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:['tablelamp', 'mop', 'microwave', 'chair', 'freezer', 'walllamp', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'newspaper', 'television', 'doorjamb', 'mouse', 'dresser', 'door'] Task:Browse internet response: { thoughts : Walk to the Home Office. Find the computer. Turn on the computer., actions : ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>'] } Scene_Objects:['chair', 'freezer', 'food_carrot', 'drawing', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'keyboard', 'bookshelf', 'toaster', 'window', 'foundation', 'wall', 'bed', 'food_food', 'coffe_maker', 'toothbrush_holder', 'water', 'drinking_glass', 'food_onion', 'mouse', 'kitchen_counter', 'dresser', 'cupboard', 'hair', 'door', 'bathroom_cabinet', 'light'] Task:Drink response: | { im feeling thirsty im going to kitchen and open the freezer where i can find some cold water and im going to drink it to end up my thirst } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'woman', 'drawing', 'wallshelf', 'bathroom_counter', 'floor', 'man', 'bookshelf', 'keyboard', 'piano_bench', 'stovefan', 'tvstand', 'shower', 'faucet', 'oil', 'dining_room', 'food_kiwi', 'nightstand', 'bench', 'oven', 'powersocket', 'coffe_maker', 'tray', 'curtain', 'towel_rack', 'cupboard', 'door', 'sink', 'light'] Task:Greet guests response: { thoughts : Stand next to the door. When the door opens from the outside, greet the guests., actions : ['[RUN] <home_office>', '[WALK] <woman>', '[FIND] <woman>', '[TURNTO] <woman>', '[LOOKAT] <woman>', '[GREET] <woman>', '[FIND] <man>', '[TURNTO] <man>', '[LOOKAT] <man>', '[GREET] <man>'] } Scene_Objects:['water_glass', 'food_bread', 'chair', 'freezer', 'walllamp', 'detergent', 'trashcan', 'drawing', 'desk', 'keyboard', 'bookshelf', 'bookmark', 'stovefan', 'ceilinglamp', 'tvstand', 'shower', 'faucet', 'pillow', 'bowl', 'wall', 'box', 'coffe_maker', 'razor', 'television', 'curtain', 'doorjamb', 'towel_rack', 'door', 'sink', 'bathroom_cabinet'] Task:Drink response: | { Pour water into a glass and drink from the glass. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'beer', 'microwave', 'chair', 'freezer', 'ground_coffee', 'floor', 'ceiling', 'mail', 'food_bacon', 'toaster', 'deck_of_cards', 'faucet', 'window', 'wall', 'wall_clock', 'bench', 'cutting_board', 'toy', 'light_bulb', 'coffe_maker', 'coffee_filter', 'water', 'curtain', 'after_shave', 'pencil', 'kitchen_counter', 'pajamas', 'sink', 'light'] Task:Make coffee response: { thoughts : Open coffee maker. Put filter in main basket, put ground coffee in filter, fill reservoir with water, turn on coffee maker., actions : ['[WALK] <dining_room>', '[WALK] <coffe_maker>', '[FIND] <coffe_maker>', '[OPEN] <coffe_maker>', '[FIND] <coffee_filter>', '[GRAB] <coffee_filter>', '[PUTBACK] <coffee_filter> <coffe_maker>', '[FIND] <ground_coffee>', '[GRAB] <ground_coffee>', '[FIND] <ground_coffee>', '[PUTBACK] <ground_coffee> <coffe_maker>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <coffe_maker>', '[CLOSE] <coffe_maker>', '[SWITCHON] <coffe_maker>'] } Scene_Objects:['sheets', 'filing_cabinet', 'microwave', 'ground_coffee', 'knifeblock', 'wallshelf', 'ceiling', 'phone', 'character', 'desk', 'piano_bench', 'stovefan', 'toaster', 'couch', 'clothes_hat', 'pillow', 'bench', 'oven', 'tape', 'cutting_board', 'doorjamb', 'cards', 'mouse', 'dishrack', 'cupboard', 'hairdryer', 'sink', 'clothes_scarf', 'table', 'dishwasher'] Task:Pick up phone response: | { i go find the phone. i pick up the 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:['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:['fork', 'microwave', 'drawing', 'orchid', 'knifeblock', 'wallshelf', 'floor', 'ceiling', 'phone', 'stamp', 'bedroom', 'remote_control', 'button', 'mat', 'faucet', 'homework', 'couch', 'pillow', 'wall', 'basket_for_clothes', 'coffe_maker', 'television', 'tray', 'curtain', 'doorjamb', 'kitchen_counter', 'door', 'table', 'light', 'laser_pointer'] Task:Change TV channel response: | { go to living room. grab remote control. sit on couch. point remote at tv. push buttons. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'bathroom', 'trashcan', 'drawing', 'orchid', 'floor', 'phone', 'ceiling', 'desk', 'bedroom', 'keyboard', 'computer', 'faucet', 'picture', 'window', 'closetdrawer', 'couch', 'dining_room', 'bed', 'light_bulb', 'keys', 'check', 'video_game_controller', 'tray', 'doorjamb', 'mouse', 'kitchen_counter', 'bathtub', 'home_office'] Task:Pet cat response: { thoughts : Petting the cat, actions : ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[TOUCH] <cat>'] } Scene_Objects:['pot', 'walllamp', 'drawing', 'orchid', 'wallshelf', 'cpuscreen', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'keyboard', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'cup', 'photoframe', 'television', 'curtain', 'doorjamb', 'mouse', 'door', 'bathroom_cabinet', 'table', 'light'] Task:Watch TV response: | { You walk to the living room and sit on the sofa. You grab the remote control, look at it and point at the television, you watch television. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['chair', 'freezer', 'walllamp', 'drawing', 'wallshelf', 'floor', 'character', 'keyboard', 'bookshelf', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'window', 'closetdrawer', 'couch', 'pillow', 'wall', 'nightstand', 'powersocket', 'wall_clock', 'toilet_paper', 'mouthwash', 'television', 'food_food', 'coffe_maker', 'curtain', 'doorjamb', 'bathroom_cabinet', 'table'] Task:Relax on sofa response: { thoughts : walk to living room, find sofa, sit in sofa, actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[WALK] <couch>', '[SIT] <couch>'] } Scene_Objects:['tablelamp', 'microwave', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'mat', 'plate', 'faucet', 'tvstand', 'clothes_hat', 'pillow', 'wall', 'oven', 'powersocket', 'newspaper', 'photoframe', 'check', 'coffe_maker', 'doorjamb', 'kitchen_counter', 'dishrack', 'cupboard', 'door', 'sink', 'clothes_scarf', 'table', 'clothes_skirt', 'dishwasher'] Task:Wash dishes by hand response: | { Walking towards sink and look at the leftover plates. Scrape dishes to remove leftover food - use a rubber spatula or paper towel. Fill sink or dishpan with clean, hot water. Then wash and rinse to removing residues. Finally leave it to dry. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sponge', 'glue', 'toilet', 'chair', 'detergent', 'dough', 'drawing', 'orchid', 'hanger', 'floor', 'ceiling', 'keyboard', 'alcohol', 'stovefan', 'ceilinglamp', 'couch', 'microphone', 'wall', 'nightstand', 'photoframe', 'coffe_maker', 'coffee_filter', 'doorjamb', 'kitchen_counter', 'hairbrush', 'cupboard', 'home_office', 'dishwasher', 'coffee', 'shoe_rack'] Task:Make coffee response: { thoughts : Open coffee maker. Put filter in main basket, put ground coffee in filter, fill reservoir with water, turn on coffee maker., actions : ['[WALK] <dining_room>', '[WALK] <coffe_maker>', '[FIND] <coffe_maker>', '[OPEN] <coffe_maker>', '[FIND] <coffee_filter>', '[GRAB] <coffee_filter>', '[PUTBACK] <coffee_filter> <coffe_maker>', '[FIND] <coffee>', '[GRAB] <coffee>', '[PUTBACK] <coffee> <coffe_maker>'] } Scene_Objects:['juice', 'blender', 'tea', 'toilet', 'chair', 'freezer', 'walllamp', 'trashcan', 'knifeblock', 'cpuscreen', 'floor', 'ceiling', 'keyboard', 'bookshelf', 'toaster', 'ceilinglamp', 'shower', 'mousepad', 'food_jam', 'pillow', 'wall', 'powersocket', 'bed', 'tray', 'kitchen_counter', 'dresser', 'cupboard', 'home_office', 'table', 'bathroom_cabinet'] Task:Put groceries in Fridge response: | { Go to kitchen and 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:['blender', 'freezer', 'walllamp', 'bathroom', 'drawing', 'clothes_underwear', 'hanger', 'floor', 'ceiling', 'character', 'keyboard', 'brush', 'tvstand', 'stereo', 'window', 'closetdrawer', 'towel', 'wall', 'powersocket', 'tape', 'food_food', 'television', 'curtain', 'doorjamb', 'vacuum_cleaner', 'dresser', 'door', 'clothes_scarf', 'dishwasher', 'board_game'] Task:vacuum carpet response: { thoughts : I bring my vacuum cleaner into the living room. I plug it into the wall. I press the on switch on the vacuum cleaner. I push the vacuum cleaner back and forth over the length and width of the carpet until I have vacuumed the entire carpet. I turn the vacuum cleaner off. I take the vacuum cleaner back to the hall closet., actions : ['[WALK] <home_office>', '[WALK] <dresser>', '[OPEN] <dresser>', '[FIND] <vacuum_cleaner>', '[GRAB] <vacuum_cleaner>', '[PULL] <vacuum_cleaner>', '[PLUGIN] <vacuum_cleaner>', '[SWITCHON] <vacuum_cleaner>', '[PULL] <vacuum_cleaner>', '[PUSH] <vacuum_cleaner>', '[PULL] <vacuum_cleaner>', '[PUSH] <vacuum_cleaner>', '[PULL] <vacuum_cleaner>', '[PUSH] <vacuum_cleaner>', '[SWITCHOFF] <vacuum_cleaner>', '[PLUGOUT] <vacuum_cleaner>', '[WALK] <dresser>', '[PUTIN] <vacuum_cleaner> <dresser>', '[CLOSE] <dresser>'] } Scene_Objects:['dry_pasta', 'filing_cabinet', 'jelly', 'drawing', 'orchid', 'knifeblock', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'character', 'computer', 'bookmark', 'faucet', 'clothes_socks', 'couch', 'pillow', 'broom', 'wall', 'wall_clock', 'tape', 'photoframe', 'novel', 'check', 'food_onion', 'doorjamb', 'door', 'bathtub', 'table', 'light'] Task:Relax on sofa response: | { Go to the living room and relax on the sofa with a 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', 'toilet', 'jelly', 'ceilingfan', 'drawing', 'hanger', 'floor', 'stamp', 'desk', 'ceilinglamp', 'balanceball', 'faucet', 'window', 'couch', 'clothes_pants', 'pillow', 'wall', 'nightstand', 'bed', 'photoframe', 'television', 'oven_mitts', 'food_rice', 'doorjamb', 'cards', 'shaving_cream', 'sink', 'table', 'light', 'shoe_rack'] Task:Relax on sofa response: { thoughts : go to living room and lie down on the sofa., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[LIE] <couch>'] } Scene_Objects:['scissors', 'chair', 'bathroom', 'drawing', 'wallshelf', 'cpuscreen', 'character', 'desk', 'envelope', 'computer', 'shower', 'faucet', 'electric_shaver', 'dustpan', 'dining_room', 'wall', 'bench', 'tape', 'photoframe', 'check', 'doorjamb', 'centerpiece', 'mouse', 'hairbrush', 'bathroom_cabinet', 'table', 'home_office', 'light', 'instrument_guitar', 'creditcard'] Task:Receive credit card response: | { hear the dooble, go to door, take de envelope, open it with a scissor, take the creditcard } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'tablelamp', 'microwave', 'walllamp', 'bathroom', 'drawing', 'wallshelf', 'floor', 'ceiling', 'bedroom', 'bookshelf', 'computer', 'brush', 'mat', 'tvstand', 'couch', 'clothes_hat', 'pillow', 'wall', 'nightstand', 'powersocket', 'cup', 'photoframe', 'food_food', 'television', 'doorjamb', 'bag', 'light', 'dishwasher', 'table'] Task:Relax on sofa response: { thoughts : Open coffee maker. Put filter in main basket, put ground coffee in filter, fill reservoir with water, turn on coffee maker., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>'] } Scene_Objects:['pot', 'filing_cabinet', 'tablelamp', 'blender', 'band-aids', 'trashcan', 'drawing', 'knifeblock', 'bathroom_counter', 'shampoo', 'phone', 'remote_control', 'mat', 'plate', 'window', 'oil', 'food_jam', 'bowl', 'wall', 'nightstand', 'newspaper', 'keys', 'check', 'coffe_maker', 'curtain', 'doorjamb', 'towel_rack', 'mouse', 'cupboard', 'table'] Task:Change TV channel response: | { take remote control, push \ change channel\ 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:['sheets', 'spectacles', 'filing_cabinet', 'walllamp', 'ceilingfan', 'food_carrot', 'toothbrush', 'drawing', 'desk', 'bookshelf', 'stovefan', 'balanceball', 'shower', 'window', 'candle', 'clothes_pants', 'food_orange', 'dining_room', 'bench', 'bed', 'keys', 'food_food', 'diary', 'mouse', 'shoes', 'sink', 'vase', 'tooth_paste', 'scrabble', 'teeth'] Task:Brush teeth response: { thoughts : EARLY MORNING AND BEFORE GOING TO BED, actions : ['[WALK] <bathroom>', '[WALK] <tooth_paste>', '[FIND] <tooth_paste>', '[GRAB] <tooth_paste>', '[FIND] <toothbrush>', '[GRAB] <toothbrush>'] } Scene_Objects:['tablelamp', 'walllamp', 'trashcan', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'bedroom', 'stamp', 'desk', 'button', 'toaster', 'mat', 'plate', 'shower', 'dish_soap', 'pillow', 'wall', 'nightstand', 'food_cheese', 'coffe_maker', 'food_food', 'kitchen_counter', 'dishrack', 'cupboard', 'controller', 'hairdryer', 'home_office', 'dishwasher', 'instrument_violin'] Task:Wash dishes with dishwasher response: | { Walk to kitchen. Find dishwasher. Open dishwasher. Find dishrack. Find plate 1. Grab plate 1. Put plate 1 in dishrack. Repeat for dish 2. Find dish soap. Grab dish soap. Put dish soap to dishwasher. Close dishwasher. Switch on dishwasher. