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:['pot', 'tablelamp', 'microwave', 'toothbrush', 'drawing', 'orchid', 'wallshelf', 'kitchen_cabinet', 'floor', 'ceiling', 'desk', 'bedroom', 'stovefan', 'toaster', 'ceilinglamp', 'faucet', 'shower', 'mousepad', 'pillow', 'wall', 'pasta', 'oven', 'coffe_maker', 'water', 'tray', 'towel_rack', 'kitchen_counter', 'headset', 'sauce_pan', 'cupboard'] Task:Cook some food response: { thoughts : Cook some pasta on the stove, actions : ['[WALK] <dining_room>', '[WALK] <kitchen_cabinet>', '[FIND] <kitchen_cabinet>', '[OPEN] <kitchen_cabinet>', '[FIND] <pasta>', '[GRAB] <pasta>', '[FIND] <water>', '[GRAB] <water>', '[FIND] <sauce_pan>', '[POUR] <water> <sauce_pan>', '[FIND] <oven>', '[SWITCHON] <oven>', '[PUTBACK] <pasta> <sauce_pan>', '[FIND] <sauce_pan>', '[GRAB] <sauce_pan>', '[PUTBACK] <sauce_pan> <oven>'] } Scene_Objects:['tea', 'chair', 'freezer', 'cpuscreen', 'food_egg', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'bookshelf', 'keyboard', 'computer', 'clothes_jacket', 'stovefan', 'mousepad', 'wall', 'keys', 'check', 'oven_mitts', 'doorjamb', 'mouse', 'pencil', 'dresser', 'cupboard', 'door', 'clothes_scarf', 'napkin', 'home_office', 'light'] Task:Turn on light response: | { turn on the light for 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:['sheets', 'pot', 'chair', 'freezer', 'walllamp', 'bathroom', 'drawing', 'ceiling', 'dvd_player', 'character', 'bookshelf', 'keyboard', 'brush', 'ceilinglamp', 'toaster', 'mat', 'window', 'nightstand', 'bench', 'photoframe', 'food_food', 'after_shave', 'diary', 'kettle', 'shoes', 'chessboard', 'dresser', 'door', 'bathroom_cabinet', 'colander'] Task:Dust response: { thoughts : Using soft brush, carefully dust both Indonesian wedding doll statues., actions : ['[WALK] <home_office>', '[WALK] <dresser>', '[OPEN] <dresser>', '[FIND] <brush>', '[GRAB] <brush>', '[CLOSE] <dresser>'] } Scene_Objects:['food_salt', 'bathroom', 'detergent', 'ceilingfan', 'drawing', 'orchid', 'floor', 'ceiling', 'character', 'keyboard', 'remote_control', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'couch', 'food_peanut_butter', 'pillow', 'towel', 'dining_room', 'wall', 'powersocket', 'toilet_paper', 'television', 'curtain', 'pencil', 'headset', 'cd', 'table', 'dishwasher'] Task:Change TV channel response: | { Lift the remote and 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:['filing_cabinet', 'chair', 'ceilingfan', 'knifeblock', 'orchid', 'clothes_underwear', 'hanger', 'floor', 'ceiling', 'phone', 'character', 'desk', 'computer', 'couch', 'broom', 'wall', 'coffe_maker', 'video_game_controller', 'wine', 'doorjamb', 'towel_rack', 'cards', 'pencil', 'kitchen_counter', 'mouse', 'dresser', 'cupboard', 'door', 'light', 'board_game'] Task:Turn on light response: { thoughts : Walk over to light switch. Turn on lights., actions : ['[WALK] <light>', '[SWITCHON] <light>'] } Scene_Objects:['filing_cabinet', 'food_bread', 'toilet', 'chair', 'cat', 'trashcan', 'ceilingfan', 'orchid', 'cpuscreen', 'longboard', 'desk', 'remote_control', 'button', 'food_bacon', 'foundation', 'couch', 'dining_room', 'oven', 'bench', 'basket_for_clothes', 'cup', 'bed', 'check', 'toothbrush_holder', 'doorjamb', 'coffee_pot', 'vacuum_cleaner', 'controller', 'spoon', 'table'] Task:Change TV channel response: | { Walk into living room. Find television remote control. Pick up remote control. Press 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:['pot', 'filing_cabinet', 'beer', 'freezer', 'walllamp', 'bathroom', 'bathroom_counter', 'character', 'bedroom', 'desk', 'ceilinglamp', 'tvstand', 'faucet', 'clothes_socks', 'clothes_pants', 'towel', 'bench', 'basket_for_clothes', 'bed', 'coin', 'food_donut', 'curtain', 'towel_rack', 'mouse', 'cd', 'comb', 'laundry_detergent', 'bathtub', 'bathroom_cabinet', 'washing_machine'] Task:Wash clothes response: { thoughts : Go to kitchen, find washing machine, find laundry, put laundry in washing machine, find soap, put soap in washing machine, turn on., actions : ['[WALK] <dining_room>', '[WALK] <washing_machine>', '[FIND] <washing_machine>', '[FIND] <basket_for_clothes>', '[GRAB] <basket_for_clothes>', '[OPEN] <washing_machine>', '[PUTBACK] <basket_for_clothes> <washing_machine>', '[WALK] <laundry_detergent>', '[FIND] <laundry_detergent>', '[GRAB] <laundry_detergent>', '[POUR] <laundry_detergent> <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>'] } Scene_Objects:['food_ice_cream', 'microwave', 'freezer', 'ceilingfan', 'knifeblock', 'drawing', 'orchid', 'floor', 'ceiling', 'dvd_player', 'character', 'bookshelf', 'clothes_jacket', 'ceilinglamp', 'tvstand', 'deck_of_cards', 'mousepad', 'couch', 'food_jam', 'pillow', 'food_kiwi', 'wall', 'powersocket', 'bed', 'food_food', 'ice', 'mouse', 'door', 'dishwasher', 'scrabble'] Task:Cook some food response: | { Walk Into Kitchen. Open Refrigerator. Grab Food. Walk to Microwave. Insert food into microwave. Cook until warm. