tvstand', 'balanceball', 'electric_shaver', 'food_noodles', 'garbage_can', 'mousepad', 'clothes_hat', 'pillow', 'broom', 'food_kiwi', 'bench', 'food_vegetable', 'food_cheese', 'food_food', 'ice', 'wine', 'rag', 'shaving_cream', 'dresser', 'cupboard', 'napkin', 'pantry'] Task:Organize pantry response: { thoughts : Remove all perishable foods from the pantry, check dates and throw away any old food. Decide on an efficient ad neat arrangement for the food and replace it in the pantry accordingly., actions : ['[WALK] <dining_room>', '[WALK] <pantry>', '[FIND] <food_food>', '[GRAB] <food_food>', '[TURNTO] <food_food>', '[LOOKAT] <food_food>', '[FIND] <garbage_can>', '[PUTBACK] <food_food> <garbage_can>', '[FIND] <food_vegetable>', '[GRAB] <food_vegetable>', '[TURNTO] <food_vegetable>', '[LOOKAT] <food_vegetable>', '[PUTBACK] <food_vegetable> <garbage_can>', '[FIND] <dry_pasta>', '[GRAB] <dry_pasta>', '[TURNTO] <dry_pasta>', '[LOOKAT] <dry_pasta>', '[PUTOBJBACK] <dry_pasta>', '[FIND] <food_food>', '[TURNTO] <food_food>', '[LOOKAT] <food_food>', '[PUSH] <food_food>', '[FIND] <food_noodles>', '[GRAB] <food_noodles>', '[TURNTO] <food_noodles>', '[LOOKAT] <food_noodles>', '[PUTOBJBACK] <food_noodles>'] } Scene_Objects:['tablelamp', 'orchid', 'wallshelf', 'hanger', 'bathroom_counter', 'floor', 'stamp', 'tvstand', 'faucet', 'shower', 'mousepad', 'couch', 'dining_room', 'wall', 'toy', 'bed', 'food_food', 'toilet_paper', 'mouthwash', 'doorjamb', 'pencil', 'kitchen_counter', 'comb', 'dresser', 'laundry_detergent', 'napkin', 'home_office', 'bathroom_cabinet', 'dishwasher', 'washing_machine'] Task:Wash clothes response: | { \ I walk to entrance hall\ \ I walk to bedroom\ \ I find basket of clothes\ \ I lift basket of clothes\ \ I walk to kitchen\ \ I find washing machine\ \ I open washing machine \ \ I put laundry in washing machine\ \ I add laundry detergent\ \ \ I close washing machine lid\ \ I switch washing machine on\ } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['toilet', 'freezer', 'dough', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'mat', 'deck_of_cards', 'shower', 'tvstand', 'food_jam', 'dining_room', 'wall', 'nightstand', 'powersocket', 'food_cheese', 'photoframe', 'novel', 'food_food', 'toilet_paper', 'coffe_maker', 'food_donut', 'doorjamb', 'kitchen_counter', 'dresser', 'door', 'light', 'tooth_paste', 'coffee'] Task:Put groceries in Fridge response: { thoughts : in my home i walk to the kitchen with some groceries and locate the fridge,then open the fridge put the groceries into the fridge and closed., actions : ['[WALK] <dining_room>', '[WALK] <food_food>', '[FIND] <food_food>', '[GRAB] <food_food>', '[FIND] <freezer>', '[OPEN] <freezer>', '[PUTIN] <food_food> <freezer>', '[CLOSE] <freezer>'] } Scene_Objects:['sponge', 'pot', 'tablelamp', 'food_salt', 'measuring_cup', 'walllamp', 'bathroom', 'milk', 'orchid', 'cpuscreen', 'stamp', 'keyboard', 'food_noodles', 'closetdrawer', 'mousepad', 'clothes_pants', 'pasta', 'powersocket', 'food_food', 'video_game_controller', 'check', 'water', 'chessboard', 'dresser', 'cupboard', 'clothes_scarf', 'home_office', 'bathroom_cabinet', 'soap', 'scrabble'] Task:Wash hands response: | { put soap on hands, scrub it and rinse with 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:['microwave', 'chair', 'detergent', 'cat', 'drawing', 'floor', 'stamp', 'computer', 'ceilinglamp', 'mat', 'balanceball', 'picture', 'window', 'foundation', 'faucet', 'couch', 'pillow', 'wall', 'powersocket', 'oven', 'mouthwash', 'television', 'ice', 'centerpiece', 'towel_rack', 'mouse', 'kitchen_counter', 'dresser', 'table', 'dishwasher'] 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>'] } Scene_Objects:['water_glass', 'food_salt', 'chair', 'freezer', 'drawing', 'wallshelf', 'hanger', 'phone', 'folder', 'bedroom', 'desk', 'keyboard', 'purse', 'couch', 'food_peanut_butter', 'clothes_pants', 'dining_room', 'wall', 'water', 'after_shave', 'doorjamb', 'towel_rack', 'mouse', 'kitchen_counter', 'conditioner', 'sink', 'napkin', 'home_office', 'table', 'tooth_paste'] Task:Drink response: | { Drinking a glass of 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:['water_glass', 'pot', 'freezer', 'walllamp', 'knifeblock', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'stovefan', 'ceilinglamp', 'faucet', 'oil', 'mousepad', 'food_peanut_butter', 'wall', 'oven', 'powersocket', 'food_food', 'water', 'tray', 'doorjamb', 'mouse', 'kitchen_counter', 'cupboard', 'door', 'sink', 'light'] 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:['tablelamp', 'chair', 'walllamp', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'dvd_player', 'desk', 'keyboard', 'purse', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'mousepad', 'food_noodles', 'couch', 'pillow', 'wall', 'nightstand', 'television', 'doorjamb', 'mouse', 'dresser', 'door', 'table'] Task:Write an email response: | { FIRST YOU NEED TO SWITVH ON YOU COMPUTER AND CHECK THE INTERNET CONNECTION.FOR SENDING EMAIL EMAIL ID FOR REQUIRED FOR BOTH SEND AND RECEIVE .SO CLEALY MENTION THE ID ON THE TO PLACE THEN ONLY IT WILL GO CORRECTLY } |