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'blender', 'chair', 'freezer', 'walllamp', 'trashcan', 'knifeblock', 'orchid', 'food_egg', 'kitchen_cabinet', 'floor', 'ceiling', 'food_bacon', 'stovefan', 'ceilinglamp', 'toaster', 'faucet', 'wall', 'oven', 'food_cheese', 'food_food', 'food_donut', 'food_rice', 'wine', 'tray', 'kitchen_counter', 'dresser', 'cupboard', 'sink', 'dishwasher'] Task:Cook some food response: { thoughts : Walk into kitchen. Open fridge. Take food from fridge. Close fridge. Put food on kitchen counter. Prepare food. Turn on stove. Open kitchen cabinet. Take pot. Close cabinet. Put food in pot. Put pot on stove. Cook food., actions : ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <food_food>', '[GRAB] <food_food>', '[FIND] <kitchen_counter>', '[PUTBACK] <food_food> <kitchen_counter>', '[CLOSE] <freezer>', '[FIND] <kitchen_cabinet>', '[OPEN] <kitchen_cabinet>', '[FIND] <pot>', '[GRAB] <pot>', '[CLOSE] <kitchen_cabinet>', '[FIND] <oven>', '[PUTBACK] <pot> <oven>', '[GRAB] <food_food>', '[PUTBACK] <food_food> <oven>'] } Scene_Objects:['sheets', 'spectacles', 'filing_cabinet', 'tablelamp', 'freezer', 'bathroom', 'bathroom_counter', 'phone', 'table_cloth', 'toaster', 'mat', 'tvstand', 'faucet', 'mousepad', 'towel', 'nightstand', 'oven', 'cup', 'bed', 'photoframe', 'newspaper', 'food_food', 'after_shave', 'doorjamb', 'towel_rack', 'mouse', 'dishrack', 'controller', 'dishwasher', 'tooth_paste'] Task:Turn on light response: | { I walk into my bedroom, go to the lamp and use the switch to turn it 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:['tablelamp', 'chair', 'dough', 'bills', 'drawing', 'clothes_underwear', 'floor', 'ceiling', 'shampoo', 'bookshelf', 'computer', 'mat', 'window', 'food_noodles', 'bowl', 'wall', 'nightstand', 'oven', 'basket_for_clothes', 'cup', 'bed', 'toilet_paper', 'mouthwash', 'ice', 'doorjamb', 'vacuum_cleaner', 'dishrack', 'door', 'napkin', 'home_office'] Task:Go to sleep response: { thoughts : Walk to bedroom. Walk to bed, lie in bed., actions : ['[WALK] <bedroom>', '[WALK] <bed>', '[LIE] <bed>'] } Scene_Objects:['filing_cabinet', 'walllamp', 'bathroom', 'detergent', 'orchid', 'knifeblock', 'drawing', 'hanger', 'floor', 'ceiling', 'phone', 'bookshelf', 'mat', 'shower', 'faucet', 'wall', 'powersocket', 'oven', 'light_bulb', 'novel', 'check', 'television', 'food_donut', 'curtain', 'doorjamb', 'kitchen_counter', 'spoon', 'home_office', 'light', 'dishwasher'] Task:Turn on light response: | { Switch on light 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:['spectacles', 'tablelamp', 'microwave', 'chair', 'wallshelf', 'hanger', 'floor', 'phone', 'food_bacon', 'piano_bench', 'stovefan', 'ceilinglamp', 'shower', 'mousepad', 'closetdrawer', 'powersocket', 'television', 'coin', 'food_donut', 'ice', 'rag', 'pencil', 'shoes', 'dresser', 'clothes_dress', 'clothes_scarf', 'sink', 'bathroom_cabinet', 'light', 'home_office'] Task:Hang up jacket response: { thoughts : I put clothes on hangers and hang them in the closet, actions : ['[WALK] <bedroom>', '[WALK] <clothes_dress>', '[FIND] <clothes_dress>', '[GRAB] <clothes_dress>', '[WALK] <dresser>', '[FIND] <hanger>', '[OPEN] <dresser>', '[PUTIN] <clothes_dress> <dresser>', '[FIND] <clothes_dress>', '[GRAB] <clothes_dress>', '[WALK] <dresser>', '[PUTIN] <clothes_dress> <dresser>', '[CLOSE] <dresser>'] } Scene_Objects:['sponge', 'pot', 'microwave', 'walllamp', 'knifeblock', 'food_egg', 'floor', 'ceiling', 'desk', 'bedroom', 'ceilinglamp', 'plate', 'faucet', 'window', 'dish_soap', 'mousepad', 'bowl', 'wall', 'oven', 'powersocket', 'check', 'mouthwash', 'after_shave', 'kitchen_counter', 'dishrack', 'dresser', 'cupboard', 'sink', 'bathtub', 'dishwasher'] Task:Wash dishes by hand response: | { I go to the kitchen and turn on the faucet. I get dish soap and put it into the sink. I grab a sponge and a bowl and start cleaning it. I put the bowl into the dishrack. I find a plate and clean it as well. I put it into the dishrack, turn off the faucet and put the sponge back. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['toilet', 'chair', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'toaster', 'mat', 'stereo', 'faucet', 'mousepad', 'wall', 'wall_clock', 'cup', 'bed', 'photoframe', 'novel', 'coffe_maker', 'television', 'mouse', 'kitchen_counter', 'headset', 'cupboard', 'bathroom_cabinet', 'light'] Task:Listen to music response: { thoughts : I walk to my bedroom. I locate my stereo and turn it on. I put on my headphones and sit to listen., actions : ['[WALK] <bedroom>', '[WALK] <stereo>', '[FIND] <stereo>', '[WALK] <stereo>', '[SWITCHON] <stereo>', '[FIND] <headset>', '[GRAB] <headset>', '[PUTON] <headset>', '[FIND] <chair>', '[SIT] <chair>'] } Scene_Objects:['microwave', 'walllamp', 'cat', 'toothbrush', 'orchid', 'knife', 'bills', 'bathroom_counter', 'floor', 'desk', 'stovefan', 'laptop', 'shoe-shine_kit', 'shower', 'window', 'mousepad', 'couch', 'powersocket', 'photoframe', 'wooden_spoon', 'curtain', 'doorjamb', 'coffee_pot', 'mouse', 'door', 'bathtub', 'home_office', 'table', 'light', 'clothes_shirt'] Task:Pet cat response: | { I walk to my cat, and I pet him } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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:['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: | { Sit down, turn on the TV with the remote control that is on the coffee 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:['sponge', 'microwave', 'toilet', 'jelly', 'freezer', 'ground_coffee', 'food_carrot', 'drawing', 'wallshelf', 'floor', 'ceiling', 'phone', 'button', 'mat', 'shower', 'picture', 'dustpan', 'food_orange', 'form', 'nightstand', 'wall', 'powersocket', 'food_cheese', 'photoframe', 'light_bulb', 'food_food', 'doorjamb', 'cd', 'door', 'light'] Task:Added meat to freezer response: { thoughts : After shopping for groceries, i returned home, i walked to the dining room and placed meat items in freezer located in the dining room. I opened up the bags from the grocery store, removed all the meat items, and after opening the freezer door, i placed the meat items into the freezer, and closed the door., actions : ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <food_food>', '[GRAB] <food_food>', '[PUTBACK] <food_food> <freezer>', '[CLOSE] <freezer>'] } Scene_Objects:['sheets', 'walllamp', 'trashcan', 'cpuscreen', 'bathroom_counter', 'floor', 'phone', 'ceiling', 'folder', 'bedroom', 'food_cake', 'computer', 'shower', 'iron', 'window', 'pillow', 'wall', 'nightstand', 'powersocket', 'tape', 'bed', 'television', 'wine', 'doorjamb', 'towel_rack', 'dresser', 'home_office', 'light', 'bathroom_cabinet', 'dishwasher'] Task:Pick up phone response: | { I walk to the kitchen and find the phone. I pick up the phone. I hold 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:['dry_pasta', 'tablelamp', 'food_salt', 'chair', 'walllamp', 'detergent', 'drawing', 'clothes_underwear', 'floor', 'bedroom', 'toaster', 'ceilinglamp', 'tvstand', 'shower', 'food_noodles', 'garbage_can', 'mousepad', 'microphone', 'wall', 'nightstand', 'food_vegetable', 'bed', 'food_food', 'coffee_filter', 'mouse', 'sink', 'home_office', 'table', 'dishwasher', '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:['pot', 'food_pizza', 'mop', 'walllamp', 'knifeblock', 'floor', 'ceiling', 'bedroom', 'bookshelf', 'clothes_jacket', 'stovefan', 'faucet', 'window', 'pillow', 'bowl', 'wall', 'wall_clock', 'oven', 'cup', 'photoframe', 'food_food', 'toilet_paper', 'tray', 'after_shave', 'towel_rack', 'kitchen_counter', 'cupboard', 'sink', 'table', 'tooth_paste'] Task:Cook some food response: | { I switch on the stove and cook my groceries there. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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:['spectacles', 'pot', 'food_ice_cream', 'microwave', 'toilet', 'walllamp', 'knifeblock', 'drawing', 'floor', 'ceiling', 'desk', 'computer', 'toaster', 'faucet', 'mousepad', 'oil', 'candle', 'bowl', 'wall', 'bed', 'photoframe', 'coffe_maker', 'lighter', 'cards', 'kitchen_counter', 'cupboard', 'door', 'sink', 'dishwasher', 'colander'] Task:Wash dishes with dishwasher response: | { Walk to Kitchen. Take the dishes from the sink. Apply dish washer, scrub and then wash 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:['chair', 'walllamp', 'bathroom', 'drawing', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'bedroom', 'keyboard', 'computer', 'table_cloth', 'ceilinglamp', 'tvstand', 'window', 'mousepad', 'wall', 'wall_clock', 'powersocket', 'check', 'television', 'tray', 'curtain', 'doorjamb', 'mouse', 'kitchen_counter', 'bathtub', 'sink', 'table'] Task:Browse internet response: { thoughts : I go to the office and sit in a chair, I turn on the computer and grab the mouse. I type on the keyboard and starting working on the computer., actions : ['[WALK] <home_office>', '[WALK] <desk>', '[FIND] <desk>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <mouse>', '[GRAB] <mouse>', '[FIND] <keyboard>', '[TYPE] <keyboard>', '[TURNTO] <computer>', '[LOOKAT] <computer>'] } Scene_Objects:['food_ice_cream', 'toilet', 'walllamp', 'nail_polish', 'dough', 'orchid', 'wallshelf', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'keyboard', 'computer', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'wall', 'nightstand', 'powersocket', 'photoframe', 'television', 'curtain', 'doorjamb', 'cards', 'dishrack', 'door', 'light'] Task:Change TV channel response: | { first i will go to living room and then take the remote and swtitch on television after that il 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', 'microwave', 'chair', 'bathroom', 'food_butter', 'drawing', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'shower', 'foundation', 'couch', 'pillow', 'wall', 'nightstand', 'powersocket', 'box', 'newspaper', 'coffe_maker', 'food_onion', 'doorjamb', 'mouse', 'controller', 'door', 'bathtub', 'table', 'light', 'scrabble'] Task:Relax on sofa response: { thoughts : Walk to the living room, find the sofa and sit in the sofa and find pillow. lie down in sofa., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <pillow>', '[LIE] <couch>'] } Scene_Objects:['microwave', 'chair', 'food_butter', 'food_carrot', 'drawing', 'orchid', 'knifeblock', 'knife', 'cpuscreen', 'floor', 'ceiling', 'bookshelf', 'toaster', 'mat', 'food_noodles', 'couch', 'pillow', 'wall', 'bed', 'photoframe', 'food_food', 'curtain', 'doorjamb', 'towel_rack', 'cupboard', 'door', 'bathroom_cabinet', 'table', 'light', 'dirt'] Task:Relax on sofa response: | { Relax on the sofa in the 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:['tablelamp', 'blender', 'microwave', 'freezer', 'walllamp', 'bathroom', 'orchid', 'drawing', 'hanger', 'floor', 'ceiling', 'character', 'desk', 'computer', 'mat', 'tvstand', 'faucet', 'window', 'mousepad', 'closetdrawer', 'pillow', 'wall', 'nightstand', 'food_cheese', 'bed', 'novel', 'curtain', 'diary', 'dresser', 'bathroom_cabinet'] Task:Read book response: { thoughts : Put child in bed, sit down,read book., actions : ['[WALK] <bedroom>', '[WALK] <dresser>', '[OPEN] <dresser>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <bed>', '[SIT] <bed>', '[READ] <novel>'] } Scene_Objects:['pot', 'filing_cabinet', 'chair', 'bathroom', 'trashcan', 'knifeblock', 'orchid', 'wallshelf', 'cpuscreen', 'bathroom_counter', 'phone', 'desk', 'food_cake', 'computer', 'table_cloth', 'tvstand', 'faucet', 'couch', 'oven', 'powersocket', 'cup', 'photoframe', 'check', 'tray', 'curtain', 'wooden_spoon', 'doorjamb', 'door', 'bathtub', 'soap'] Task:Pick up phone response: | { Walk into the home office. Pick up the phone. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'tablelamp', 'freezer', 'walllamp', 'food_carrot', 'desk', 'food_cake', 'remote_control', 'button', 'ceilinglamp', 'faucet', 'stereo', 'window', 'mousepad', 'couch', 'wall_clock', 'bench', 'box', 'cup', 'bed', 'keys', 'newspaper', 'food_food', 'ice', 'after_shave', 'maindoor', 'bathroom_cabinet', 'light', 'vase', 'soap'] Task:Watch TV response: { thoughts : I walk to the living room and sit on the couch. I grab the TV remote. I press the power button on the TV remote and the TV turns on. I grab the surround sound remote. I press the power button on the surround sound remote and the system turns on., actions : ['[WALK] <home_office>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[PUSH] <remote_control>', '[FIND] <remote_control>', '[PUSH] <remote_control>'] } Scene_Objects:['tablelamp', 'food_salt', 'microwave', 'chair', 'walllamp', 'knifeblock', 'floor', 'phone', 'desk', 'tea_bag', 'keyboard', 'bookshelf', 'purse', 'toaster', 'mat', 'stereo', 'faucet', 'mousepad', 'pillow', 'mouthwash', 'curtain', 'cards', 'shoes', 'cd', 'dishrack', 'dresser', 'door', 'instrument_guitar', 'table', 'bathroom_cabinet'] Task:Read book response: | { Read a 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:['filing_cabinet', 'food_salt', 'freezer', 'walllamp', 'drawing', 'orchid', 'floor', 'ceiling', 'bedroom', 'remote_control', 'ceilinglamp', 'tvstand', 'mat', 'homework', 'window', 'wall', 'powersocket', 'oven', 'toy', 'bed', 'toilet_paper', 'television', 'toothbrush_holder', 'food_donut', 'tray', 'doorjamb', 'door', 'sink', 'spoon', 'table'] Task:Change TV channel response: { thoughts : Lift the remote and change the channel, actions : ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[TURNTO] <television>', '[WATCH] <television>'] } Scene_Objects:['sponge', 'pot', 'food_ice_cream', 'microwave', 'freezer', 'walllamp', 'knifeblock', 'floor', 'bookshelf', 'clothes_jacket', 'plate', 'faucet', 'tvstand', 'towel', 'wall', 'nightstand', 'bench', 'coffe_maker', 'television', 'wooden_spoon', 'after_shave', 'towel_rack', 'mouse', 'kitchen_counter', 'cupboard', 'pajamas', 'door', 'sink', 'home_office', 'tooth_paste'] Task:Wash dishes by hand response: | { 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. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'food_salt', 'measuring_cup', 'jelly', 'freezer', 'nail_polish', 'ceilingfan', 'drawing', 'orchid', 'longboard', 'floor', 'ceiling', 'bedroom', 'keyboard', 'ceilinglamp', 'tvstand', 'balanceball', 'stereo', 'window', 'deck_of_cards', 'mousepad', 'couch', 'clothes_pants', 'wall', 'television', 'curtain', 'kitchen_counter', 'chessboard', 'spoon', 'table'] Task:Change TV channel response: { thoughts : I walk in living room. I find TV remote. I grab TV remote. I sit on sofa. I switch on TV. I switch channel., actions : ['[WALK] <home_office>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[WALK] <couch>', '[SIT] <couch>', '[FIND] <television>', '[SWITCHON] <television>', '[TURNTO] <remote_control>', '[LOOKAT] <remote_control>', '[PUSH] <remote_control>'] } Scene_Objects:['sheets', 'dry_pasta', 'food_ice_cream', 'toilet', 'freezer', 'knifeblock', 'wallshelf', 'folder', 'desk', 'stamp', 'bedroom', 'computer', 'toaster', 'mat', 'floor_lamp', 'dustpan', 'pillow', 'dining_room', 'broom', 'wall', 'nightstand', 'check', 'curtain', 'console', 'dresser', 'door', 'sink', 'bathroom_cabinet', 'light', 'dishwasher'] Task:Turn on light response: | { I go home and it's dark so I can not see anything } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'chair', 'walllamp', 'detergent', 'knifeblock', 'orchid', 'cpuscreen', 'drawing', 'bathroom_counter', 'phone', 'folder', 'man', 'keyboard', 'mop_bucket', 'tvstand', 'faucet', 'picture', 'plate', 'mousepad', 'bench', 'oven', 'powersocket', 'photoframe', 'food_food', 'check', 'food_onion', 'clothes_scarf', 'spoon', 'light', 'dishwasher'] Task:Greet guests response: { thoughts : When someone knocks I n the door walk through the hallway and greet them., actions : ['[RUN] <home_office>', '[WALK] <man>', '[FIND] <man>', '[GREET] <man>', '[FIND] <man>', '[GREET] <man>'] } Scene_Objects:['sponge', 'toilet', 'chair', 'freezer', 'band-aids', 'walllamp', 'cat', 'drawing', 'orchid', 'floor', 'ceiling', 'phone', 'bedroom', 'ceilinglamp', 'tvstand', 'clothes_socks', 'couch', 'pillow', 'dining_room', 'wall', 'bench', 'clothes_gloves', 'novel', 'tray', 'doorjamb', 'kitchen_counter', 'door', 'table', 'light', 'dishwasher'] Task:Pet cat response: | { walk to entrance hall, look at the sofa, sit on the sofa, look at the cat, allow cat to near with you, touch the cat smoothly on it head, now pet the cat smoothly } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'chair', 'walllamp', 'detergent', 'knifeblock', 'orchid', 'cpuscreen', 'drawing', 'bathroom_counter', 'phone', 'folder', 'man', 'keyboard', 'mop_bucket', 'tvstand', 'faucet', 'picture', 'plate', 'mousepad', 'bench', 'oven', 'powersocket', 'photoframe', 'food_food', 'check', 'food_onion', 'clothes_scarf', 'spoon', 'light', 'dishwasher'] Task:Greet guests response: { thoughts : When someone knocks I n the door walk through the hallway and greet them., actions : ['[RUN] <home_office>', '[WALK] <man>', '[FIND] <man>', '[GREET] <man>', '[FIND] <man>', '[GREET] <man>'] } 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: | { Walk to home office. Walk to computer. Switch on Computer. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['chair', 'walllamp', 'bathroom', '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', 'filing_cabinet', 'microwave', 'ground_coffee', 'walllamp', 'orchid', 'knifeblock', 'floor', 'ceiling', 'character', 'bookshelf', 'toaster', 'mat', 'faucet', 'wall', 'basket_for_clothes', 'photoframe', 'bed', 'coffe_maker', 'food_food', 'coffee_filter', 'kitchen_counter', 'cd', 'dresser', 'cupboard', 'door', 'napkin', 'bathroom_cabinet', 'light', 'dishwasher'] Task:Make coffee response: | { You walk into the kitchen and turn to the coffee maker. You grab the coffee filter and put into the coffee machine, you also grab the ground coffee and put it into the coffee machine. You turn on the coffee machine. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'trashcan', 'knifeblock', 'floor', 'ceiling', 'desk', 'bedroom', 'stovefan', 'ceilinglamp', 'plate', 'mat', 'couch', 'wall', 'oven', 'food_food', 'tray', 'food_onion', 'curtain', 'diary', 'kitchen_counter', 'dishrack', 'sauce_pan', 'cupboard', 'spoon', 'home_office'] Task:Cook some food response: { thoughts : I pull a sauce pan from the cupboard. I turn the stove on. I take my ingredients from the pantry and fridge. I put the ingredients in the pan and I mix them with a spoon. I cook until the food is finished and transfer my food to a plate., actions : ['[WALK] <dining_room>', '[WALK] <food_food>', '[FIND] <food_food>', '[FIND] <pot>', '[GRAB] <pot>', '[FIND] <spoon>', '[GRAB] <spoon>', '[FIND] <sauce_pan>', '[PUTBACK] <spoon> <sauce_pan>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <plate>', '[PUTBACK] <pot> <plate>'] } Scene_Objects:['filing_cabinet', 'bathroom', 'drawing', 'orchid', 'floor', 'ceiling', 'phone', 'desk', 'bookshelf', 'keyboard', 'shower', 'oil', 'couch', 'pillow', 'bowl', 'wall', 'powersocket', 'bed', 'television', 'doorjamb', 'towel_rack', 'kitchen_counter', 'door', 'sink', 'bathtub', 'bathroom_cabinet', 'light', 'table', 'clothes_skirt', 'creditcard'] Task:Relax on sofa response: | { I want to relax on the sofa to some relaxing music in the 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:['filing_cabinet', 'blender', 'crayon', 'toilet', 'chair', 'freezer', 'drawing', 'hanger', 'floor', 'ceiling', 'bookshelf', 'computer', 'clothes_jacket', 'ceilinglamp', 'window', 'pillow', 'wall', 'pasta', 'powersocket', 'toy', 'box', 'cup', 'check', 'coffe_maker', 'toothbrush_holder', 'doorjamb', 'dresser', 'door', 'light', 'scrabble'] Task:Pick up toys response: { thoughts : Pickup toys from around the room. Organize toys back into their appropriate spaces on the shelves and into the toy boxes., actions : ['[WALK] <bedroom>', '[WALK] <toy>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <filing_cabinet>', '[OPEN] <filing_cabinet>', '[PUTBACK] <toy> <filing_cabinet>', '[CLOSE] <filing_cabinet>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <dresser>', '[OPEN] <dresser>', '[PUTBACK] <toy> <dresser>', '[CLOSE] <dresser>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <filing_cabinet>', '[OPEN] <filing_cabinet>', '[PUTBACK] <toy> <filing_cabinet>', '[CLOSE] <filing_cabinet>'] } Scene_Objects:['tablelamp', 'chair', 'freezer', 'bathroom', 'orchid', 'floor', 'ceiling', 'character', 'bedroom', 'computer', 'toaster', 'stovefan', 'ceilinglamp', 'picture', 'tooth_paste', 'couch', 'pillow', 'wall', 'nightstand', 'food_food', 'check', 'television', 'tray', 'doorjamb', 'mouse', 'kitchen_counter', 'cupboard', 'home_office', 'bathroom_cabinet', 'board_game'] Task:Put groceries in Fridge response: | { Walk to the kitchen. Open the fridge, take the groceries and put in it. Closed the 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:['food_bread', 'chair', 'bathroom', 'detergent', 'orchid', 'knife', 'hanger', 'floor', 'character', 'computer', 'mail', 'table_cloth', 'toaster', 'foundation', 'window', 'mousepad', 'bench', 'shelf', 'photoframe', 'bed', 'coffe_maker', 'cards', 'chessboard', 'controller', 'door', 'maindoor', 'bathtub', 'light', 'vase', 'laser_pointer'] Task:Pick up phone response: { thoughts : walk into living room, look at the phone when it ringing, grab the phone or pickup the phone, actions : ['[WALK] <home_office>', '[WALK] <phone>', '[FIND] <phone>', '[TURNTO] <phone>', '[LOOKAT] <phone>'] } Scene_Objects:['pot', 'tablelamp', 'walllamp', 'orchid', 'floor', 'ceiling', 'character', 'desk', 'table_cloth', 'toaster', 'ceilinglamp', 'plate', 'faucet', 'stovefan', 'dish_soap', 'mousepad', 'couch', 'wall', 'powersocket', 'bed', 'coffe_maker', 'food_food', 'kitchen_counter', 'cupboard', 'controller', 'sink', 'dishwasher', 'soap', 'clothes_shirt', 'teeth'] Task:Wash dishes with dishwasher response: | { Walk to the kitchen. Open the dishwasher. Grab plate and put it in the dishwasher. Grab dish soap and put it in the dishwasher. Switch on the dishwasher. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sponge', 'food_pizza', 'juice', 'toilet', 'freezer', 'blow_dryer', 'walllamp', 'ceilingfan', 'knifeblock', 'bathroom_counter', 'alcohol', 'button', 'stereo', 'form', 'towel', 'oven', 'basket_for_clothes', 'photoframe', 'light_bulb', 'toilet_paper', 'toothbrush_holder', 'kitchen_counter', 'shoes', 'chessboard', 'vacuum_cleaner', 'clothes_scarf', 'home_office', 'dishwasher', 'soap', 'shoe_rack'] Task:Wash hands response: { thoughts : I walk to the kitchen and get the soap and wash my both hand using the soap and rinse my hands and use towel., actions : ['[WALK] <dining_room>', '[WALK] <soap>', '[FIND] <soap>', '[GRAB] <soap>', '[SCRUB] <soap>', '[FIND] <towel>', '[RINSE] <towel>'] } Scene_Objects:['filing_cabinet', 'chair', 'freezer', 'orchid', 'bedroom', 'clothes_jacket', 'mop_bucket', 'stovefan', 'mousepad', 'pillow', 'dining_room', 'nightstand', 'wall', 'powersocket', 'oven', 'basket_for_clothes', 'bed', 'photoframe', 'mouthwash', 'television', 'wine', 'after_shave', 'doorjamb', 'sink', 'bathroom_cabinet', 'light', 'dishwasher', 'soap', 'washing_machine', 'coffee'] Task:Wash clothes response: | { Walk to the kitchen and find the basket of clothes. Put the soap and clothes into the washing machine. Turn on the washing machine. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['filing_cabinet', 'chair', 'walllamp', 'orchid', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'food_bacon', 'brush', 'ceilinglamp', 'tvstand', 'mousepad', 'dining_room', 'wall', 'powersocket', 'bench', 'food_food', 'television', 'doorjamb', 'mouse', 'dresser', 'cupboard', 'bathroom_cabinet', 'table', 'light'] Task:Turn on computer response: { thoughts : Find the power button. Press., actions : ['[WALK] <home_office>', '[WALK] <chair>', '[PULL] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>'] } Scene_Objects:['filing_cabinet', 'juice', 'food_ice_cream', 'knifeblock', 'needle', 'cpuscreen', 'floor', 'ceiling', 'phone', 'character', 'desk', 'bookshelf', 'mop_bucket', 'toaster', 'laptop', 'faucet', 'food_jam', 'wall', 'powersocket', 'box', 'television', 'curtain', 'doorjamb', 'mouse', 'kitchen_counter', 'chessboard', 'door', 'bag', 'light', 'table'] Task:Turn on light response: | { approach the light switch, raise hand to the switch, flip 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:['sheets', 'scissors', 'mop', 'toilet', 'blow_dryer', 'detergent', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'keyboard', 'toaster', 'tvstand', 'shower', 'mousepad', 'pillow', 'wall', 'powersocket', 'oven', 'cup', 'photoframe', 'bed', 'food_onion', 'doorjamb', 'shaving_cream', 'mouse', 'kitchen_counter', 'bathroom_cabinet'] Task:Go to toilet response: { thoughts : I walk to bathroom, I open the door of the bathroom, and sit on the toilet., actions : ['[WALK] <bathroom>', '[WALK] <toilet>', '[FIND] <toilet>', '[SIT] <toilet>'] } Scene_Objects:['pot', 'tablelamp', 'microwave', 'walllamp', 'knifeblock', 'kitchen_cabinet', 'floor', 'ceiling', 'folder', 'character', 'desk', 'faucet', 'stereo', 'mousepad', 'food_orange', 'wall', 'oven', 'photoframe', 'oven_mitts', 'water', 'drinking_glass', 'wooden_spoon', 'towel_rack', 'shaving_cream', 'kitchen_counter', 'cupboard', 'food_steak', 'sink', 'spoon', 'board_game'] Task:Drink response: | { Go to kitchen, open cabinet, get glass, close cabinet, put glass under faucet, turn on water, turn off water when glass has 85% water, lift glass to mouth, open mouth and put on glass, tilt glass up and swallow 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:['filing_cabinet', 'tea', 'measuring_cup', 'band-aids', 'knifeblock', 'cpuscreen', 'dvd_player', 'folder', 'desk', 'bookmark', 'stereo', 'faucet', 'dustpan', 'microphone', 'oven', 'cup', 'bed', 'photoframe', 'check', 'coffe_maker', 'television', 'food_rice', 'pencil', 'shredder', 'controller', 'home_office', 'light', 'table', 'scrabble', 'electrical_outlet'] Task:Shred receipts response: { thoughts : Take old receipts and put through the shredder, actions : ['[WALK] <home_office>', '[WALK] <filing_cabinet>', '[FIND] <filing_cabinet>', '[OPEN] <filing_cabinet>', '[FIND] <check>', '[GRAB] <check>', '[CLOSE] <filing_cabinet>', '[FIND] <electrical_outlet>', '[FIND] <shredder>', '[PLUGIN] <shredder>', '[SWITCHON] <shredder>', '[PUTBACK] <check> <shredder>'] } Scene_Objects:['pot', 'ground_coffee', 'walllamp', 'floor', 'ceiling', 'phone', 'bedroom', 'keyboard', 'food_cake', 'toaster', 'window', 'couch', 'wall', 'cup', 'coffe_maker', 'food_food', 'coffee_filter', 'water', 'after_shave', 'towel_rack', 'mouse', 'shaving_cream', 'kitchen_counter', 'cupboard', 'bathtub', 'napkin', 'home_office', 'instrument_guitar', 'dishwasher', 'instrument_violin'] Task:Make coffee response: | { Walk to kitchen. Find coffee maker. Find coffee filter. Put it in the coffee maker. Find ground coffee. Put it in the coffee maker. Find Water. Put it in the coffe maker. Switch on the 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:['glue', 'food_bread', 'filing_cabinet', 'bathroom', 'ceiling', 'phone', 'keyboard', 'purse', 'bookshelf', 'laptop', 'ceilinglamp', 'faucet', 'nightstand', 'bench', 'photoframe', 'bed', 'clothes_gloves', 'food_food', 'coffe_maker', 'television', 'toothbrush_holder', 'curtain', 'shaving_cream', 'pencil', 'dresser', 'conditioner', 'door', 'spoon', 'bathroom_cabinet', 'table'] Task:Shut front door response: { thoughts : Close the storm door. Lock the storm door., actions : ['[WALK] <home_office>'] } Scene_Objects:['filing_cabinet', 'mop', 'chair', 'blow_dryer', 'orchid', 'cpuscreen', 'floor', 'phone', 'folder', 'desk', 'bookshelf', 'remote_control', 'computer', 'toaster', 'stovefan', 'mousepad', 'couch', 'pillow', 'wall', 'wall_clock', 'photoframe', 'novel', 'television', 'coin', 'coffee_filter', 'doorjamb', 'shoes', 'cupboard', 'sink', 'light'] Task:Watch TV response: | { I walk to the living room and sit on the couch. I grab the TV remote. I press the power button on the TV remote and the TV turns on. I grab the surround sound remote. I press the power button on the surround sound remote and the system turns on. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'milk', 'drawing', 'floor', 'ceiling', 'phone', 'keyboard', 'mat', 'tvstand', 'shower', 'oil', 'garbage_can', 'form', 'food_dessert', 'food_kiwi', 'wall', 'food_cheese', 'food_vegetable', 'doorjamb', 'centerpiece', 'towel_rack', 'kitchen_counter', 'cupboard', 'door', 'sink', 'bathroom_cabinet'] Task:Rotate stock in refrigerator response: { thoughts : Throw out expired items, put older items in front., actions : ['[WALK] <freezer>', '[OPEN] <freezer>', '[FIND] <food_bread>', '[GRAB] <food_bread>', '[TURNTO] <food_bread>', '[LOOKAT] <food_bread>', '[PUTOBJBACK] <food_bread>', '[FIND] <food_cheese>', '[GRAB] <food_cheese>', '[TURNTO] <food_cheese>', '[LOOKAT] <food_cheese>', '[FIND] <garbage_can>', '[PUTBACK] <food_cheese> <garbage_can>', '[FIND] <food_cheese>', '[GRAB] <food_cheese>', '[TURNTO] <food_cheese>', '[LOOKAT] <food_cheese>', '[PUTOBJBACK] <food_cheese>', '[FIND] <food_dessert>', '[TURNTO] <food_dessert>', '[LOOKAT] <food_dessert>', '[PUSH] <food_dessert>', '[FIND] <food_vegetable>', '[GRAB] <food_vegetable>', '[TURNTO] <food_vegetable>', '[LOOKAT] <food_vegetable>', '[PUTBACK] <food_vegetable> <garbage_can>', '[FIND] <milk>', '[GRAB] <milk>', '[TURNTO] <milk>', '[LOOKAT] <milk>', '[PUTOBJBACK] <milk>', '[CLOSE] <freezer>'] } Scene_Objects:['walllamp', 'detergent', 'orchid', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'wall', 'powersocket', 'photoframe', 'coffe_maker', 'television', 'coffee_filter', 'curtain', 'doorjamb', 'towel_rack', 'mouse', 'cupboard', 'sink', 'bathtub', 'light', 'soap'] Task:Watch TV response: | { I pick up remote. I turn on tv. I push on the remote. I 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:['food_salt', 'chair', 'ceilingfan', 'drawing', 'floor', 'ceiling', 'phone', 'remote_control', 'food_bacon', 'table_cloth', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'couch', 'wall', 'powersocket', 'oven', 'cup', 'bed', 'coffe_maker', 'television', 'curtain', 'lighter', 'doorjamb', 'shaving_cream', 'headset', 'cupboard', 'table', 'clothes_shirt'] Task:Watch TV response: { thoughts : We recently got a 43 inch TV and have enjoyed watching some of our favorite movies and TV shows. We use a remote to do so., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[TOUCH] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>', '[TURNTO] <television>', '[WATCH] <television>'] } Scene_Objects:['walllamp', 'drawing', 'orchid', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'purse', 'keyboard', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'deck_of_cards', 'couch', 'pillow', 'wall', 'powersocket', 'photoframe', 'bed', 'television', 'curtain', 'doorjamb', 'door', 'bathtub', 'table', 'light'] Task:Watch TV response: | { 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. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'juice', 'microwave', 'walllamp', 'trashcan', 'knifeblock', 'drawing', 'cpuscreen', 'knife', 'kitchen_cabinet', 'floor', 'ceiling', 'bookshelf', 'laptop', 'tvstand', 'faucet', 'electric_shaver', 'dining_room', 'wall', 'nightstand', 'oven', 'photoframe', 'novel', 'water', 'kitchen_counter', 'cupboard', 'hairdryer', 'sink', 'door'] Task:Drink response: { thoughts : Opening the kitchen cabinet to grab water glass and pour water from the faucet into it to drink., actions : ['[WALK] <dining_room>', '[WALK] <kitchen_cabinet>', '[FIND] <kitchen_cabinet>', '[OPEN] <kitchen_cabinet>', '[FIND] <water_glass>', '[GRAB] <water_glass>', '[CLOSE] <kitchen_cabinet>', '[FIND] <sink>', '[PUTBACK] <water_glass> <sink>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[SWITCHOFF] <faucet>', '[GRAB] <water_glass>', '[FIND] <water>', '[DRINK] <water_glass>'] } Scene_Objects:['trashcan', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'shampoo', 'tea_bag', 'keyboard', 'food_bacon', 'stovefan', 'tvstand', 'faucet', 'couch', 'microphone', 'pillow', 'wall', 'nightstand', 'powersocket', 'photoframe', 'television', 'oven_mitts', 'doorjamb', 'mouse', 'door', 'bathtub', 'sink', 'table', 'light', 'dishwasher'] Task:Relax on sofa response: | { Go to the living room. Find the sofa. Sit on the sofa. Close your eyes. Breath calmly. 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:['pot', 'food_pizza', 'tablelamp', 'mop', 'freezer', 'blow_dryer', 'bathroom', 'detergent', 'milk', 'bathroom_counter', 'ceiling', 'character', 'mop_bucket', 'stovefan', 'shoe-shine_kit', 'balanceball', 'deck_of_cards', 'stereo', 'shower', 'mousepad', 'microphone', 'pillow', 'light_bulb', 'coffee_filter', 'doorjamb', 'towel_rack', 'pencil', 'cupboard', 'light', 'dishwasher'] Task:Browse internet response: { thoughts : The task is browse and surf on the internet regarding a particular topic, actions : ['[WALK] <bedroom>', '[WALK] <laptop>', '[FIND] <laptop>', '[SWITCHON] <laptop>', '[TURNTO] <laptop>', '[LOOKAT] <laptop>', '[WATCH] <laptop>'] } Scene_Objects:['dry_pasta', 'filing_cabinet', 'tablelamp', 'tea', 'microwave', 'chair', 'drawing', 'orchid', 'floor', 'computer', 'food_bacon', 'table_cloth', 'stovefan', 'toaster', 'homework', 'mousepad', 'couch', 'powersocket', 'oven', 'bench', 'check', 'oven_mitts', 'coffee_filter', 'curtain', 'rag', 'doorjamb', 'kitchen_counter', 'shoes', 'bathtub', 'dishwasher'] Task:Pet cat response: | { I walk into the living room and I pet the cat } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'spectacles', 'sponge', 'beer', 'chair', 'freezer', 'detergent', 'food_butter', 'cpuscreen', 'hanger', 'bedroom', 'desk', 'bookshelf', 'table_cloth', 'toaster', 'ceilinglamp', 'shower', 'iron', 'window', 'wall', 'oven', 'food_food', 'razor', 'food_rice', 'curtain', 'kitchen_counter', 'food_steak', 'door', 'spoon', 'bathroom_cabinet'] Task:Listen to music response: { thoughts : I pull up my online classes on the computer to look at what the assigned reading is. I get my textbook, notebook, and mechanical pencil. As I'm reading, I take notes over important points. I then use those notes to complete the assignment for the week. Frequently that involves writing a post on an online discussion board that answers a question related to things from the reading., actions : ['[WALK] <home_office>', '[WALK] <stereo>', '[FIND] <stereo>', '[SWITCHON] <stereo>'] } Scene_Objects:['spectacles', 'filing_cabinet', 'microwave', 'chair', 'bathroom', 'food_butter', 'drawing', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'shower', 'foundation', 'couch', 'pillow', 'wall', 'nightstand', 'powersocket', 'box', 'newspaper', 'coffe_maker', 'food_onion', 'doorjamb', 'mouse', 'controller', 'door', 'bathtub', 'table', 'light', 'scrabble'] Task:Relax on sofa response: | { Walk to the living room, find the sofa and sit in the sofa and find pillow. lie down in 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', 'beer', 'microwave', 'toilet', 'walllamp', 'bathroom', 'trashcan', 'dough', 'orchid', 'dvd_player', 'keyboard', 'piano_bench', 'brush', 'faucet', 'pillow', 'dining_room', 'powersocket', 'newspaper', 'coffe_maker', 'television', 'wine', 'curtain', 'doorjamb', 'towel_rack', 'kitchen_counter', 'conditioner', 'clothes_scarf', 'bathtub', 'bathroom_cabinet', 'creditcard'] Task:Lock door response: { thoughts : Turn the lock., actions : ['[WALK] <bedroom>'] } Scene_Objects:['pot', 'scissors', 'crayon', 'chair', 'walllamp', 'knifeblock', 'bills', 'wallshelf', 'bathroom_counter', 'phone', 'ceiling', 'bedroom', 'computer', 'stovefan', 'ceilinglamp', 'tvstand', 'window', 'couch', 'food_peanut_butter', 'dining_room', 'nightstand', 'oven', 'television', 'tray', 'curtain', 'towel_rack', 'door', 'bathtub', 'napkin', 'bag'] Task:Read book response: | { walk to living room ,find a book ,open the book ,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:['sheets', 'filing_cabinet', 'beer', 'jelly', 'bathroom', 'ceilingfan', 'drawing', 'floor', 'ceiling', 'keyboard', 'clothes_jacket', 'table_cloth', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'homework', 'food_noodles', 'couch', 'wall', 'oven', 'basket_for_clothes', 'cup', 'television', 'curtain', 'conditioner', 'maindoor', 'table', 'vase'] Task:Watch TV response: { thoughts : Walk into the living room. Sit on the couch. Turn on TV., actions : ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>'] } Scene_Objects:['fork', 'filing_cabinet', 'chair', 'trashcan', 'drawing', 'clothes_underwear', 'floor', 'phone', 'character', 'keyboard', 'mat', 'ceilinglamp', 'plate', 'tvstand', 'shower', 'faucet', 'mousepad', 'couch', 'wall', 'bench', 'powersocket', 'newspaper', 'bed', 'television', 'mouse', 'controller', 'table', 'light', 'instrument_violin', 'creditcard'] Task:Set up table response: | { I walk to the table. I put down the dish. I put down the silverware. I put down the napkin. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'stovefan', 'ceilinglamp', 'tvstand', 'shower', 'window', 'mousepad', 'wall', 'nightstand', 'powersocket', 'bench', 'photoframe', 'television', 'tray', 'curtain', 'doorjamb', 'mouse', 'cd', 'sink', 'bathtub', 'table', 'dirt'] Task:Write an email response: { thoughts : I go to my office and sit at my desk. Turn on the computer and type my email at the keyboard., actions : ['[WALK] <home_office>', '[WALK] <desk>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <keyboard>', '[TYPE] <keyboard>'] } Scene_Objects:['filing_cabinet', 'microwave', 'chair', 'walllamp', 'nail_polish', 'knifeblock', 'drawing', 'cpuscreen', 'wallshelf', 'bathroom_counter', 'desk', 'cleaning_solution', 'bookshelf', 'stovefan', 'mat', 'tvstand', 'shower', 'faucet', 'ceilinglamp', 'pillow', 'bench', 'cup', 'mouse', 'controller', 'laundry_detergent', 'door', 'napkin', 'light', 'dirt', 'hands_both'] Task:Wash hands response: | { walk to bathroom , find cleaning solution , squeeze cleaning solution , wash 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:['sponge', 'glue', 'toilet', 'chair', 'detergent', 'dough', 'drawing', 'orchid', 'hanger', 'floor', 'ceiling', 'keyboard', 'alcohol', 'stovefan', 'ceilinglamp', 'couch', 'microphone', 'wall', 'nightstand', 'photoframe', 'coffe_maker', 'coffee_filter', 'doorjamb', 'kitchen_counter', 'hairbrush', 'cupboard', 'home_office', 'dishwasher', 'coffee', 'shoe_rack'] Task:Make coffee response: { thoughts : Open coffee maker. Put filter in main basket, put ground coffee in filter, fill reservoir with water, turn on coffee maker., actions : ['[WALK] <dining_room>', '[WALK] <coffe_maker>', '[FIND] <coffe_maker>', '[OPEN] <coffe_maker>', '[FIND] <coffee_filter>', '[GRAB] <coffee_filter>', '[PUTBACK] <coffee_filter> <coffe_maker>', '[FIND] <coffee>', '[GRAB] <coffee>', '[PUTBACK] <coffee> <coffe_maker>'] } Scene_Objects:['pot', 'tablelamp', 'crayon', 'microwave', 'dog', 'band-aids', 'walllamp', 'trashcan', 'knifeblock', 'orchid', 'floor', 'desk', 'bookshelf', 'computer', 'piano_bench', 'plate', 'faucet', 'dish_soap', 'food_jam', 'form', 'wall', 'photoframe', 'doorjamb', 'kettle', 'kitchen_counter', 'dishrack', 'cupboard', 'pajamas', 'sink', 'table'] Task:Wash dishes by hand response: | { Walk to the kitchen and turn to the sink. Put the plate into the sink. Grab and squeeze the dish soap. Scrub the plate then rinse it. Put the plate into the dish rack. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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:['glue', 'crayon', 'chair', 'freezer', 'walllamp', 'bathroom', 'orchid', 'cpuscreen', 'ceiling', 'character', 'bedroom', 'mat', 'faucet', 'window', 'mousepad', 'couch', 'candle', 'pillow', 'bench', 'oven', 'coffe_maker', 'rag', 'towel_rack', 'dresser', 'pajamas', 'cupboard', 'bathtub', 'napkin', 'home_office', 'dishwasher'] Task:Pet cat response: | { You walk to the living room and find the cat. You look at the cat and touch it to pet 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', 'tablelamp', 'chair', 'freezer', 'drawing', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'food_bacon', 'stovefan', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'closetdrawer', 'wall', 'nightstand', 'photoframe', 'novel', 'television', 'mouse', 'kitchen_counter', 'door', 'sink', 'clothes_skirt', 'clothes_shirt'] Task:Read book response: { thoughts : Go to home office, find the book. Sit in the chair and read the book., actions : ['[WALK] <home_office>', '[WALK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <chair>', '[SIT] <chair>', '[READ] <novel>'] } Scene_Objects:['pot', 'filing_cabinet', 'tablelamp', 'walllamp', 'drawing', 'floor', 'ceiling', 'phone', 'bedroom', 'bookmark', 'mat', 'shoe-shine_kit', 'tvstand', 'window', 'couch', 'pillow', 'towel', 'wall', 'nightstand', 'powersocket', 'bed', 'novel', 'coffe_maker', 'mouthwash', 'tray', 'doorjamb', 'controller', 'door', 'light', 'creditcard'] Task:Read book response: | { I go to the bedroom and turn on the light. I lie in bed. I grab my book from the nightstand, and look for the bookmark to check where I last left off. I read for a while. When I'm done, I put the bookmark on the page I stop at and place the book back on the nightstand. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'walllamp', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'shampoo', 'bedroom', 'mop_bucket', 'faucet', 'balanceball', 'towel', 'wall', 'photoframe', 'keys', 'novel', 'razor', 'television', 'diary', 'kettle', 'coffee_pot', 'cd', 'sink', 'bathroom_cabinet', 'home_office', 'soap', 'hands_both', 'shoe_rack'] Task:Wash hands response: { thoughts : I go to the bathroom and locate the sink. I turn the faucet so that water is running, and rinse my hands briefly. Then I grab the soap and squeeze some onto my hands. I spend a few minutes rubbing my hands together, then I rinse them again. Finally, I turn the faucet off and wipe my hands on a towel., actions : ['[WALK] <bathroom>', '[WALK] <sink>', '[FIND] <sink>', '[TURNTO] <sink>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <hands_both>', '[RINSE] <hands_both>', '[FIND] <soap>', '[GRAB] <soap>', '[SQUEEZE] <soap>', '[WASH] <hands_both>', '[RINSE] <hands_both>', '[SWITCHOFF] <faucet>', '[FIND] <towel>', '[GRAB] <towel>', '[WIPE] <hands_both>'] } Scene_Objects:['sponge', 'pot', 'glue', 'tablelamp', 'microwave', 'toilet', 'walllamp', 'knifeblock', 'floor', 'ceiling', 'phone', 'food_cake', 'table_cloth', 'plate', 'faucet', 'stereo', 'dish_soap', 'towel', 'bowl', 'wall', 'nightstand', 'oven', 'coffe_maker', 'food_food', 'centerpiece', 'kitchen_counter', 'dishrack', 'cupboard', 'sink', 'spoon'] Task:Wash dishes by hand response: | { I enter the kitchen, walk to the sink, turn on the faucet, grab the sponge and get it wet, then apply dish soap to the sponge. I take a dish, scrub it with the sponge, rinse it, and place it on the dish rack to dry, and repeat until all the dishes are clean. I rinse the sponge, put it down, and turn off the faucet. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['ceilingfan', 'drawing', 'knifeblock', 'floor', 'ceiling', 'remote_control', 'computer', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'faucet', 'window', 'couch', 'wall', 'powersocket', 'oven', 'coffe_maker', 'television', 'coffee_filter', 'food_rice', 'tray', 'curtain', 'pencil', 'kitchen_counter', 'cupboard', 'sink', 'napkin', 'table', 'dirt'] Task:Watch TV response: { thoughts : I like to set on my sofa.Turn on the tv. And watch Perry Mason. Monday's through Friday's., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <remote_control>', '[GRAB] <remote_control>'] } 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: | { 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. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'crayon', 'microwave', 'walllamp', 'knifeblock', 'floor', 'ceiling', 'character', 'bedroom', 'bookshelf', 'purse', 'toaster', 'faucet', 'shower', 'homework', 'pillow', 'wall', 'oven', 'water', 'doorjamb', 'mouse', 'kitchen_counter', 'cupboard', 'sink', 'bathtub', 'bathroom_cabinet', 'home_office', 'soap', 'teeth'] Task:Wash hands response: { thoughts : walk to kitchen, turn on water, find soap, apply to hand, lather, rinse, dry hands, actions : ['[WALK] <dining_room>', '[WALK] <sink>', '[FIND] <sink>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <soap>', '[GRAB] <soap>', '[SCRUB] <soap>', '[PUTOBJBACK] <soap>', '[FIND] <water>', '[RINSE] <water>'] } Scene_Objects:['dry_pasta', 'spectacles', 'filing_cabinet', 'mop', 'toilet', 'detergent', 'trashcan', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'phone', 'desk', 'computer', 'toaster', 'ceilinglamp', 'mat', 'couch', 'clothes_pants', 'pillow', 'food_food', 'television', 'doorjamb', 'towel_rack', 'kitchen_counter', 'hairbrush', 'hairdryer', 'bathtub', 'dishwasher', 'dirt'] Task:Pick up phone response: | { Walk to the living room, Find Phone stand. Find Phone. Pickup the receiver to attend the call. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'water_glass', '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: { thoughts : I go to the kitchen, take a glass from the cupboard, fill with water and drink, actions : ['[WALK] <dining_room>', '[WALK] <cupboard>', '[FIND] <cupboard>', '[OPEN] <cupboard>', '[FIND] <water_glass>', '[GRAB] <water_glass>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <water_glass>', '[DRINK] <water_glass>', '[RINSE] <water_glass>', '[PUTBACK] <water_glass> <cupboard>'] } Scene_Objects:['walllamp', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'computer', 'button', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'photoframe', 'bed', 'television', 'curtain', 'doorjamb', 'towel_rack', 'cd', 'door', 'table', 'light', 'clothes_shirt'] Task:Change TV channel response: | { Pickup remote control for the living room TV and push the change channel 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:['sheets', 'pot', 'chair', 'freezer', 'detergent', 'trashcan', 'dough', 'clothes_underwear', 'folder', 'stamp', 'bookshelf', 'clothes_jacket', 'table_cloth', 'mousepad', 'couch', 'food_jam', 'clothes_hat', 'pillow', 'nightstand', 'bench', 'oven', 'cutting_board', 'bed', 'food_food', 'check', 'doorjamb', 'console', 'cupboard', 'home_office', 'table'] Task:Pick up phone response: { thoughts : i go find the phone. i pick up the phone, actions : ['[WALK] <home_office>', '[WALK] <phone>', '[FIND] <phone>', '[GRAB] <phone>'] } Scene_Objects:['food_bread', 'drawing', 'orchid', 'knifeblock', 'bills', 'floor', 'ceiling', 'desk', 'bedroom', 'keyboard', 'shower', 'stereo', 'mousepad', 'couch', 'pillow', 'wall', 'oven', 'photoframe', 'television', 'food_rice', 'tray', 'curtain', 'doorjamb', 'pencil', 'kitchen_counter', 'door', 'home_office', 'table', 'light', 'bathroom_cabinet'] Task:Relax on sofa response: | { Walk into the living room. Walk up to the sofa. Sit down 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:['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: { thoughts : walk into living room, look at the sofa which one is available, sit on the sofa, now take relax on the sofa, actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[TURNTO] <couch>', '[LOOKAT] <couch>', '[SIT] <couch>'] } Scene_Objects:['bathroom', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'character', 'bookshelf', 'piano_bench', 'stovefan', 'ceilinglamp', 'faucet', 'electric_shaver', 'window', 'teeth', 'food_orange', 'pillow', 'wall', 'powersocket', 'food_food', 'tray', 'curtain', 'dresser', 'hair', 'controller', 'sink', 'bathroom_cabinet', 'soap', 'hands_both'] Task:Wash hands response: | { I walk in to the bathroom. I find the soap. I find the faucet. I turn on the faucet. I wash my hands. I put the soap back. I rinse my hands. I turn the faucet off. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'juice', 'measuring_cup', 'microwave', 'chair', 'freezer', 'band-aids', 'walllamp', 'detergent', 'knifeblock', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'mop_bucket', 'toaster', 'stovefan', 'faucet', 'couch', 'wall', 'oven', 'cup', 'tray', 'food_onion', 'kitchen_counter', 'cupboard', 'food_snack', 'sink', 'napkin', 'home_office'] Task:Have snack response: { thoughts : Pour soda into a glass. Get pretzels out of bag. Eat and drink, actions : ['[WALK] <dining_room>', '[WALK] <cup>', '[FIND] <cup>', '[GRAB] <cup>', '[WALK] <freezer>', '[OPEN] <freezer>', '[FIND] <juice>', '[GRAB] <juice>', '[POUR] <juice> <cup>', '[PUTIN] <juice> <freezer>', '[CLOSE] <freezer>', '[WALK] <cupboard>', '[OPEN] <cupboard>', '[FIND] <food_snack>', '[GRAB] <food_snack>', '[CLOSE] <cupboard>', '[DRINK] <cup>', '[EAT] <food_snack>'] } Scene_Objects:['pot', 'filing_cabinet', 'crayon', 'microwave', 'walllamp', 'knifeblock', 'floor', 'ceiling', 'character', 'bedroom', 'bookshelf', 'purse', 'toaster', 'faucet', 'shower', 'homework', 'pillow', 'wall', 'oven', 'water', 'doorjamb', 'mouse', 'kitchen_counter', 'cupboard', 'sink', 'bathtub', 'bathroom_cabinet', 'home_office', 'soap', 'teeth'] Task:Wash hands response: | { walk to kitchen, turn on water, find soap, apply to hand, lather, rinse, dry 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:['chair', 'walllamp', 'bathroom', 'orchid', 'wallshelf', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'computer', 'button', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'faucet', 'mousepad', 'dining_room', 'wall', 'powersocket', 'photoframe', 'television', 'curtain', 'rag', 'doorjamb', 'kitchen_counter', 'light', 'table'] Task:Change TV channel response: { thoughts : walk to living room, look at the television, switch on the television, grab the remote control, press the channel button in remote control, now the tv channel is changed, actions : ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[TURNTO] <television>', '[LOOKAT] <television>', '[SWITCHON] <television>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <button>', '[GRAB] <button>'] } Scene_Objects:['microwave', 'walllamp', 'ground_coffee', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'phone', 'bookshelf', 'remote_control', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'oven', 'photoframe', 'television', 'curtain', 'doorjamb', 'towel_rack', 'pencil', 'door', 'table', 'light'] Task:Watch TV response: | { walk to living room, find couch, sit on couch, find remote control , turn on tv by pressing 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', 'tablelamp', 'food_ice_cream', 'toothbrush', 'drawing', 'cpuscreen', 'hanger', 'bathroom_counter', 'purse', 'faucet', 'window', 'towel', 'wall', 'toy', 'bed', 'light_bulb', 'novel', 'coffe_maker', 'television', 'water', 'tray', 'curtain', 'towel_rack', 'kitchen_counter', 'dresser', 'maindoor', 'sink', 'tooth_paste', 'clothes_shirt', 'teeth'] Task:Wash teeth response: { thoughts : Walk to bathroom. Find tooth paste, tooth brush and water. Squeeze tooth paste on tooth brush. Wash teeth., actions : ['[WALK] <bathroom>', '[WALK] <tooth_paste>', '[FIND] <tooth_paste>', '[FIND] <toothbrush>', '[FIND] <water>', '[SQUEEZE] <tooth_paste>', '[FIND] <teeth>', '[WASH] <teeth>'] } Scene_Objects:['pot', 'filing_cabinet', 'tablelamp', 'toilet', 'chair', 'freezer', 'walllamp', 'food_carrot', 'drawing', 'orchid', 'floor', 'ceiling', 'character', 'desk', 'bedroom', 'keyboard', 'toaster', 'shower', 'wall', 'novel', 'food_food', 'television', 'oven_mitts', 'tray', 'kitchen_counter', 'headset', 'dresser', 'cupboard', 'hair', 'bathtub'] Task:Put groceries in Fridge response: | { Go to kitchen, open fridge, get groceries, put groceries in fridge, close 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:['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:['tea', 'walllamp', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'phone', 'bookshelf', 'remote_control', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'form', 'pillow', 'wall', 'powersocket', 'photoframe', 'bed', 'television', 'curtain', 'doorjamb', 'cupboard', 'door', 'table', 'light'] Task:Watch TV response: | { Walk to livingroom, sit on couch, grab remote and turn 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:['pot', 'tablelamp', 'chair', 'freezer', 'drawing', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'food_bacon', 'stovefan', 'mat', 'ceilinglamp', 'tvstand', 'mousepad', 'closetdrawer', 'wall', 'nightstand', 'photoframe', 'novel', 'television', 'mouse', 'kitchen_counter', 'door', 'sink', 'clothes_skirt', 'clothes_shirt'] Task:Read book response: { thoughts : Go to home office, find the book. Sit in the chair and read the book., actions : ['[WALK] <home_office>', '[WALK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <chair>', '[SIT] <chair>', '[READ] <novel>'] } Scene_Objects:['fork', 'water_glass', 'pot', 'walllamp', 'bathroom', 'milk', 'knife', 'knifeblock', 'drawing', 'floor', 'ceiling', 'bedroom', 'toaster', 'stovefan', 'plate', 'shower', 'faucet', 'dish_soap', 'wall', 'oven', 'coffe_maker', 'tray', 'curtain', 'kitchen_counter', 'cupboard', 'sink', 'spoon', 'coffee_cup', 'dishwasher', 'table'] Task:Wash dishes with dishwasher response: | { I go to the kitchen and put plates, cutlery and glasses into the dishwasher, put the soap, close the machine and switch it 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:['drawing', 'hanger', 'floor', 'ceiling', 'computer', 'brush', 'mat', 'ceilinglamp', 'faucet', 'stovefan', 'window', 'mousepad', 'closetdrawer', 'couch', 'pillow', 'dining_room', 'wall', 'cutting_board', 'shelf', 'toy', 'standingmirror', 'television', 'curtain', 'doorjamb', 'towel_rack', 'controller', 'home_office', 'table', 'soap', 'shoe_rack'] Task:Turn off TV response: { thoughts : Walk over to tv and press power button, actions : ['[WALK] <home_office>', '[WALK] <television>', '[SWITCHOFF] <television>'] } Scene_Objects:['band-aids', 'walllamp', 'orchid', 'wallshelf', 'cpuscreen', 'floor', 'ceiling', 'phone', 'bookshelf', 'remote_control', 'button', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'clothes_pants', 'dining_room', 'wall', 'powersocket', 'photoframe', 'coffee_table', 'bed', 'clothes_gloves', 'television', 'curtain', 'doorjamb', 'bathtub', 'light'] Task:Change TV channel response: | { Go to the living room, find the remote control on the coffee table, and 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:['fork', 'dry_pasta', 'filing_cabinet', 'scissors', 'kitchen_cabinet', 'envelope', 'faucet', 'dish_soap', 'mousepad', 'couch', 'pillow', 'dining_room', 'wall_clock', 'bench', 'toy', 'cutting_board', 'razor', 'food_onion', 'doorjamb', 'towel_rack', 'kitchen_counter', 'pajamas', 'clothes_dress', 'bathtub', 'sink', 'bathroom_cabinet', 'table', 'dishwasher', 'vase', 'light'] Task:Wash dishes with dishwasher response: { thoughts : I walk to the kitchen. I open the dishwasher. I open the kitchen cabinet. I reach inside the cabinet and grab the box of dish soap. I add some soap to the open dishwasher. I put the box of dish soap back in the kitchen cabinet. I close the kitchen cabinet and then I close the dishwasher. I turn the dishwasher on and wait., actions : ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[FIND] <kitchen_cabinet>', '[OPEN] <kitchen_cabinet>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[PUTBACK] <dish_soap> <dishwasher>', '[GRAB] <dish_soap>', '[PUTIN] <dish_soap> <kitchen_cabinet>', '[CLOSE] <kitchen_cabinet>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>'] } Scene_Objects:['filing_cabinet', 'crayon', 'microwave', 'detergent', 'drawing', 'orchid', 'bathroom_counter', 'floor', 'ceiling', 'computer', 'alcohol', 'toaster', 'shower', 'couch', 'clothes_hat', 'pillow', 'wall', 'pasta', 'bench', 'oven', 'photoframe', 'newspaper', 'coffe_maker', 'tray', 'doorjamb', 'hairbrush', 'cupboard', 'door', 'table', 'light'] Task:Relax on sofa response: | { Walk to the living room. Find the sofa. Walk to the sofa. Lie 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:['pot', 'water_glass', 'microwave', 'toilet', 'chair', 'freezer', 'bathroom', 'wallshelf', 'bookshelf', 'clothes_jacket', 'toaster', 'ceilinglamp', 'faucet', 'window', 'closetdrawer', 'dining_room', 'nightstand', 'wall', 'wall_clock', 'powersocket', 'basket_for_clothes', 'novel', 'coffe_maker', 'tray', 'doorjamb', 'console', 'dishrack', 'hairdryer', 'door', 'bathtub'] Task:Drink response: { thoughts : Drink water, actions : ['[WALK] <dining_room>', '[WALK] <water_glass>', '[FIND] <water_glass>', '[GRAB] <water_glass>', '[DRINK] <water_glass>'] } Scene_Objects:['walllamp', 'orchid', 'drawing', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'bookshelf', 'remote_control', 'envelope', 'clothes_jacket', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'bench', 'photoframe', 'bed', 'television', 'curtain', 'doorjamb', 'door', 'light', 'table'] Task:Watch TV response: | { Enter the living room, find TV remote, grab TV remote, switch on TV, find sofa, sit down on the sofa, watch 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:['chair', 'bathroom', 'orchid', 'wallshelf', 'ceiling', 'phone', 'stamp', 'bookshelf', 'mail', 'computer', 'tvstand', 'shower', 'couch', 'pillow', 'oven', 'powersocket', 'box', 'bed', 'clothes_gloves', 'photoframe', 'check', 'curtain', 'pencil', 'dresser', 'cupboard', 'door', 'sink', 'bathtub', 'home_office', 'dishwasher'] Task:Pet cat response: { thoughts : find a cat, touch it gently, actions : ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[TOUCH] <cat>'] } Scene_Objects:['water_glass', 'filing_cabinet', 'jelly', 'freezer', 'walllamp', 'knifeblock', 'orchid', 'wallshelf', 'bathroom_counter', 'ceiling', 'bookshelf', 'toaster', 'ceilinglamp', 'faucet', 'shower', 'window', 'clothes_hat', 'nightstand', 'wall', 'bench', 'coffe_maker', 'tray', 'curtain', 'doorjamb', 'mouse', 'cupboard', 'napkin', 'bathroom_cabinet', 'clothes_skirt', 'instrument_violin'] Task:Drink response: | { Drink 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:['tablelamp', 'blender', 'chair', 'bathroom', 'detergent', 'drawing', 'cpuscreen', 'floor', 'phone', 'desk', 'mat', 'tvstand', 'clothes_pants', 'wall', 'nightstand', 'powersocket', 'photoframe', 'bed', 'novel', 'check', 'keys', 'tray', 'after_shave', 'curtain', 'doorjamb', 'kitchen_counter', 'cupboard', 'door', 'bathtub', 'tooth_paste'] Task:Read response: { thoughts : I like to read books in my bedroom., actions : ['[WALK] <bedroom>', '[WALK] <desk>', '[FIND] <novel>', '[GRAB] <novel>', '[WALK] <bed>', '[LIE] <bed>', '[READ] <novel>'] } Scene_Objects:['sheets', 'pot', 'walllamp', 'bathroom', 'orchid', 'wallshelf', 'floor', 'ceiling', 'phone', 'desk', 'bookshelf', 'remote_control', 'keyboard', 'table_cloth', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'faucet', 'wall', 'powersocket', 'bench', 'photoframe', 'television', 'curtain', 'doorjamb', 'kitchen_counter', 'light', 'dishwasher'] Task:Watch TV response: | { I grab the remote. I find the red power circular button. I