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'bathroom', 'bathroom_counter', 'floor', 'ceiling', 'bedroom', 'purse', 'stovefan', 'mat', 'toaster', 'faucet', 'shower', 'plate', 'closetdrawer', 'towel', 'wall', 'wall_clock', 'oven', 'toy', 'hands_both', 'coin', 'tray', 'mouse', 'sink', 'bathtub', 'bathroom_cabinet', 'table', 'home_office', 'soap', 'teeth'] Task:Wash hands response: { thoughts : Go to the bathroom. Turn on the sink. Rinse hands. Apply soap and scrub your hands together. Rinse hands again. Turn off faucet. Dry hands on a towel., actions : ['[WALK] <bathroom>', '[WALK] <faucet>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <hands_both>', '[RINSE] <hands_both>', '[FIND] <soap>', '[GRAB] <soap>', '[SCRUB] <hands_both>', '[PUTOBJBACK] <soap>', '[RINSE] <hands_both>', '[SWITCHOFF] <faucet>', '[FIND] <towel>', '[GRAB] <towel>', '[WIPE] <hands_both>', '[PUTOBJBACK] <towel>'] } Scene_Objects:['freezer', 'bathroom', 'ceilingfan', 'food_carrot', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'computer', 'food_bacon', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'stovefan', 'window', 'couch', 'food_orange', 'wall', 'powersocket', 'cutting_board', 'bed', 'novel', 'mouthwash', 'television', 'curtain', 'towel_rack', 'home_office', 'table', 'clothes_skirt'] Task:Watch TV response: | { I come home and go to the sofa for turn off the tv 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:['freezer', 'band-aids', 'dough', 'cpuscreen', 'food_egg', 'floor', 'ceiling', 'dvd_player', 'desk', 'bedroom', 'keyboard', 'computer', 'clothes_jacket', 'ceilinglamp', 'mat', 'mousepad', 'wall', 'powersocket', 'cup', 'bed', 'photoframe', 'newspaper', 'water', 'food_donut', 'doorjamb', 'mouse', 'door', 'light', 'table', 'shoe_rack'] Task:Drink response: { thoughts : Feeling tired after hard work I opened the fridge and grabbed cool water and drank from the glass., actions : ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <cup>', '[GRAB] <cup>', '[CLOSE] <freezer>', '[FIND] <water>', '[GRAB] <water>', '[FIND] <cup>', '[POUR] <water> <cup>', '[FIND] <cup>', '[DRINK] <cup>'] } Scene_Objects:['tablelamp', 'mop', 'walllamp', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'envelope', 'stovefan', 'faucet', 'couch', 'form', 'wall', 'bench', 'photoframe', 'coffe_maker', 'television', 'food_donut', 'wine', 'tray', 'after_shave', 'mouse', 'paper_towel', 'door', 'sink', 'bathroom_cabinet', 'dishwasher', 'clothes_skirt', 'soap', 'hands_both'] Task:Wash hands response: | { I walk to the bathroom and find the sink. I grab the soap and rub some on my hands. I turn the faucet on and put my hands in the water. I rinse my hands and then turn off the faucet. Then I dry my hands on a paper towel. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'microwave', 'chair', 'walllamp', 'bills', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'window', 'mousepad', 'dining_room', 'wall', 'nightstand', 'powersocket', 'oven', 'photoframe', 'food_food', 'television', 'doorjamb', 'towel_rack', 'mouse', 'bathroom_cabinet', 'table', 'home_office'] Task:Work response: { thoughts : Sit at a desk. Turn on computer. Sign onto mTurk. Perform tasks., actions : ['[WALK] <home_office>', '[WALK] <chair>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[FIND] <keyboard>', '[TYPE] <keyboard>'] } Scene_Objects:['tablelamp', 'microwave', 'cd_player', 'freezer', 'detergent', 'trashcan', 'food_carrot', 'drawing', 'knifeblock', 'hanger', 'floor', 'phone', 'character', 'button', 'toaster', 'ceilinglamp', 'stovefan', 'window', 'food_noodles', 'couch', 'wall', 'wall_clock', 'bench', 'powersocket', 'television', 'towel_rack', 'dresser', 'sink', 'table', 'light'] Task:Listen to music response: | { Walk to living room, walk to cd player, turn on cd player, press play button, walk to sofa, sit in sofa and listen to music } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['water_glass', 'food_pizza', 'pot', 'microwave', 'bathroom', 'bills', 'knifeblock', 'cpuscreen', 'drawing', 'longboard', 'floor', 'phone', 'folder', 'bedroom', 'keyboard', 'mail', 'food_bacon', 'piano_bench', 'button', 'table_cloth', 'shower', 'couch', 'dining_room', 'wall', 'powersocket', 'cutting_board', 'water', 'tray', 'pencil', 'door'] Task:Drink response: { thoughts : Drinking a glass of water, actions : ['[WALK] <dining_room>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[FIND] <water_glass>', '[POUR] <water> <water_glass>', '[FIND] <water_glass>', '[GRAB] <water_glass>', '[DRINK] <water_glass>'] } Scene_Objects:['glue', 'tablelamp', 'chair', 'walllamp', 'bathroom', 'trashcan', 'ceilingfan', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'computer', 'laptop', 'balanceball', 'mousepad', 'pillow', 'wall', 'cup', 'bed', 'television', 'razor', 'doorjamb', 'kitchen_counter', 'dresser', 'cupboard', 'door', 'spoon', 'light', 'vase'] Task:Turn on light response: | { push any ligth button to turn it on, for example 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:['chair', 'walllamp', 'blow_dryer', 'knifeblock', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'folder', 'desk', 'food_cake', 'stovefan', 'toaster', 'deck_of_cards', 'faucet', 'candle', 'pillow', 'dining_room', 'oven', 'photoframe', 'check', 'food_food', 'television', 'bathroom_cabinet', 'table', 'dishwasher', 'soap', 'board_game', 'clothes_shirt'] Task:Pet cat response: { thoughts : Walk to living room. Find cat. Walk to cat. Pull