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:['glue', 'microwave', 'toilet', 'wallshelf', 'cpuscreen', 'hanger', 'bookshelf', 'computer', 'bookmark', 'mat', 'tvstand', 'shower', 'faucet', 'foundation', 'oil', 'closetdrawer', 'towel', 'powersocket', 'bed', 'novel', 'coin', 'after_shave', 'pencil', 'dresser', 'cupboard', 'clothes_dress', 'napkin', 'table', 'laser_pointer', 'creditcard'] Task:Pick up phone response: | { walk to living room , find phone ,pick up phone 3 } |
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', 'fork', 'blender', 'food_ice_cream', 'food_butter', 'phone', 'character', 'bookshelf', 'brush', 'ceilinglamp', 'plate', 'shower', 'iron', 'stereo', 'toaster', 'oil', 'food_orange', 'pillow', 'cup', 'food_food', 'check', 'oven_mitts', 'food_donut', 'food_onion', 'after_shave', 'mouse', 'hairdryer', 'bag', 'bathroom_cabinet', 'home_office'] 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>'] } Scene_Objects:['sponge', 'glue', 'tablelamp', 'crayon', 'freezer', 'cat', 'milk', 'wallshelf', 'bathroom_counter', 'bedroom', 'desk', 'bookshelf', 'thread', 'stovefan', 'stereo', 'faucet', 'pillow', 'pasta', 'oven', 'powersocket', 'cup', 'bed', 'coffe_maker', 'after_shave', 'mouse', 'dresser', 'door', 'hairdryer', 'dishwasher', 'creditcard'] Task:Pet cat response: | { Petting a cat may sound simple.Letting the Cat Come to You.Extend a hand or finger and allow the cat a chance to touch her nose to you. When a cat bumps her head into your hand, it's a signal she wants attention.Focusing on Areas with Scent Glands. Feed with food. } |
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', 'dough', 'drawing', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'dvd_player', 'desk', 'keyboard', 'bookshelf', 'computer', 'clothes_jacket', 'homework', 'mousepad', 'towel', 'wall', 'nightstand', 'bed', 'novel', 'coffe_maker', 'toothbrush_holder', 'ice', 'diary', 'kettle', 'mouse', 'door', 'spoon', 'instrument_violin'] Task:Study response: { thoughts : Do homework or read books while sitting on the chair., actions : ['[WALK] <bedroom>', '[WALK] <chair>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <novel>', '[GRAB] <novel>', '[READ] <novel>', '[PUTOBJBACK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[READ] <novel>', '[PUTOBJBACK] <novel>'] } Scene_Objects:['sheets', 'food_bread', 'filing_cabinet', 'tablelamp', 'blender', 'crayon', 'measuring_cup', 'microwave', 'freezer', 'bathroom', 'milk', 'needle', 'cpuscreen', 'wallshelf', 'hanger', 'phone', 'computer', 'toaster', 'ceilinglamp', 'newspaper', 'food_food', 'coffe_maker', 'ice', 'curtain', 'after_shave', 'dishrack', 'hairbrush', 'spoon', 'table', 'colander'] Task:Pick up phone response: | { I walk into the living room and walk over to the table with the phone. I pick up the phone and put it to my ear. } |
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', 'blender', 'freezer', 'trashcan', 'food_carrot', 'drawing', 'knifeblock', 'hanger', 'floor', 'ceiling', 'phone', 'computer', 'ceilinglamp', 'plate', 'iron', 'wall', 'nightstand', 'bed', 'food_food', 'check', 'drinking_glass', 'curtain', 'centerpiece', 'coffee_pot', 'cupboard', 'laundry_detergent', 'door', 'dishwasher', 'vase'] 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:['pot', 'water_glass', 'microwave', 'toilet', 'drawing', 'wallshelf', 'ceiling', 'desk', 'bookmark', 'toaster', 'stovefan', 'mat', 'shower', 'couch', 'wall', 'oven', 'coffe_maker', 'coin', 'water', 'tray', 'towel_rack', 'kitchen_counter', 'shoes', 'vacuum_cleaner', 'cupboard', 'controller', 'hairdryer', 'spoon', 'dishwasher', 'creditcard'] Task:Drink response: | { I go to the kitchen, take a glass from the cupboard, fill with water and drink } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'bookmark', 'mat', 'ceilinglamp', 