point the remote at the television. I push button down and TV screen lights up. I sit and 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:['food_ice_cream', 'microwave', 'toilet', 'chair', 'bathroom_counter', 'floor', 'laptop', 'faucet', 'shower', 'towel', 'wall', 'wall_clock', 'nightstand', 'cup', 'bed', 'photoframe', 'water', 'tray', 'doorjamb', 'towel_rack', 'dresser', 'door', 'sink', 'bathtub', 'bathroom_cabinet', 'light', 'table', 'soap', 'scrabble', 'hands_both'] Task:Wash hands response: { thoughts : Go into the bathroom and go over to the sink. Grab soap and turn on the water. Wet your hands and rub them together so that the soap lathers. Rub the soap all over your hands thoroughly. Rinse off the soap with water and turn off the sink. Dry your hands with a towel., actions : ['[WALK] <bathroom>', '[WALK] <sink>', '[FIND] <soap>', '[GRAB] <soap>', '[FIND] <water>', '[GRAB] <water>', '[FIND] <hands_both>', '[POUR] <water> <hands_both>', '[FIND] <hands_both>', '[SCRUB] <hands_both>', '[PUTOBJBACK] <soap>', '[RINSE] <hands_both>', '[FIND] <towel>', '[GRAB] <towel>', '[WIPE] <hands_both>'] } 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: | { walk to living room ,find television , switch on remote control } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'tablelamp', 'chair', 'band-aids', 'walllamp', 'detergent', 'orchid', 'drawing', 'floor', 'ceiling', 'phone', 'video_game_console', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'plate', 'window', 'closetdrawer', 'couch', 'pillow', 'nightstand', 'wall', 'photoframe', 'video_game_controller', 'television', 'curtain', 'dresser', 'table', 'dishwasher'] Task:Play games response: { thoughts : Turn on game. Use controller, actions : ['[WALK] <home_office>', '[WALK] <television>', '[PLUGIN] <television>', '[SWITCHON] <television>', '[FIND] <video_game_console>', '[PLUGIN] <video_game_console>', '[SWITCHON] <video_game_console>', '[FIND] <video_game_console>', '[FIND] <video_game_controller>', '[GRAB] <video_game_controller>', '[WALK] <couch>', '[SIT] <couch>'] } Scene_Objects:['filing_cabinet', 'cd_player', 'blow_dryer', 'bathroom', 'detergent', 'orchid', 'bills', 'bathroom_counter', 'phone', 'bedroom', 'remote_control', 'thread', 'button', 'mat', 'ceilinglamp', 'couch', 'pillow', 'dining_room', 'broom', 'wall_clock', 'powersocket', 'bench', 'box', 'coffe_maker', 'razor', 'towel_rack', 'vacuum_cleaner', 'bathtub', 'dishwasher', 'soap'] Task:Listen to music response: | { I walk to my living room. Find CD player. Plugin the CD player to Power. Also find the remote control. Push the Botton } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'blender', 'knifeblock', 'needle', 'bills', 'drawing', 'phone', 'mat', 'deck_of_cards', 'shoe-shine_kit', 'ceilinglamp', 'electric_shaver', 'window', 'clothes_socks', 'couch', 'dining_room', 'nightstand', 'wall', 'bench', 'cup', 'bed', 'mouthwash', 'coffee_filter', 'rag', 'towel_rack', 'hairbrush', 'dresser', 'clothes_dress', 'bathroom_cabinet', 'laser_pointer'] Task:Pick up phone response: { thoughts : walk to phone, grab phone, pick up phone, put to ear, actions : ['[WALK] <home_office>', '[WALK] <phone>', '[FIND] <phone>', '[GRAB] <phone>'] } Scene_Objects:['filing_cabinet', 'detergent', 'trashcan', 'drawing', 'food_egg', 'ceiling', 'keyboard', 'stovefan', 'mat', 'ceilinglamp', 'toaster', 'window', 'mousepad', 'couch', 'dining_room', 'oven', 'light_bulb', 'check', 'coffe_maker', 'food_food', 'tray', 'doorjamb', 'mouse', 'cupboard', 'door', 'bathtub', 'table', 'dishwasher', 'clothes_skirt', 'creditcard'] Task:Pick up phone response: | { Walk into the living room, walk over to phone, grab the phone, put it to your 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:['food_pizza', 'tea', 'microwave', 'walllamp', 'bathroom', 'trashcan', 'orchid', 'floor', 'phone', 'keyboard', 'food_cake', 'toaster', 'stovefan', 'plate', 'mat', 'dish_soap', 'oil', 'pillow', 'wall', 'cup', 'photoframe', 'coffe_maker', 'curtain', 'centerpiece', 'mouse', 'kitchen_counter', 'comb', 'cupboard', 'bathroom_cabinet', '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:['filing_cabinet', 'tablelamp', 'microwave', 'toilet', 'chair', 'bathroom', 'detergent', 'trashcan', 'toothbrush', 'knifeblock', 'bathroom_counter', 'character', 'keyboard', 'computer', 'food_bacon', 'tvstand', 'nightstand', 'oven', 'bench', 'powersocket', 'cup', 'bed', 'ice', 'diary', 'cards', 'dresser', 'hairbrush', 'home_office', 'dishwasher', 'scrabble'] Task:Listen to music response: | { go to radio. run on 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:['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:['filing_cabinet', 'walllamp', 'orchid', 'drawing', 'wallshelf', 'floor', 'ceiling', 'desk', 'bookshelf', 'remote_control', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'laptop', 'mousepad', 'couch', 'pillow', 'wall', 'powersocket', 'photoframe', 'video_game_controller', 'television', 'curtain', 'doorjamb', 'door', 'light', 'table'] Task:Watch TV response: | { Watching 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:['blender', 'toilet', 'freezer', 'walllamp', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'ceilinglamp', 'shoe-shine_kit', 'shower', 'faucet', 'mat', 'oil', 'food_peanut_butter', 'towel', 'wall', 'nightstand', 'powersocket', 'photoframe', 'bed', 'toilet_paper', 'curtain', 'doorjamb', 'kitchen_counter', 'door', 'sink', 'bathroom_cabinet', 'light', 'colander'] Task:Take shower response: { thoughts : Walk to Bathroom. Open the Bathroom Cabinet. Grab a Towel. Close the Bathroom Cabinet. Rinse the Shower., actions : ['[WALK] <bathroom>', '[WALK] <bathroom_cabinet>', '[FIND] <bathroom_cabinet>', '[OPEN] <bathroom_cabinet>', '[FIND] <towel>', '[GRAB] <towel>', '[CLOSE] <bathroom_cabinet>', '[FIND] <shower>', '[RINSE] <shower>'] } Scene_Objects:['glue', 'tablelamp', 'microwave', 'freezer', 'drawing', 'phone', 'bookshelf', 'toaster', 'stovefan', 'tvstand', 'mousepad', 'couch', 'clothes_hat', 'food_orange', 'wall', 'photoframe', 'clothes_gloves', 'bed', 'check', 'television', 'food_rice', 'tray', 'doorjamb', 'dresser', 'hairdryer', 'sink', 'bathtub', 'bathroom_cabinet', 'light', 'door'] Task:Listen to music response: | { I go to my bedroom, and then I switch on 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:['food_bread', 'beer', 'toilet', 'chair', 'freezer', 'food_butter', 'food_carrot', 'milk', 'drawing', 'floor', 'ceiling', 'toaster', 'mat', 'shower', 'mousepad', 'garbage_can', 'food_dessert', 'wall', 'nightstand', 'powersocket', 'oven', 'food_vegetable', 'food_cheese', 'photoframe', 'food_food', 'food_onion', 'doorjamb', 'laundry_detergent', 'door', 'light'] Task:Rotate stock in refrigerator response: { thoughts : Throw out expired items, put older items in front., actions : ['[WALK] <freezer>', '[OPEN] <freezer>', '[FIND] <food_bread>', '[GRAB] <food_bread>', '[TURNTO] <food_bread>', '[LOOKAT] <food_bread>', '[PUTOBJBACK] <food_bread>', '[FIND] <food_cheese>', '[GRAB] <food_cheese>', '[TURNTO] <food_cheese>', '[LOOKAT] <food_cheese>', '[FIND] <garbage_can>', '[PUTBACK] <food_cheese> <garbage_can>', '[FIND] <food_cheese>', '[GRAB] <food_cheese>', '[TURNTO] <food_cheese>', '[LOOKAT] <food_cheese>', '[PUTOBJBACK] <food_cheese>', '[FIND] <food_dessert>', '[TURNTO] <food_dessert>', '[LOOKAT] <food_dessert>', '[PUSH] <food_dessert>', '[FIND] <food_vegetable>', '[GRAB] <food_vegetable>', '[TURNTO] <food_vegetable>', '[LOOKAT] <food_vegetable>', '[PUTBACK] <food_vegetable> <garbage_can>', '[FIND] <milk>', '[GRAB] <milk>', '[TURNTO] <milk>', '[LOOKAT] <milk>', '[PUTOBJBACK] <milk>', '[CLOSE] <freezer>'] } Scene_Objects:['tablelamp', 'chair', 'cat', 'drawing', 'orchid', 'floor', 'ceiling', 'keyboard', 'computer', 'stovefan', 'brush', 'window', 'couch', 'pillow', 'dining_room', 'food_kiwi', 'wall', 'oven', 'coffe_maker', 'curtain', 'doorjamb', 'towel_rack', 'mouse', 'shaving_cream', 'cards', 'door', 'table', 'light', 'tooth_paste', 'laser_pointer'] Task:Pet cat response: | { The cat is laying on the couch in the living room. I want to pet it, so I am going to walk to the living room, sit on the couch, and pet the cat. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'food_salt', 'walllamp', 'bathroom', 'trashcan', 'knifeblock', 'bedroom', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'shower', 'mousepad', 'microphone', 'dining_room', 'nightstand', 'basket_for_clothes', 'bed', 'newspaper', 'coffe_maker', 'check', 'tray', 'curtain', 'doorjamb', 'mouse', 'headset', 'laundry_detergent', 'maindoor', 'bathroom_cabinet', 'washing_machine'] Task:Wash clothes response: { thoughts : Walk to laundry room. Find laundry basket. Grab laundry basket. Find washing machine. Walk to washing machine. Open washing machine. Find detergent. Grab detergent. Put in detergent. Put in clothes. Close washing machine. Turn on machine., actions : ['[WALK] <bathroom>', '[WALK] <basket_for_clothes>', '[FIND] <basket_for_clothes>', '[GRAB] <basket_for_clothes>', '[FIND] <washing_machine>', '[WALK] <washing_machine>', '[OPEN] <washing_machine>', '[FIND] <laundry_detergent>', '[GRAB] <laundry_detergent>', '[POUR] <laundry_detergent> <washing_machine>', '[PUTOBJBACK] <laundry_detergent>', '[PUTBACK] <basket_for_clothes> <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>'] } 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: | { Walk to living room. Find light switch. Switch on light 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:['glue', 'filing_cabinet', 'toilet', 'walllamp', 'nail_polish', 'food_butter', 'drawing', 'orchid', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'character', 'ceilinglamp', 'tvstand', 'shower', 'closetdrawer', 'couch', 'form', 'dining_room', 'wall', 'wall_clock', 'bed', 'toothbrush_holder', 'doorjamb', 'chessboard', 'door', 'napkin', 'bathroom_cabinet', 'shoe_rack'] Task:Pick up phone response: { thoughts : I walk over to the phone and pick it up., actions : ['[WALK] <phone>', '[GRAB] <phone>'] } Scene_Objects:['dry_pasta', 'toilet', 'freezer', 'ground_coffee', 'knifeblock', 'floor', 'ceiling', 'character', 'bedroom', 'keyboard', 'purse', 'computer', 'toaster', 'window', 'mousepad', 'broom', 'wall', 'check', 'food_food', 'food_rice', 'doorjamb', 'mouse', 'pencil', 'dresser', 'sink', 'napkin', 'light', 'colander', 'tooth_paste', 'shoe_rack'] Task:Wash dishes with dishwasher response: | { grab the vesseles and wash } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'walllamp', 'bathroom', 'trashcan', 'dough', 'drawing', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'faucet', 'window', 'food_noodles', 'mousepad', 'pillow', 'dining_room', 'wall', 'bed', 'food_food', 'razor', 'rag', 'console', 'mouse', 'towel_rack', 'kitchen_counter', 'door', 'sink', 'bathtub', 'bathroom_cabinet'] Task:Clean sink response: { thoughts : Take a premoistened cleaning wipe and wipe down top of sink and faucet. Next clean the sink bowl. Let air dry., actions : ['[WALK] <bathroom>', '[WALK] <rag>', '[FIND] <rag>', '[GRAB] <rag>', '[WALK] <sink>', '[FIND] <faucet>', '[WIPE] <faucet>', '[WIPE] <sink>', '[PUTOBJBACK] <rag>'] } Scene_Objects:['filing_cabinet', 'tablelamp', 'microwave', 'walllamp', 'orchid', 'wallshelf', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'keyboard', 'computer', 'toaster', 'faucet', 'shower', 'closetdrawer', 'couch', 'wall', 'nightstand', 'tray', 'curtain', 'towel_rack', 'mouse', 'kitchen_counter', 'vacuum_cleaner', 'dresser', 'hairbrush', 'laundry_detergent', 'door'] Task:Vacuum response: | { Plug in vacuum. Walk around with vacuum, covering all of the floor. Unplug vacuum. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'beer', 'detergent', 'food_butter', 'orchid', 'hanger', 'floor', 'ceiling', 'computer', 'toaster', 'mat', 'closetdrawer', 'broom', 'wall', 'nightstand', 'toy', 'newspaper', 'toilet_paper', 'television', 'wine', 'doorjamb', 'kitchen_counter', 'shoes', 'chessboard', 'dresser', 'door', 'dishwasher', 'instrument_violin', 'laser_pointer'] Task:Put away shoes response: { thoughts : Pick up shoes from entry hall. Open entry way closet. Put shoes in closet. Close closet door., actions : ['[WALK] <home_office>', '[WALK] <shoes>', '[FIND] <shoes>', '[GRAB] <shoes>', '[FIND] <dresser>', '[OPEN] <dresser>', '[PUTIN] <shoes> <dresser>', '[CLOSE] <dresser>'] } Scene_Objects:['filing_cabinet', 'juice', 'food_salt', 'microwave', 'detergent', 'trashcan', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'folder', 'desk', 'keyboard', 'food_cake', 'purse', 'shoe-shine_kit', 'faucet', 'wall', 'nightstand', 'powersocket', 'photoframe', 'check', 'coffe_maker', 'doorjamb', 'hair', 'sink', 'bathroom_cabinet', 'table'] Task:Clean sink response: | { Take a premoistened cleaning wipe and wipe down top of sink and faucet. Next clean the sink bowl. Let air 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:['mop', 'chair', 'jelly', 'walllamp', 'drawing', 'wallshelf', 'food_egg', 'hanger', 'floor', 'ceiling', 'character', 'desk', 'remote_control', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'closetdrawer', 'couch', 'pillow', 'wall', 'photoframe', 'television', 'food_rice', 'doorjamb', 'diary', 'kitchen_counter', 'dresser', 'coffee'] Task:Watch horror movie response: { thoughts : I would find something scary to watch on dvd, actions : ['[WALK] <home_office>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <television>', '[SWITCHON] <television>', '[TURNTO] <television>', '[WATCH] <television>'] } Scene_Objects:['dry_pasta', 'pot', 'food_salt', 'dog', 'freezer', 'walllamp', 'bathroom', 'drawing', 'floor', 'bedroom', 'computer', 'toaster', 'mat', 'tvstand', 'clothes_socks', 'closetdrawer', 'couch', 'food_orange', 'pillow', 'dining_room', 'wall', 'tape', 'check', 'coffe_maker', 'television', 'doorjamb', 'towel_rack', 'kitchen_counter', 'dresser', 'table'] Task:Put out flowers response: | { Place a flower centrepiece on the entrance hall 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:['pot', 'chair', 'freezer', 'walllamp', 'bathroom', 'drawing', 'wallshelf', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'bookshelf', 'remote_control', 'computer', 'button', 'piano_bench', 'mat', 'tvstand', 'ceilinglamp', 'mousepad', 'closetdrawer', 'couch', 'pillow', 'wall', 'photoframe', 'novel', 'television', 'doorjamb', 'dresser'] Task:Change TV channel response: { thoughts : first i will go to living room and then take the remote and swtitch on television after that il change the channel, actions : ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <remote_control>', '[TURNTO] <remote_control>', '[POINTAT] <remote_control>', '[TOUCH] <remote_control>', '[TURNTO] <television>', '[WATCH] <television>'] } Scene_Objects:['filing_cabinet', 'toilet', 'chair', 'walllamp', 'trashcan', 'cpuscreen', 'floor', 'ceiling', 'character', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'faucet', 'shower', 'mousepad', 'couch', 'pillow', 'dining_room', 'wall', 'powersocket', 'coffe_maker', 'television', 'doorjamb', 'towel_rack', 'mouse', 'cupboard', 'table', 'coffee'] Task:Call family member with skype application response: | { Sit down on desk chair located in front of computer. Turn on computer. Log in to skype application. Locate individual to call on contacts list. Press the call button with computer mouse. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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:['filing_cabinet', 'microwave', 'drawing', 'orchid', 'wallshelf', 'floor', 'desk', 'bookshelf', 'purse', 'computer', 'mat', 'tvstand', 'couch', 'clothes_pants', 'pillow', 'wall', 'bench', 'powersocket', 'basket_for_clothes', 'photoframe', 'bed', 'television', 'doorjamb', 'pencil', 'laundry_detergent', 'clothes_dress', 'table', 'light', 'clothes_shirt', 'washing_machine'] Task:Do laundry response: | { Collecting laundry from the children's hamper } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'measuring_cup', 'chair', 'orchid', 'drawing', 'cpuscreen', 'wallshelf', 'floor', 'ceiling', 'desk', 'tea_bag', 'keyboard', 'bookshelf', 'computer', 'alcohol', 'stovefan', 'mat', 'ceilinglamp', 'tvstand', 'stereo', 'floor_lamp', 'mousepad', 'wall', 'nightstand', 'novel', 'video_game_controller', 'television', 'mouse', 'door', 'napkin'] Task:Study response: { thoughts : Study norwegian, actions : ['[WALK] <home_office>', '[WALK] <floor_lamp>', '[FIND] <floor_lamp>', '[SWITCHON] <floor_lamp>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <chair>', '[SIT] <chair>', '[READ] <novel>'] } Scene_Objects:['tablelamp', 'microwave', 'chair', 'freezer', 'bathroom', 'trashcan', 'drawing', 'cpuscreen', 'wallshelf', 'bathroom_counter', 'floor', 'phone', 'mail', 'stovefan', 'ceilinglamp', 'tvstand', 'window', 'mousepad', 'pillow', 'wall_clock', 'child', 'check', 'coffe_maker', 'tray', 'doorjamb', 'mouse', 'dresser', 'sink', 'bathroom_cabinet', 'home_office'] Task:Greet guests response: | { Say hi } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'bathroom', 'trashcan', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'desk', 'bookshelf', 'alcohol', 'mat', 'electric_shaver', 'oil', 'wall', 'powersocket', 'box', 'food_cheese', 'photoframe', 'bed', 'food_food', 'coffe_maker', 'doorjamb', 'lighter', 'dishrack', 'door', 'bathroom_cabinet', 'light', 'dishwasher', 'coffee'] 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', 'toilet', 'chair', 'walllamp', 'trashcan', 'cpuscreen', 'wallshelf', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'toaster', 'ceilinglamp', 'tvstand', 'mat', 'mousepad', 'pillow', 'wall', 'nightstand', 'powersocket', 'newspaper', 'television', 'curtain', 'rag', 'doorjamb', 'mouse', 'door', 'bathtub', 'table'] Task:Use computer response: | { Browse reddit } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['filing_cabinet', 'walllamp', 'bathroom', 'detergent', 'orchid', 'knifeblock', 'drawing', 'hanger', 'floor', 'ceiling', 'phone', 'bookshelf', 'mat', 'shower', 'faucet', 'wall', 'powersocket', 'oven', 'light_bulb', 'novel', 'check', 'television', 'food_donut', 'curtain', 'doorjamb', 'kitchen_counter', 'spoon', 'home_office', 'light', 'dishwasher'] Task:Turn on light response: { thoughts : Switch on light in home office, actions : ['[WALK] <home_office>', '[WALK] <light>', '[FIND] <light>', '[PLUGIN] <light>', '[SWITCHON] <light>', '[WALK] <home_office>'] } Scene_Objects:['tablelamp', 'microwave', 'toilet', 'chair', 'walllamp', 'nail_polish', 'trashcan', 'bathroom_counter', 'floor', 'ceiling', 'character', 'bedroom', 'toaster', 'stovefan', 'faucet', 'towel', 'pillow', 'wall', 'wall_clock', 'bed', 'check', 'television', 'doorjamb', 'kitchen_counter', 'dresser', 'controller', 'sink', 'bathroom_cabinet', 'soap', 'hands_both'] Task:Wash hands response: | { Cleaning 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:['glue', 'toilet', 'chair', 'walllamp', 'drawing', 'wallshelf', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'computer', 'mail', 'mat', 'tvstand', 'ceilinglamp', 'closetdrawer', 'couch', 'pillow', 'dining_room', 'wall', 'cutting_board', 'photoframe', 'bed', 'television', 'doorjamb', 'dishrack', 'dresser', 'door', 'dishwasher'] Task:Watch TV response: { thoughts : go to the living room to watch TV, actions : ['[RUN] <home_office>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[WALK] <couch>', '[SIT] <couch>', '[FIND] <television>', '[TURNTO] <television>', '[POINTAT] <television>', '[TOUCH] <remote_control>', '[SWITCHON] <television>', '[TURNTO] <television>', '[LOOKAT] <television>', '[WATCH] <television>', '[DROP] <remote_control>', '[TURNTO] <television>', '[LOOKAT] <television>', '[WATCH] <television>'] } Scene_Objects:['fork', 'microwave', 'freezer', 'knife', 'food_egg', 'wallshelf', 'kitchen_cabinet', 'ceiling', 'character', 'desk', 'tea_bag', 'toaster', 'stovefan', 'plate', 'faucet', 'shower', 'mat', 'wall', 'oven', 'bench', 'coffe_maker', 'drinking_glass', 'tray', 'kitchen_counter', 'cupboard', 'door', 'sink', 'spoon', 'napkin', 'dishwasher'] Task:Unload dishwasher response: | { Open the dishwasher door. Take out all of the dishes and silverware. Put the dishes and silverware in their drawers and cabinets. Close the dishwasher door. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['toilet', 'chair', 'jelly', 'walllamp', 'detergent', 'drawing', 'wallshelf', 'bathroom_counter', 'floor', 'phone', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'stereo', 'window', 'homework', 'closetdrawer', 'couch', 'pillow', 'wall', 'newspaper', 'coffe_maker', 'television', 'tray', 'curtain', 'towel_rack', 'cupboard', 'home_office', 'table'] Task:Read newspaper response: { thoughts : Read the newspaper on the couch, actions : ['[WALK] <home_office>', '[WALK] <newspaper>', '[FIND] <newspaper>', '[GRAB] <newspaper>', '[FIND] <couch>', '[SIT] <couch>', '[READ] <newspaper>'] } Scene_Objects:['measuring_cup', 'walllamp', 'bathroom', 'detergent', 'bathroom_counter', 'floor', 'ceiling', 'character', 'bedroom', 'stovefan', 'mat', 'tvstand', 'faucet', 'shower', 'ceilinglamp', 'couch', 'towel', 'dining_room', 'wall', 'oven', 'photoframe', 'doorjamb', 'mouse', 'cupboard', 'door', 'sink', 'bathtub', 'bathroom_cabinet', 'soap', 'hands_both'] Task:Wash hands response: | { Turn on the water faucet. Wet my hands and turn off the faucet. Put soap on my hands. Rub hands together, making sure the soap covers all areas of the hands. Scrub hands for about 20 seconds. Turn on the water water faucet. Rinse hands under the running water. Turn off the water faucet. Dry hands with a towel. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'microwave', 'chair', 'milk', 'bathroom_counter', 'floor', 'bookshelf', 'table_cloth', 'toaster', 'tvstand', 'shower', 'foundation', 'pillow', 'wall', 'nightstand', 'powersocket', 'cutting_board', 'cup', 'coffe_maker', 'food_onion', 'kitchen_counter', 'dishrack', 'cupboard', 'clothes_dress', 'sink', 'bag', 'table', 'dishwasher', 'dirt', 'shoe_rack'] Task:Wash dishes by hand response: { thoughts : walk to kitchen , find dish washer , wash the dishe rack , put dishes in dish washer , switch on dish washer, actions : ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[FIND] <dishrack>', '[FIND] <dishrack>', '[GRAB] <dishrack>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[PUTBACK] <dishrack> <dishwasher>', '[SWITCHON] <dishwasher>'] } Scene_Objects:['filing_cabinet', 'tablelamp', 'chair', 'walllamp', 'bathroom', 'knife', 'drawing', 'wallshelf', 'orchid', 'hanger', 'cpuscreen', 'floor', 'character', 'keyboard', 'purse', 'homework', 'mousepad', 'wall', 'pasta', 'bench', 'keys', 'television', 'wooden_spoon', 'towel_rack', 'kettle', 'kitchen_counter', 'hair', 'conditioner', 'home_office', 'table'] Task:Hang up car keys response: | { Open the front door. Enter the entrance hall. Take out car keys from purse. Hang car keys up on hook on the wall. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'juice', 'microwave', 'chair', 'freezer', 'detergent', 'drawing', 'orchid', 'floor', 'ceiling', 'toaster', 'stovefan', 'plate', 'shower', 'mat', 'ceilinglamp', 'couch', 'pillow', 'wall', 'pasta', 'oven', 'cup', 'newspaper', 'coffe_maker', 'television', 'ice', 'wine', 'tray', 'towel_rack', 'kitchen_counter', 'headset', 'cupboard', 'table', 'dishwasher', 'creditcard'] Task:Grab some juice response: { thoughts : I go to the fridge, and grab some juice out of it. I then get a glass, and pour the juice into the glass., actions : ['[WALK] <dining_room>', '[WALK] <cupboard>', '[FIND] <cupboard>', '[OPEN] <cupboard>', '[FIND] <cup>', '[GRAB] <cup>', '[CLOSE] <cupboard>', '[WALK] <freezer>', '[OPEN] <freezer>', '[FIND] <juice>', '[GRAB] <juice>', '[POUR] <juice> <cup>', '[PUTOBJBACK] <juice>', '[CLOSE] <freezer>', '[FIND] <table>', '[PUTBACK] <cup> <table>'] } Scene_Objects:['filing_cabinet', 'mop', 'microwave', 'chair', 'freezer', 'dog', 'trashcan', 'drawing', 'wallshelf', 'hanger', 'bathroom_counter', 'phone', 'dvd_player', 'character', 'bookshelf', 'computer', 'stovefan', 'mat', 'shower', 'couch', 'pillow', 'bench', 'photoframe', 'food_food', 'tray', 'curtain', 'kitchen_counter', 'door', 'sink', 'table'] Task:Pet dog response: | { Pet my dog in hall } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'beer', 'toilet', 'freezer', 'walllamp', 'drawing', 'knifeblock', 'floor', 'ceiling', 'desk', 'toaster', 'mat', 'stovefan', 'shower', 'faucet', 'food_orange', 'nightstand', 'wall', 'powersocket', 'oven', 'photoframe', 'coffe_maker', 'tray', 'doorjamb', 'kitchen_counter', 'cupboard', 'door', 'sink', 'light'] Task:Make toast response: { thoughts : Place slices of bread in a toaster ,wait for the bread to pop up .Set aside., actions : ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <food_bread>', '[GRAB] <food_bread>', '[CLOSE] <freezer>', '[FIND] <toaster>', '[PLUGIN] <toaster>', '[PUTBACK] <food_bread> <toaster>', '[SWITCHON] <toaster>'] } Scene_Objects:['glue', 'pot', 'filing_cabinet', 'microwave', 'chair', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'face', 'toaster', 'stovefan', 'faucet', 'oil', 'towel', 'wall', 'facial_cleanser', 'check', 'coffe_maker', 'tray', 'rag', 'mouse', 'kitchen_counter', 'dresser', 'door', 'sink', 'bathroom_cabinet', 'table', 'soap'] Task:Wash face response: | { Turn the faucet on. Wet the face. Take facial cleanser out of packaging. Lather on face. Rinse face with water. Turn off the faucet. Dry face with towel. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'tablelamp', 'beer', 'toilet', 'freezer', 'walllamp', 'drawing', 'knifeblock', 'kitchen_cabinet', 'floor', 'ceiling', 'food_chicken', 'stovefan', 'mat', 'toaster', 'shower', 'nightstand', 'wall', 'powersocket', 'oven', 'photoframe', 'food_food', 'food_donut', 'tray', 'doorjamb', 'kitchen_counter', 'cupboard', 'door', 'light', 'dishwasher'] Task:Cook some food response: { thoughts : Walk into the kitchen. Open the fridge. Take out the chicken. Open the kitchen cabinet. Take out the frying pan. Put the chicken in the frying pan. Put the frying pan on the stove. Turn on the stove. Cook the chicken., actions : ['[WALK] <dining_room>', '[WALK] <freezer>', '[OPEN] <freezer>', '[FIND] <food_chicken>', '[GRAB] <food_chicken>', '[CLOSE] <freezer>', '[FIND] <kitchen_cabinet>', '[OPEN] <kitchen_cabinet>', '[FIND] <pot>', '[GRAB] <pot>', '[CLOSE] <kitchen_cabinet>', '[WALK] <oven>', '[PUTBACK] <pot> <oven>', '[PUTBACK] <food_chicken> <oven>', '[SWITCHON] <oven>'] } Scene_Objects:['filing_cabinet', 'walllamp', 'drawing', 'wallshelf', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'mat', 'ceilinglamp', 'tvstand', 'window', 'homework', 'mousepad', 'couch', 'pillow', 'wall', 'oven', 'box', 'cup', 'photoframe', 'television', 'curtain', 'doorjamb', 'dresser', 'bathtub', 'bathroom_cabinet', 'table', 'light'] Task:Straighten pictures on wall response: | { Move the pictures/paintings until they are straight. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'tablelamp', 'chair', 'walllamp', 'trashcan', 'knifeblock', 'bathroom_counter', 'keyboard', 'computer', 'brush', 'tvstand', 'shower', 'faucet', 'mousepad', 'wall', 'bench', 'cup', 'bed', 'photoframe', 'clothes_gloves', 'tray', 'wooden_spoon', 'towel_rack', 'dresser', 'cupboard', 'door', 'bathtub', 'napkin', 'bathroom_cabinet'] Task:Wash monitor response: { thoughts : Clean the grime off of my monitor screen when not in use, actions : ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[SWITCHOFF] <computer>', '[FIND] <brush>', '[TURNTO] <brush>', '[LOOKAT] <brush>', '[GRAB] <brush>', '[WIPE] <computer>', '[DROP] <brush>', '[FIND] <napkin>', '[GRAB] <napkin>', '[WASH] <napkin>', '[WIPE] <computer>'] } Scene_Objects:['chair', 'freezer', 'orchid', 'drawing', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'tvstand', 'shower', 'window', 'mousepad', 'dining_room', 'wall', 'check', 'television', 'wine', 'doorjamb', 'shaving_cream', 'mouse', 'dresser', 'door', 'light', 'table'] Task:Complete surveys on amazon turk response: | { Sit down at computer, Turn computer on. Go online to Amazon mechanical turk, Browse through surveys, Select a survey. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['toilet', 'chair', 'walllamp', 'ceilingfan', 'drawing', 'floor', 'ceiling', 'keyboard', 'remote_control', 'ceilinglamp', 'tvstand', 'balanceball', 'shoe-shine_kit', 'window', 'oil', 'couch', 'wall', 'cup', 'food_food', 'coffe_maker', 'television', 'curtain', 'doorjamb', 'console', 'hairbrush', 'cupboard', 'food_steak', 'maindoor', 'door', 'table'] Task:Watch TV response: { thoughts : Watch favorite shows, netflix, hulu, actions : ['[WALK] <home_office>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[WALK] <couch>', '[SIT] <couch>', '[FIND] <television>', '[SWITCHON] <television>', '[PUTBACK] <remote_control> <couch>', '[TURNTO] <television>', '[WATCH] <television>'] } Scene_Objects:['filing_cabinet', 'chair', 'walllamp', 'drawing', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'food_cake', 'mat', 'ceilinglamp', 'tvstand', 'window', 'couch', 'pillow', 'dining_room', 'wall', 'wall_clock', 'photoframe', 'clothes_gloves', 'bed', 'television', 'curtain', 'doorjamb', 'towel_rack', 'kitchen_counter', 'home_office', 'table', 'light'] Task:Admire art response: | { Looking at painting, art } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'detergent', 'orchid', 'longboard', 'floor', 'desk', 'food_bacon', 'stovefan', 'ceilinglamp', 'toaster', 'faucet', 'balanceball', 'window', 'bed', 'oven_mitts', 'ice', 'curtain', 'after_shave', 'lighter', 'towel_rack', 'cards', 'controller', 'laundry_detergent', 'maindoor', 'door', 'sink', 'home_office', 'table'] Task:Turn on light response: { thoughts : Twist the lamp switch until the light goes on., actions : ['[WALK] <home_office>', '[WALK] <floor_lamp>', '[FIND] <floor_lamp>', '[SWITCHON] <floor_lamp>'] } Scene_Objects:['tablelamp', 'microwave', 'freezer', 'walllamp', 'trashcan', 'woman', 'bathroom_counter', 'ceiling', 'phone', 'bedroom', 'man', 'computer', 'stovefan', 'ceilinglamp', 'faucet', 'couch', 'dining_room', 'child', 'powersocket', 'bench', 'oven', 'photoframe', 'bed', 'coffe_maker', 'doorjamb', 'towel_rack', 'bathtub', 'sink', 'bathroom_cabinet', 'table'] Task:Say goodbye to guests leaving response: | { Tell them bye } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'chair', 'walllamp', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'bedroom', 'keyboard', 'tea_bag', 'computer', 'table_cloth', 'ceilinglamp', 'tvstand', 'mousepad', 'pillow', 'wall', 'nightstand', 'powersocket', 'bench', 'photoframe', 'television', 'tray', 'doorjamb', 'mouse', 'home_office', 'table'] Task:Browse internet response: { thoughts : Walk to home office. Find computer. Sit in chair in front of computer desk. Turn on computer. Open internet browser. Browse the internet, actions : ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[WALK] <desk>', '[FIND] <chair>', '[SIT] <chair>', '[SWITCHON] <computer>'] } Scene_Objects:['filing_cabinet', 'toilet', 'chair', 'freezer', 'walllamp', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'character', 'desk', 'keyboard', 'bookshelf', 'purse', 'mail', 'computer', 'laptop', 'deck_of_cards', 'faucet', 'foundation', 'mousepad', 'wall', 'wall_clock', 'bench', 'cup', 'doorjamb', 'mouse', 'door', 'light', 'table'] Task:Sent email response: | { Walk into home office. Sit down in a chair at a desk. Turn on laptop. Bring up the internet. Go to gmail website. Begin composing an email. Hit the send 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', 'filing_cabinet', 'food_bread', 'microwave', 'trashcan', 'drawing', 'knifeblock', 'cpuscreen', 'hanger', 'bathroom_counter', 'bedroom', 'tea_bag', 'tvstand', 'window', 'form', 'pillow', 'broom', 'bench', 'basket_for_clothes', 'newspaper', 'bed', 'check', 'coffe_maker', 'tray', 'door', 'home_office', 'light', 'bathroom_cabinet', 'tooth_paste', 'coffee'] Task:Get dressed response: { thoughts : I get dressed in my bedroom in the mornings., actions : ['[WALK] <bedroom>', '[WALK] <shoes>', '[FIND] <shoes>', '[GRAB] <shoes>', '[PUTON] <shoes>'] } Scene_Objects:['dry_pasta', 'filing_cabinet', 'walllamp', 'toothbrush', 'drawing', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'clothes_jacket', 'mat', 'tvstand', 'ceilinglamp', 'window', 'couch', 'pillow', 'wall', 'bench', 'box', 'cup', 'photoframe', 'novel', 'mouthwash', 'television', 'curtain', 'doorjamb', 'comb', 'light', 'table'] Task:Read book response: | { Sit and read } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'freezer', 'detergent', 'knifeblock', 'phone', 'bookshelf', 'computer', 'mop_bucket', 'brush', 'clothes_socks', 'mousepad', 'dining_room', 'nightstand', 'basket_for_clothes', 'food_food', 'curtain', 'doorjamb', 'towel_rack', 'mouse', 'kitchen_counter', 'dresser', 'laundry_detergent', 'bathtub', 'sink', 'home_office', 'napkin', 'dishwasher', 'bathroom_cabinet', 'washing_machine'] Task:Wash clothes response: { thoughts : 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 , actions : ['[WALK] <home_office>', '[WALK] <bedroom>', '[WALK] <basket_for_clothes>', '[FIND] <basket_for_clothes>', '[GRAB] <basket_for_clothes>', '[WALK] <dining_room>', '[WALK] <washing_machine>', '[FIND] <washing_machine>', '[OPEN] <washing_machine>', '[PUTBACK] <basket_for_clothes> <washing_machine>', '[FIND] <laundry_detergent>', '[GRAB] <laundry_detergent>', '[PUTBACK] <laundry_detergent> <washing_machine>', '[CLOSE] <washing_machine>', '[TURNTO] <washing_machine>'] } Scene_Objects:['pot', 'tablelamp', 'toilet', 'chair', 'freezer', 'bathroom', 'wallshelf', 'hanger', 'floor', 'ceiling', 'character', 'computer', 'laptop', 'tvstand', 'shower', 'faucet', 'mousepad', 'closetdrawer', 'clothes_pants', 'wall', 'powersocket', 'bed', 'tray', 'doorjamb', 'diary', 'dresser', 'clothes_dress', 'sink', 'clothes_shirt', 'dirt'] Task:Get dressed response: | { Find dresser, grab pants, grab shirt, put on pants, put on shirt } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'sponge', 'tablelamp', 'mop', 'bathroom', 'drawing', 'orchid', 'knifeblock', 'wallshelf', 'floor', 'ceiling', 'stamp', 'wine_glass', 'clothes_socks', 'couch', 'pillow', 'wall', 'nightstand', 'food_cheese', 'bed', 'photoframe', 'food_food', 'check', 'doorjamb', 'door', 'sink', 'bag', 'bathroom_cabinet', 'table', 'light'] Task:Entertain response: { thoughts : Give guests wine, cheese, crackers and sit and talk, actions : ['[WALK] <home_office>', '[WALK] <food_cheese>', '[FIND] <food_cheese>', '[FIND] <food_food>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <wine_glass>', '[GRAB] <wine_glass>', '[DRINK] <wine_glass>'] } Scene_Objects:['food_ice_cream', 'microwave', 'toilet', 'freezer', 'trashcan', 'drawing', 'knife', 'wallshelf', 'kitchen_cabinet', 'floor', 'ceiling', 'character', 'ceilinglamp', 'mat', 'shower', 'food_jam', 'dining_room', 'wall', 'bench', 'cutting_board', 'food_vegetable', 'photoframe', 'television', 'doorjamb', 'kitchen_counter', 'cupboard', 'door', 'bathtub', 'table', 'light'] Task:Chop vegetables response: | { Cut up veggies with knife } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['filing_cabinet', 'food_salt', 'freezer', 'walllamp', 'drawing', 'orchid', 'floor', 'ceiling', 'bedroom', 'remote_control', 'ceilinglamp', 'tvstand', 'mat', 'homework', 'window', 'wall', 'powersocket', 'oven', 'toy', 'bed', 'toilet_paper', 'television', 'toothbrush_holder', 'food_donut', 'tray', 'doorjamb', 'door', 'sink', 'spoon', 'table'] Task:Change TV channel response: { thoughts : Lift the remote and change the channel, actions : ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[TURNTO] <television>', '[WATCH] <television>'] } Scene_Objects:['tablelamp', 'beer', 'food_butter', 'trashcan', 'drawing', 'hanger', 'floor', 'ceiling', 'phone', 'bedroom', 'bookshelf', 'mail', 'stovefan', 'mat', 'tvstand', 'stereo', 'window', 'wall', 'nightstand', 'child', 'oven', 'powersocket', 'bed', 'novel', 'curtain', 'doorjamb', 'towel_rack', 'kitchen_counter', 'home_office', 'table'] Task:Story reading time response: | { Sit on bed with child, open mother goose, pick story, read book, point at the pretty pictures } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'detergent', 'orchid', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'wall', 'powersocket', 'photoframe', 'coffe_maker', 'television', 'coffee_filter', 'curtain', 'doorjamb', 'towel_rack', 'mouse', 'cupboard', 'sink', 'bathtub', 'light', 'soap'] Task:Watch TV response: { thoughts : I pick up remote. I turn on tv. I push on the remote. I change the channel., actions : ['[WALK] <home_office>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>'] } Scene_Objects:['filing_cabinet', 'microwave', 'chair', 'walllamp', 'orchid', 'cpuscreen', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'mousepad', 'pillow', 'dining_room', 'wall', 'nightstand', 'powersocket', 'cutting_board', 'television', 'curtain', 'doorjamb', 'mouse', 'door', 'table'] Task:Watch youtube response: | { Go to youtube.Com watch videos } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'chair', 'walllamp', 'detergent', 'cpuscreen', 'wallshelf', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'brush', 'ceilinglamp', 'tvstand', 'plate', 'mousepad', 'closetdrawer', 'dustpan', 'pillow', 'wall', 'powersocket', 'television', 'tray', 'doorjamb', 'centerpiece', 'mouse', 'shoes', 'table'] Task:Write an email response: { thoughts : walk to living room, look at computer, find chair, sit in chair, grab keyboard, grab mouse, type using keyboard and mouse, actions : ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[WALK] <computer>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <keyboard>', '[GRAB] <keyboard>', '[FIND] <mouse>', '[GRAB] <mouse>', '[TYPE] <keyboard>'] } Scene_Objects:['filing_cabinet', 'food_ice_cream', 'chair', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'stovefan', 'mat', 'faucet', 'shower', 'window', 'mousepad', 'couch', 'towel', 'wall', 'bed', 'photoframe', 'curtain', 'after_shave', 'kitchen_counter', 'sink', 'bathroom_cabinet', 'light', 'soap', 'hands_both', 'shoe_rack'] Task:Wash hands response: | { Wash hands with soap and hot 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:['fork', 'toilet', 'freezer', 'ground_coffee', 'ceilingfan', 'milk', 'floor', 'ceiling', 'shampoo', 'purse', 'ceilinglamp', 'mat', 'faucet', 'oil', 'wall', 'pasta', 'tape', 'novel', 'food_food', 'food_donut', 'wooden_spoon', 'mouse', 'kitchen_counter', 'door', 'home_office', 'bathroom_cabinet', 'vase', 'soap', 'instrument_violin', 'creditcard'] 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:['juice', 'walllamp', 'bathroom', 'detergent', 'trashcan', 'orchid', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'keyboard', 'alcohol', 'faucet', 'closetdrawer', 'food_jam', 'wall', 'oven', 'cup', 'photoframe', 'coffe_maker', 'razor', 'curtain', 'doorjamb', 'towel_rack', 'sink', 'bathroom_cabinet', 'light', 'soap', 'hands_both'] Task:Wash hands response: | { go to bathroom. walk to sink,turn on faucet, put hands in water. rub hands together. grab soap. rub soap in hands. put soap down. put hands under water. rubs hands together. turn off faucet } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'drawing', 'hanger', 'longboard', 'floor', 'ceiling', 'bathroom_counter', 'bookshelf', 'keyboard', 'computer', 'button', 'ceilinglamp', 'tvstand', 'faucet', 'picture', 'mousepad', 'pillow', 'wall', 'basket_for_clothes', 'photoframe', 'curtain', 'shoes', 'cd', 'vacuum_cleaner', 'dresser', 'cupboard', 'clothes_dress', 'home_office', 'table', 'shoe_rack'] Task:Take off shoes response: { thoughts : 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., actions : ['[WALK] <bedroom>', '[WALK] <shoes>', '[FIND] <shoes>', '[GRAB] <shoes>', '[PULL] <shoes>', '[WALK] <dresser>', '[OPEN] <dresser>', '[PUTIN] <shoes> <dresser>', '[FIND] <shoes>', '[GRAB] <shoes>', '[PULL] <shoes>', '[WALK] <dresser>', '[PUTIN] <shoes> <dresser>', '[CLOSE] <dresser>'] } Scene_Objects:['blender', 'chair', 'walllamp', 'trashcan', 'drawing', 'orchid', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'character', 'desk', 'bookshelf', 'keyboard', 'computer', 'mat', 'mousepad', 'wall', 'bench', 'photoframe', 'novel', 'curtain', 'doorjamb', 'towel_rack', 'mouse', 'shaving_cream', 'door', 'bathroom_cabinet', 'light', 'home_office'] Task:Read response: | { We pick out a book from the bookshelf and read 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', 'chair', 'walllamp', 'trashcan', 'knifeblock', 'floor', 'character', 'computer', 'table_cloth', 'toaster', 'plate', 'faucet', 'dish_soap', 'wall', 'oven', 'bench', 'cup', 'coffe_maker', 'food_food', 'television', 'wine', 'tray', 'pencil', 'kitchen_counter', 'dresser', 'cupboard', 'sink', 'home_office', 'dishwasher', 'vase'] Task:Wash dishes with dishwasher response: { thoughts : I walk into the kitchen and go to the dishwasher. I open the dishwasher and grab the dishes. Iplace the dishes into the dishwasher then close it. I add soap then turn the dishwasher on., actions : ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[OPEN] <dishwasher>', '[WALK] <kitchen_counter>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[PUTBACK] <dish_soap> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>'] } Scene_Objects:['dog', 'freezer', 'chair', 'walllamp', 'bathroom', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'character', 'desk', 'bedroom', 'computer', 'stovefan', 'tvstand', 'faucet', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'curtain', 'rag', 'doorjamb', 'towel_rack', 'sink', 'bathroom_cabinet', 'table', 'light'] Task:Wipe down sink response: | { Use a cloth to wipe the edge of the sink. Then wipe the bowl of the sink as well. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'freezer', 'walllamp', 'trashcan', 'drawing', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'ceiling', 'character', 'food_bacon', 'mat', 'ceilinglamp', 'shower', 'wall', 'wall_clock', 'cup', 'photoframe', 'bed', 'food_food', 'tray', 'doorjamb', 'mouse', 'kitchen_counter', 'cupboard', 'door', 'coffee'] Task:Drink response: { thoughts : Walk into kitchen, look for cup, walk to cup, look for refrigerator, walk to refrigerator, open door, grab water, pour water into cup, actions : ['[WALK] <dining_room>', '[WALK] <cup>', '[FIND] <cup>', '[TURNTO] <cup>', '[LOOKAT] <cup>', '[WALK] <cup>', '[FIND] <freezer>', '[TURNTO] <freezer>', '[LOOKAT] <freezer>', '[WALK] <freezer>', '[GRAB] <cup>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <cup>'] } Scene_Objects:['microwave', 'chair', 'walllamp', 'bathroom', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'character', 'keyboard', 'alcohol', 'toaster', 'tvstand', 'shower', 'closetdrawer', 'nightstand', 'wall_clock', 'bench', 'powersocket', 'food_food', 'doorjamb', 'towel_rack', 'mouse', 'cupboard', 'sink', 'home_office', 'table', 'light', 'coffee'] Task:Walk through response: | { Walk through the hallway. } |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.