cat., actions : ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[WALK] <cat>', '[PULL] <cat>'] } Scene_Objects:['filing_cabinet', 'blender', 'jelly', 'freezer', 'chair', 'drawing', 'clothes_underwear', 'bathroom_counter', 'floor', 'button', 'stovefan', 'ceilinglamp', 'brush', 'deck_of_cards', 'window', 'oil', 'couch', 'clothes_hat', 'dining_room', 'broom', 'wall', 'mouthwash', 'television', 'kitchen_counter', 'dishrack', 'sink', 'bathroom_cabinet', 'table', 'home_office', 'scrabble'] Task:Relax on sofa response: | { walk to living room ,find sofa ,sit on sofa } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['nail_polish', 'orchid', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'thread', 'faucet', 'couch', 'dining_room', 'wall', 'nightstand', 'bench', 'wall_clock', 'photoframe', 'coffe_maker', 'food_food', 'lighter', 'doorjamb', 'towel_rack', 'diary', 'shoes', 'comb', 'door', 'sink', 'bathroom_cabinet', 'table', 'soap', 'dirt', 'hands_both'] Task:Wash hands response: { thoughts : Go to the bathroom. turn on the water in the sink. apply soap to hands. rub hands together. rinse hands with water. turn off the water., actions : ['[WALK] <bathroom>', '[WALK] <sink>', '[FIND] <sink>', '[FIND] <soap>', '[GRAB] <soap>', '[FIND] <hands_both>', '[SCRUB] <hands_both>', '[RINSE] <hands_both>', '[WIPE] <hands_both>'] } Scene_Objects:['spectacles', 'cpuscreen', 'bathroom_counter', 'longboard', 'phone', 'desk', 'bookshelf', 'computer', 'stovefan', 'tvstand', 'shower', 'balanceball', 'window', 'foundation', 'clothes_socks', 'bowl', 'newspaper', 'bed', 'check', 'food_food', 'television', 'razor', 'food_rice', 'cards', 'cupboard', 'maindoor', 'napkin', 'bathroom_cabinet', 'table', 'dishwasher'] Task:Turn on light response: | { I go to bedroom and locate a lamp. This lamp can be turned on by touch, as it has capacitive sensing. So I do it. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['dry_pasta', 'food_pizza', 'filing_cabinet', 'scissors', 'chair', 'ceilingfan', 'dough', 'drawing', 'orchid', 'floor', 'ceiling', 'phone', 'bookshelf', 'remote_control', 'stovefan', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'couch', 'food_orange', 'wall', 'powersocket', 'coffee_table', 'television', 'coin', 'wooden_spoon', 'curtain', 'maindoor', 'table'] Task:Watch TV response: { thoughts : I walk into the living room and sit on the couch. I pick up the remote to turn on the television. I put down the remote on the coffee table and look at the television., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <coffee_table>', '[PUTBACK] <remote_control> <coffee_table>', '[TURNTO] <television>', '[LOOKAT] <television>'] } Scene_Objects:['sheets', 'tablelamp', 'food_ice_cream', 'walllamp', 'trashcan', 'ceilingfan', 'drawing', 'longboard', 'floor', 'bookshelf', 'computer', 'faucet', 'balanceball', 'window', 'iron', 'food_peanut_butter', 'food_jam', 'wall', 'nightstand', 'bench', 'powersocket', 'basket_for_clothes', 'novel', 'check', 'coffee_filter', 'shaving_cream', 'pencil', 'maindoor', 'sink', 'hairdryer'] Task:Pick up phone response: | { Enter the Home office, then walk to the phone, pickup 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', 'microwave', 'toilet', 'chair', 'detergent', 'food_butter', 'toothbrush', 'drawing', 'floor', 'ceiling', 'toaster', 'mat', 'plate', 'faucet', 'shower', 'dish_soap', 'wall', 'nightstand', 'cup', 'coffe_maker', 'coffee_filter', 'drinking_glass', 'tray', 'wooden_spoon', 'kitchen_counter', 'cupboard', 'sink', 'coffee_cup', 'dishwasher', 'shoe_rack'] Task:Clean dishes response: { thoughts : Wash dishes in the sink then place them in the dishwasher. Put detergent in the dishwasher and turn it on when full., actions : ['[WALK] <dining_room>', '[WALK] <sink>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[FIND] <drinking_glass>', '[WASH] <drinking_glass>', '[FIND] <coffee_cup>', '[WASH] <coffee_cup>', '[FIND] <plate>', '[WASH] <plate>', '[GRAB] <coffee_cup>', '[PUTBACK] <coffee_cup> <plate>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[GRAB] <drinking_glass>', '[PUTBACK] <drinking_glass> <dishwasher>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <detergent>', '[GRAB] <detergent>', '[PUTBACK] <detergent> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>'] } Scene_Objects:['sheets', 'filing_cabinet', 'food_ice_cream', 'beer', 'microwave', 'freezer', 'walllamp', 'floor', 'ceiling', 'phone', 'dvd_player', 'stovefan', 'ceilinglamp', 'toaster', 'mousepad', 'wall', 'wall_clock', 'cup', 'bed', 'food_food', 'coin', 'food_rice', 'water', 'pencil', 'shoes', 'controller', 'napkin', 'bathroom_cabinet', 'table', 'dishwasher'] Task:Drink response: | { Feeling tired after hard work I opened the fridge and grabbed cool water and drank 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:['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: { thoughts : Say hi, actions : ['[WALK] <home_office>', '[WALK] <child>', '[FIND] <child>', '[GREET] <child>'] } Scene_Objects:['pot', 'blender', 'crayon', 'measuring_cup', 'freezer', 'nail_polish', 'cat', 'floor', 'dvd_player', 'character', 'bedroom', 'tea_bag', 'piano_bench', 'toaster', 'foundation', 'window', 'couch', 'photoframe', 