'tvstand', 'picture', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'check', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'pencil', 'dresser', 'door', 'light'] Task:Compute response: { thoughts : Use computer., actions : ['[WALK] <home_office>', '[WALK] <desk>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[FIND] <keyboard>', '[TYPE] <keyboard>'] } Scene_Objects:['sheets', 'pot', 'filing_cabinet', 'tablelamp', 'freezer', 'bathroom', 'milk', 'drawing', 'floor', 'ceiling', 'bedroom', 'alcohol', 'computer', 'table_cloth', 'stovefan', 'mat', 'shower', 'oil', 'couch', 'pillow', 'wall', 'cutting_board', 'newspaper', 'food_food', 'television', 'kettle', 'kitchen_counter', 'cupboard', 'clothes_dress', 'shoe_rack'] Task:Put groceries in Fridge response: | { Walk to kitchen. Find groceries. Grab groceries. Find fridge. Walk to fridge. Put groceries in fridge. } |
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', 'measuring_cup', 'walllamp', 'ceilingfan', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'clothes_socks', 'food_noodles', 'couch', 'broom', 'wall', 'newspaper', 'light_bulb', 'novel', 'television', 'curtain', 'doorjamb', 'lighter', 'cupboard', 'table', 'light'] Task:Change TV channel response: { thoughts : Walk to the living room. Find remote control. Grab remote control. Walk to television. Look at television. Switch on remote control., actions : ['[WALK] <home_office>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[WALK] <television>', '[TURNTO] <television>', '[LOOKAT] <television>', '[SWITCHON] <television>'] } Scene_Objects:['glue', 'pot', 'filing_cabinet', 'food_bread', 'tablelamp', 'mop', 'toilet', 'freezer', 'walllamp', 'desk', 'keyboard', 'toaster', 'ceilinglamp', 'laptop', 'mousepad', 'dining_room', 'nightstand', 'cup', 'photoframe', 'clothes_gloves', 'novel', 'coffe_maker', 'curtain', 'dresser', 'controller', 'clothes_dress', 'door', 'sink', 'light', 'laser_pointer'] Task:Pet cat response: | { Find a cat in the kitchen and touch it } |
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', 'freezer', 'drawing', 'bills', 'hanger', 'floor', 'ceiling', 'keyboard', 'computer', 'toaster', 'tvstand', 'floor_lamp', 'window', 'closetdrawer', 'couch', 'towel', 'wall', 'wall_clock', 'food_food', 'doorjamb', 'mouse', 'headset', 'shoes', 'dresser', 'controller', 'bathtub', 'sink', 'home_office', 'light'] Task:Turn night light on response: { thoughts : I walk to the dresser and in the middle Io to small battery operated lamp and switch it on, actions : ['[WALK] <bedroom>', '[WALK] <dresser>', '[FIND] <floor_lamp>', '[TURNTO] <floor_lamp>', '[SWITCHON] <floor_lamp>'] } Scene_Objects:['fork', 'microwave', 'walllamp', 'bathroom', 'drawing', 'wallshelf', 'floor', 'ceiling', 'computer', 'toaster', 'mat', 'tvstand', 'brush', 'stovefan', 'couch', 'candle', 'pillow', 'wall', 'powersocket', 'toy', 'cup', 'photoframe', 'television', 'food_donut', 'tray', 'doorjamb', 'console', 'pencil', 'kitchen_counter', 'cupboard'] Task:Relax on sofa response: | { Walk to the living room. Walk to the sofa and sit on the sofa. } |
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', 'bathroom', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'shampoo', 'alcohol', 'stovefan', 'mat', 'shoe-shine_kit', 'tvstand', 'closetdrawer', 'couch', 'food_orange', 'pillow', 'wall', 'powersocket', 'photoframe', 'food_food', 'check', 'television', 'coffe_maker', 'ice', 'kitchen_counter', 'cupboard', 'hair', 'table', 'scrabble'] Task:Put groceries in Fridge response: { thoughts : I walk in to the kitchen. I open the fridge. I place the groceries in the fridge. I close the fridge., actions : ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <food_food>', '[GRAB] <food_food>', '[PUTIN] <food_food> <freezer>', '[CLOSE] <freezer>'] } Scene_Objects:['filing_cabinet', 'chair', 'walllamp', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'phone', 'stamp', 'computer', 'brush', 'mat', 'tvstand', 'mousepad', 'closetdrawer', 'couch', 'pillow', 'dining_room', 'wall', 'nightstand', 'photoframe', 'novel', 'coffe_maker', 'television', 'doorjamb', 'vacuum_cleaner', 'hairbrush', 'cupboard', 'table'] Task:Read book response: | { I pick up a book off the self that I want to read. Then, I sit down on the couch, open the book, and begin reading it. } |
Subsets and Splits
No saved queries yet
Save your SQL queries to embed, download, and access them later. Queries will appear here once saved.