'check', 'toilet_paper', 'curtain', 'centerpiece', 'shaving_cream', 'mouse', 'chessboard', 'headset', 'sink', 'napkin', 'spoon', 'light'] Task:Read book response: | { pick up the book open the book 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:['food_ice_cream', 'toilet', 'walllamp', 'nail_polish', 'dough', 'orchid', 'wallshelf', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'keyboard', 'computer', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'wall', 'nightstand', 'powersocket', 'photoframe', 'television', 'curtain', 'doorjamb', 'cards', 'dishrack', 'door', 'light'] Task:Change TV channel response: { thoughts : first i will go to living room and then take the remote and swtitch on television after that il change the channel, actions : ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <remote_control>', '[TURNTO] <remote_control>', '[POINTAT] <remote_control>', '[TOUCH] <remote_control>', '[TURNTO] <television>', '[WATCH] <television>'] } Scene_Objects:['fork', 'filing_cabinet', 'blow_dryer', 'trashcan', 'drawing', 'knife', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'character', 'desk', 'toaster', 'faucet', 'picture', 'towel', 'dining_room', 'wall', 'nightstand', 'powersocket', 'photoframe', 'novel', 'food_food', 'controller', 'door', 'sink', 'bathroom_cabinet', 'clothes_skirt', 'soap', 'board_game'] Task:Wash hands response: | { I walk into the bathroom. Walk to the sink. Turn on tap. Get soap. Wash and rinse hands. Turn off tap. 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:['scissors', 'detergent', 'orchid', 'wallshelf', 'bedroom', 'tea_bag', 'bookshelf', 'ceilinglamp', 'laptop', 'faucet', 'window', 'couch', 'broom', 'wall', 'oven', 'cutting_board', 'toy', 'cup', 'standingmirror', 'razor', 'television', 'tray', 'after_shave', 'towel_rack', 'mouse', 'kitchen_counter', 'controller', 'bathtub', 'vase', 'soap'] Task:Pick up phone response: { thoughts : walk to living room, walk to the phone reach for the phone and pick up the phone., actions : ['[WALK] <home_office>', '[WALK] <phone>', '[FIND] <phone>', '[TOUCH] <phone>', '[GRAB] <phone>'] } Scene_Objects:['pot', 'tablelamp', 'freezer', 'blow_dryer', 'ceilingfan', 'drawing', 'floor', 'ceiling', 'bedroom', 'remote_control', 'ceilinglamp', 'tvstand', 'balanceball', 'stereo', 'window', 'shoe-shine_kit', 'couch', 'microphone', 'food_jam', 'wall', 'coffe_maker', 'check', 'television', 'curtain', 'sink', 'napkin', 'bathroom_cabinet', 'table', 'colander', 'tooth_paste'] Task:Watch TV response: | { Walk to the living room. Find the television. Walk to the television. Switch on the television. Find the sofa. Walk to the sofa. Sit on the sofa. Find the remote control. Grab the remote control. Look at the television. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', '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: { thoughts : go to radio. run on radio., actions : ['[WALK] <stereo>', '[SWITCHON] <stereo>'] } Scene_Objects:['spectacles', 'food_ice_cream', 'cd_player', 'orchid', 'bedroom', 'purse', 'computer', 'stovefan', 'mat', 'ceilinglamp', 'stereo', 'tvstand', 'balanceball', 'clothes_socks', 'couch', 'food_jam', 'powersocket', 'oven', 'cutting_board', 'photoframe', 'novel', 'check', 'television', 'wine', 'food_onion', 'pencil', 'vacuum_cleaner', 'door', 'sink', 'instrument_violin'] Task:Listen to music response: | { I walk in the living room, then I go the the stereo and the cd player and turn them 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:['pot', 'food_bread', 'juice', 'toilet', 'chair', 'freezer', 'ground_coffee', 'walllamp', 'food_butter', 'food_carrot', 'drawing', 'floor', 'ceiling', 'stovefan', 'mat', 'ceilinglamp', 'shower', 'food_peanut_butter', 'food_jam', 'bowl', 'wall', 'nightstand', 'oven', 'powersocket', 'cup', 'food_cheese', 'photoframe', 'coffe_maker', 'food_food', 'tray', 'doorjamb', 'kitchen_counter', 'cupboard', 'door', 'food_steak', 'light', 'dishwasher', 'table'] 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:['pot', 'food_bread', 'toilet', 'chair', 'freezer', 'floor', 'ceiling', 'thread', 'table_cloth', 'ceilinglamp', 'faucet', 'food_peanut_butter', 'dining_room', 'wall', 'nightstand', 'powersocket', 'tape', 'photoframe', 'bed', 'food_food', 'cards', 'kitchen_counter', 'dishrack', 'dresser', 'hair', 'pajamas', 'door', 'home_office', 'dishwasher', 'vase'] Task:Put groceries in Fridge response: | { go to the kitchen and put the groceries in 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_pizza', 'freezer', 'trashcan', 'drawing', 'bathroom_counter', 'ceiling', 'phone', 'thread', 'computer', 'stovefan', 'faucet', 'shower', 'food_jam', 'dining_room', 'wall', 'powersocket', 'tape', 'coffe_maker', 'food_food', 'mirror', 'doorjamb', 'mouse', 'paper_towel', 'dresser', 'cupboard', 'sink', 'clothes_scarf', 'bathroom_cabinet', 'home_office', 'dirt'] Task:Clean mirror response: { thoughts : Spray Windex or glass and mirror cleaner onto mirror. Use paper towel to wipe off cleaner until mirror is dry and has no streaks., actions : ['[WALK] <bathroom>', '[WALK] <bathroom_cabinet>', '[FIND] <bathroom_cabinet>', '[OPEN] <bathroom_cabinet>', '[FIND] <paper_towel>', '[GRAB] <paper_towel>', '[CLOSE] <bathroom_cabinet>', '[WALK] <mirror>', '[WIPE] <mirror>', '[FIND] <trashcan>', '[PUTBACK] <paper_towel> <trashcan>'] } Scene_Objects:['toilet', 'detergent', 'drawing', 'orchid', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'character', 'desk', 'keyboard', 'thread', 'table_cloth', 'tvstand', 'balanceball', 'shower', 'mousepad', 'couch', 'wall', 'photoframe', 'bed', 'toilet_paper', 'food_onion', 'towel_rack', 'mouse', 'kitchen_counter', 'cd', 'hairbrush', 'bathroom_cabinet', 'light'] Task:Go to toilet response: | { walk to bathroom , run to toilet } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['chair', 'walllamp', 'detergent', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'mail', 'button', 'clothes_jacket', 'ceilinglamp', 'mousepad', 'closetdrawer', 'wall', 'wall_clock', 'powersocket', 'keys', 'television', 'ice', 'doorjamb', 'mouse', 'pencil', 'headset', 'dresser', 'sink', 'light', 'table'] Task:Write an email response: { thoughts : Switch on computer, Use keybord and mouse to open e-mail provider, type requested e-mail, click send, close e-mail provider, turn off computer, actions : ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <mouse>', '[FIND] <keyboard>', '[FIND] <mail>', '[OPEN] <mail>', '[TYPE] <keyboard>', '[FIND] <button>', '[PUSH] <button>', '[CLOSE] <mail>', '[SWITCHOFF] <computer>'] } Scene_Objects:['toilet', 'chair', 'ceilingfan', 'drawing', 'needle', 'floor', 'ceiling', 'folder', 'character', 'keyboard', 'remote_control', 'button', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'mat', 'window', 'couch', 'dining_room', 'wall', 'pasta', 'light_bulb', 'television', 'curtain', 'doorjamb', 'kitchen_counter', 'shoes', 'table', 'shoe_rack'] Task:Change TV channel response: | { Walk into the Living room. Find the television remote. Use it to turn on the television. Point the remote at the television. Press the channel button on the remote. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'filing_cabinet', 'blender', 'toilet', 'drawing', 'needle', 'food_egg', 'clothes_underwear', 'bathroom_counter', 'phone', 'keyboard', 'computer', 'table_cloth', 'closetdrawer', 'clothes_hat', 'nightstand', 'oven', 'basket_for_clothes', 'photoframe', 'check', 'television', 'coin', 'food_donut', 'diary', 'towel_rack', 'headset', 'comb', 'hairdryer', 'napkin'] Task:Drink response: { thoughts : Drink water, actions : ['[WALK] <dining_room>', '[WALK] <water_glass>', '[FIND] <water_glass>', '[GRAB] <water_glass>', '[DRINK] <water_glass>'] } Scene_Objects:['fork', 'sheets', 'chair', 'dog', 'walllamp', 'orchid', 'cpuscreen', 'longboard', 'phone', 'character', 'desk', 'table_cloth', 'clothes_hat', 'towel', 'wall_clock', 'oven', 'bed', 'light_bulb', 'food_food', 'drinking_glass', 'water', 'curtain', 'after_shave', 'console', 'headset', 'cupboard', 'maindoor', 'spoon', 'bathroom_cabinet', 'light'] Task:Drink response: | { I walk to the kitchen. Take a glass out of the cabinet. Then I walk to the sink and turn the water on and fill the glass. Then I take a drink. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'jelly', 'chair', 'phone', 'ceiling', 'desk', 'bedroom', 'table_cloth', 'bookmark', 'stovefan', 'mat', 'tvstand', 'stereo', 'shoe-shine_kit', 'faucet', 'toaster', 'mousepad', 'powersocket', 'cutting_board', 'shelf', 'food_cheese', 'television', 'wooden_spoon', 'after_shave', 'food_onion', 'doorjamb', 'shoes', 'dishrack', 'vase', 'electrical_outlet'] Task:Turn on radio response: { thoughts : Go to the radio. Switch on the power button. Tune the station. Set the volume. Listen to the music., actions : ['[WALK] <home_office>', '[WALK] <stereo>', '[FIND] <stereo>', '[FIND] <electrical_outlet>', '[TURNTO] <electrical_outlet>', '[PLUGIN] <stereo>', '[SWITCHON] <electrical_outlet>', '[SWITCHON] <stereo>'] } Scene_Objects:['spectacles', 'food_salt', 'toilet', 'chair', 'food_butter', 'ceilingfan', 'cpuscreen', 'floor', 'ceiling', 'dvd_player', 'character', 'desk', 'bedroom', 'bookshelf', 'keyboard', 'food_cake', 'computer', 'shoe-shine_kit', 'faucet', 'mousepad', 'oil', 'wall', 'nightstand', 'bed', 'mouse', 'kitchen_counter', 'vacuum_cleaner', 'cupboard', 'sink', 'bathroom_cabinet'] Task:Read book response: | { go to living room,find the text book on the self ,sat on the chair ,open and read the book } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'microwave', 'chair', 'walllamp', 'trashcan', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mousepad', 'couch', 'dining_room', 'wall', 'powersocket', 'oven', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'door', 'bathroom_cabinet', 'table'] Task:Turn on computer response: { thoughts : Push power button., actions : ['[WALK] <home_office>', '[WALK] <computer>', '[SWITCHON] <computer>'] } Scene_Objects:['water_glass', 'filing_cabinet', 'beer', 'freezer', 'cpuscreen', 'floor', 'ceiling', 'desk', 'bedroom', 'keyboard', 'food_cake', 'button', 'ceilinglamp', 'mat', 'pillow', 'wall', 'cup', 'basket_for_clothes', 'bed', 'check', 'coffe_maker', 'food_donut', 'tray', 'pencil', 'kitchen_counter', 'dresser', 'cupboard', 'food_steak', 'table', 'vase'] Task:Drink response: | { walk to kitchen ,find fridge ,open fridge ,find water glass , drink from water glass } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['filing_cabinet', 'walllamp', 'bathroom', 'drawing', 'orchid', 'hanger', 'floor', 'ceiling', 'desk', 'ceilinglamp', 'tvstand', 'mat', 'window', 'couch', 'clothes_hat', 'pillow', 'dining_room', 'wall', 'powersocket', 'clothes_gloves', 'television', 'razor', 'curtain', 'doorjamb', 'console', 'mouse', 'door', 'bag', 'table', 'dishwasher'] 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:['juice', 'food_ice_cream', 'blow_dryer', 'detergent', 'ceilingfan', 'drawing', 'hanger', 'longboard', 'floor', 'ceiling', 'phone', 'bedroom', 'keyboard', 'remote_control', 'ceilinglamp', 'tvstand', 'balanceball', 'faucet', 'window', 'shoe-shine_kit', 'couch', 'food_orange', 'wall', 'tape', 'television', 'curtain', 'kitchen_counter', 'conditioner', 'bathroom_cabinet', 'table'] Task:Relax on sofa response: | { For relaxing walk to living room. Find the sofa to relax. Arrange the sofa to relax. Sit on the sofa to relaxing. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'walllamp', 'ceilingfan', 'drawing', 'hanger', 'floor', 'bedroom', 'computer', 'ceilinglamp', 'deck_of_cards', 'iron', 'window', 'electric_shaver', 'couch', 'food_orange', 'wall', 'wall_clock', 'bed', 'novel', 'check', 'television', 'toothbrush_holder', 'wooden_spoon', 'after_shave', 'towel_rack', 'dresser', 'conditioner', 'maindoor', 'table', 'vase'] Task:Relax on sofa response: { thoughts : Walk to the living room. Find the sofa. Walk to the sofa. Lie in the sofa., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[WALK] <couch>', '[LIE] <couch>'] } Scene_Objects:['filing_cabinet', 'drawing', 'clothes_underwear', 'bathroom_counter', 'ceiling', 'purse', 'clothes_jacket', 'table_cloth', 'stovefan', 'shoe-shine_kit', 'faucet', 'shower', 'window', 'clothes_socks', 'clothes_pants', 'microphone', 'wall', 'nightstand', 'pasta', 'photoframe', 'razor', 'wine', 'hairbrush', 'clothes_dress', 'hairdryer', 'sink', 'bathroom_cabinet', 'dishwasher', 'vase', 'washing_machine'] Task:Wash clothes response: | { Walk to bathroom, open cabinet and collect clothes and put them into washing machine and wash clothes } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'microwave', 'chair', 'walllamp', 'orchid', 'knifeblock', 'cpuscreen', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'remote_control', 'computer', 'ceilinglamp', 'tvstand', 'window', 'closetdrawer', 'couch', 'pillow', 'dining_room', 'wall', 'nightstand', 'television', 'curtain', 'shaving_cream', 'dresser', 'home_office', 'table', 'bathroom_cabinet', 'shoe_rack'] 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:['sponge', 'freezer', 'walllamp', 'knifeblock', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'envelope', 'clothes_jacket', 'toaster', 'faucet', 'wall', 'oven', 'coffe_maker', 'television', 'drinking_glass', 'tray', 'curtain', 'lighter', 'coffee_pot', 'kitchen_counter', 'paper_towel', 'dishrack', 'comb', 'dresser', 'cupboard', 'sink', 'table', 'dishwasher'] Task:Wash dishes with dishwasher response: | { wipe loose dirt, place in the dishwasher, turn on the dishwasher } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'filing_cabinet', 'toilet', 'detergent', 'dough', 'bills', 'wallshelf', 'clothes_underwear', 'ceiling', 'keyboard', 'table_cloth', 'faucet', 'electric_shaver', 'mousepad', 'couch', 'dustpan', 'form', 'dining_room', 'newspaper', 'photoframe', 'food_food', 'coffe_maker', 'check', 'wooden_spoon', 'tray', 'rag', 'instrument_guitar', 'soap', 'washing_machine', 'coffee'] Task:Wash clothes response: { thoughts : Walk to bathroom. Open washer. Put clothes in washer. Put soap in washer. Close washer. Turn washer on., actions : ['[WALK] <home_office>', '[WALK] <washing_machine>', '[FIND] <washing_machine>', '[OPEN] <washing_machine>', '[FIND] <clothes_underwear>', '[GRAB] <clothes_underwear>', '[PUTBACK] <clothes_underwear> <washing_machine>', '[FIND] <soap>', '[GRAB] <soap>', '[PUTBACK] <soap> <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>'] } Scene_Objects:['sponge', 'chair', 'freezer', 'walllamp', 'food_carrot', 'drawing', 'knife', 'hanger', 'floor', 'phone', 'ceiling', 'keyboard', 'computer', 'brush', 'deck_of_cards', 'food_jam', 'bowl', 'dining_room', 'wall', 'bench', 'razor', 'doorjamb', 'mouse', 'dishrack', 'dresser', 'cupboard', 'door', 'sink', 'table', 'light'] Task:Pick up phone response: | { Pick up phone } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'microwave', 'toilet', 'chair', 'freezer', 'walllamp', 'ground_coffee', 'food_butter', 'food_carrot', 'bills', 'floor', 'ceiling', 'bedroom', 'computer', 'table_cloth', 'tvstand', 'shower', 'faucet', 'wall', 'oven', 'newspaper', 'photoframe', 'bed', 'coffee_filter', 'curtain', 'kitchen_counter', 'cupboard', 'controller', 'dishwasher', 'clothes_shirt'] Task:Make popcorn response: { thoughts : Lay popcorn bag flat inside microwave and press popcorn button to start., actions : ['[WALK] <dining_room>', '[WALK] <food_food>', '[FIND] <food_food>', '[GRAB] <food_food>', '[WALK] <microwave>', '[TURNTO] <microwave>', '[OPEN] <microwave>', '[PUTIN] <food_food> <microwave>', '[CLOSE] <microwave>', '[SWITCHON] <microwave>'] } Scene_Objects:['freezer', 'ground_coffee', 'nail_polish', 'bathroom', 'food_butter', 'bills', 'phone', 'bedroom', 'food_cake', 'envelope', 'bookmark', 'ceilinglamp', 'tvstand', 'stereo', 'shower', 'balanceball', 'dining_room', 'food_kiwi', 'powersocket', 'toy', 'cup', 'photoframe', 'food_food', 'television', 'tray', 'dishrack', 'maindoor', 'home_office', 'dishwasher', 'vase'] Task:Listen to music response: | { walk into living room, walk to stereo, turn on stereo, listen to music } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['food_bread', 'filing_cabinet', 'microwave', 'walllamp', 'drawing', 'orchid', 'wallshelf', 'bathroom_counter', 'phone', 'desk', 'bookshelf', 'toaster', 'ceilinglamp', 'shower', 'faucet', 'couch', 'dining_room', 'nightstand', 'wall_clock', 'oven', 'wall', 'bed', 'water', 'tray', 'towel_rack', 'kitchen_counter', 'bathtub', 'bathroom_cabinet', 'table', 'hands_both'] Task:Wash hands response: { thoughts : walk to bathroom, look at the water, wash hands, actions : ['[WALK] <bathroom>', '[WALK] <water>', '[FIND] <water>', '[TURNTO] <water>', '[LOOKAT] <water>', '[FIND] <hands_both>', '[WASH] <hands_both>'] } Scene_Objects:['dry_pasta', 'toilet', 'bathroom', 'trashcan', 'ceilingfan', 'toothbrush', 'orchid', 'floor', 'phone', 'bookshelf', 'computer', 'toaster', 'shoe-shine_kit', 'mousepad', 'pillow', 'dining_room', 'box', 'basket_for_clothes', 'keys', 'razor', 'toothbrush_holder', 'coin', 'wine', 'doorjamb', 'cards', 'door', 'napkin', 'home_office', 'soap', 'tooth_paste'] Task:Brush teeth response: | { today morning i went to bathroom and took my toothbrush and paste from tooth brush holder and brushed and cleaned my teeth 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:['sheets', 'toilet', 'bathroom', 'bills', 'orchid', 'cpuscreen', 'floor', 'phone', 'character', 'bedroom', 'piano_bench', 'toaster', 'mat', 'ceilinglamp', 'window', 'foundation', 'electric_shaver', 'oil', 'closetdrawer', 'couch', 'broom', 'nightstand', 'wall', 'cup', 'bed', 'check', 'toothbrush_holder', 'sink', 'napkin', 'dishwasher'] Task:Go to sleep response: { thoughts : Enter bedroom, turn on the light, and shut door. Change into night clothes. Turn off light. Turn down comforter, climb into bed, lay head on pillow, and cover up with comforter. Close eyes and drift off to sleep., actions : ['[WALK] <bedroom>', '[WALK] <bed>', '[FIND] <bed>', '[LIE] <bed>', '[FIND] <sheets>', '[PULL] <sheets>'] } Scene_Objects:['filing_cabinet', 'food_salt', 'beer', 'microwave', 'chair', 'bathroom', 'trashcan', 'dough', 'knifeblock', 'floor', 'computer', 'stovefan', 'mat', 'balanceball', 'faucet', 'window', 'couch', 'candle', 'wall', 'toy', 'bed', 'photoframe', 'coffe_maker', 'video_game_controller', 'wooden_spoon', 'curtain', 'dresser', 'pajamas', 'hair', 'maindoor'] Task:Go to sleep response: | { go to bedroom, put pajamas on, lie in bed, sleep } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['food_bread', 'microwave', 'toilet', 'freezer', 'trashcan', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'character', 'toaster', 'mat', 'stovefan', 'shower', 'faucet', 'window', 'couch', 'pillow', 'wall', 'oven', 'coffe_maker', 'television', 'tray', 'doorjamb', 'kitchen_counter', 'cupboard', 'food_steak', 'door', 'sink', 'table'] 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:['measuring_cup', 'chair', 'walllamp', 'nail_polish', 'ceilingfan', 'drawing', 'food_egg', 'floor', 'bedroom', 'keyboard', 'toaster', 'plate', 'stereo', 'shower', 'dish_soap', 'microphone', 'wall', 'bench', 'oven', 'box', 'check', 'video_game_controller', 'food_food', 'coffe_maker', 'tray', 'kettle', 'console', 'table', 'dishwasher', 'soap'] Task:Wash dishes with dishwasher response: | { I go the in kitchen then grab the plate on the table. I put the plate and dish soap in the dishwasher. Finally, I turn on the dishwasher. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['food_salt', 'toilet', 'dog', 'freezer', 'drawing', 'cpuscreen', 'phone', 'tea_bag', 'food_bacon', 'stovefan', 'mat', 'ceilinglamp', 'window', 'oil', 'food_orange', 'food_cheese', 'clothes_gloves', 'toilet_paper', 'food_food', 'television', 'coffee_filter', 'check', 'curtain', 'kettle', 'mouse', 'food_steak', 'spoon', 'instrument_guitar', 'light', 'dishwasher'] Task:Walk to room response: { thoughts : Leave the living room and enter the hall, actions : ['[WALK] <home_office>', '[WALK] <home_office>'] } Scene_Objects:['sponge', 'pot', 'food_salt', 'ceilingfan', 'dough', 'food_carrot', 'orchid', 'desk', 'remote_control', 'mail', 'button', 'computer', 'bookmark', 'mop_bucket', 'ceilinglamp', 'tvstand', 'iron', 'shower', 'couch', 'broom', 'bench', 'tape', 'check', 'tray', 'curtain', 'mouse', 'pencil', 'cupboard', 'controller', 'scrabble'] Task:Change TV channel response: | { I pick up the remote. I press button on remote. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['filing_cabinet', 'tablelamp', 'chair', 'nail_polish', 'food_carrot', 'drawing', 'cpuscreen', 'floor', 'phone', 'desk', 'keyboard', 'stovefan', 'mat', 'tvstand', 'homework', 'window', 'couch', 'pillow', 'nightstand', 'wall', 'powersocket', 'oven', 'bench', 'bed', 'novel', 'coffe_maker', 'toothbrush_holder', 'towel_rack', 'home_office', 'instrument_violin'] Task:Read book response: { thoughts : Go to the bedroom. Grab the book out of the nightstand. Lay down in bed. Open the book. Read the book., actions : ['[WALK] <bedroom>', '[WALK] <nightstand>', '[FIND] <nightstand>', '[OPEN] <nightstand>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <bed>', '[TURNTO] <bed>', '[SIT] <bed>', '[READ] <novel>'] } Scene_Objects:['pot', 'food_bread', 'blender', 'freezer', 'trashcan', 'food_carrot', 'drawing', 'knifeblock', 'hanger', 'floor', 'ceiling', 'phone', 'computer', 'ceilinglamp', 'plate', 'iron', 'wall', 'nightstand', 'bed', 'food_food', 'check', 'drinking_glass', 'curtain', 'centerpiece', 'coffee_pot', 'cupboard', 'laundry_detergent', 'door', 'dishwasher', 'vase'] Task:Drink response: | { Robot Drinks the 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:['dry_pasta', 'pot', 'food_pizza', 'tablelamp', 'microwave', 'freezer', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'food_bacon', 'stovefan', 'mat', 'shower', 'couch', 'pillow', 'wall', 'oven', 'powersocket', 'food_food', 'television', 'tray', 'doorjamb', 'towel_rack', 'kitchen_counter', 'cupboard', 'door', 'light'] Task:Cook some food response: { thoughts : go to the kitchen and cook some thing to eat, actions : ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <oven>', '[OPEN] <oven>', '[FIND] <food_pizza>', '[GRAB] <food_pizza>', '[PUTIN] <food_pizza> <oven>', '[SWITCHON] <oven>'] } Scene_Objects:['sponge', 'pot', 'food_bread', 'toilet', 'orchid', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'longboard', 'shampoo', 'desk', 'stamp', 'keyboard', 'toaster', 'mat', 'deck_of_cards', 'faucet', 'foundation', 'mousepad', 'form', 'wall', 'nightstand', 'photoframe', 'doorjamb', 'mouse', 'cupboard', 'door', 'bathroom_cabinet', 'light'] Task:Go to toilet response: | { Travel through the house and locate the bathroom, and proceed to the toilet. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['blender', 'microwave', 'toilet', 'toothbrush', 'bills', 'orchid', 'character', 'bedroom', 'stamp', 'stovefan', 'laptop', 'ceilinglamp', 'shower', 'mat', 'faucet', 'towel', 'pillow', 'dining_room', 'oven', 'coffe_maker', 'television', 'toothbrush_holder', 'comb', 'cupboard', 'door', 'sink', 'table', 'soap', 'tooth_paste', 'teeth'] Task:Brush teeth response: { thoughts : Walk to bathroom. Find toothbrush. Find toothpaste. Put toothpaste on toothbrush. Brush teeth., actions : ['[WALK] <bathroom>', '[WALK] <toothbrush_holder>', '[FIND] <toothbrush_holder>', '[FIND] <toothbrush>', '[GRAB] <toothbrush>', '[WALK] <tooth_paste>', '[FIND] <tooth_paste>', '[GRAB] <tooth_paste>', '[POUR] <tooth_paste> <toothbrush>', '[FIND] <teeth>', '[SCRUB] <teeth>'] } Scene_Objects:['fork', 'food_bread', 'tablelamp', 'mop', 'chair', 'drawing', 'food_egg', 'bathroom_counter', 'floor', 'phone', 'desk', 'bookmark', 'plate', 'shower', 'tvstand', 'pillow', 'wall', 'bench', 'newspaper', 'check', 'food_food', 'doorjamb', 'console', 'mouse', 'chessboard', 'dresser', 'spoon', 'table', 'light', 'vase'] Task:Set up table response: | { Place your plate on the placemat. The forks will be placed on the left side of the plate and the knife and spoon on the right and place the spoon to the right of the knife. If you want to set out food, place them above the plate. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'walllamp', 'trashcan', 'drawing', 'bathroom_counter', 'floor', 'bookshelf', 'mail', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'pillow', 'wall', 'oven', 'toy', 'mouthwash', 'television', 'wine', 'tray', 'curtain', 'cd', 'dresser', 'bathtub', 'sink', 'table', 'light'] Task:Relax on sofa response: { thoughts : go to the living room,find the sofa,sat down in the sofa,take some relaxation., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>'] } Scene_Objects:['food_pizza', 'tablelamp', 'microwave', 'chair', 'detergent', 'ceilingfan', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'clothes_jacket', 'mat', 'deck_of_cards', 'pillow', 'powersocket', 'photoframe', 'check', 'food_food', 'food_rice', 'wooden_spoon', 'doorjamb', 'shaving_cream', 'kettle', 'cd', 'shoes', 'controller', 'home_office', 'dishwasher', 'board_game', 'clothes_shirt'] Task:Pet cat response: | { Find Cat in living room. Walk to cat. Pet cat. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['filing_cabinet', 'toilet', 'chair', 'trashcan', 'drawing', 'orchid', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'computer', 'toaster', 'deck_of_cards', 'mousepad', 'closetdrawer', 'couch', 'wall', 'wall_clock', 'powersocket', 'bench', 'television', 'doorjamb', 'cd', 'dresser', 'conditioner', 'door', 'home_office', 'light', 'table'] Task:Pick up phone response: { thoughts : I walk to the kitchen and find the phone. I pick up the phone. I hold it to my ear., actions : ['[WALK] <dining_room>', '[WALK] <phone>', '[FIND] <phone>', '[GRAB] <phone>'] } Scene_Objects:['sheets', 'chair', 'freezer', 'cat', 'cpuscreen', 'hanger', 'longboard', 'floor', 'ceiling', 'desk', 'mail', 'clothes_jacket', 'ceilinglamp', 'iron', 'picture', 'oil', 'food_noodles', 'clothes_pants', 'wall', 'novel', 'food_food', 'coffe_maker', 'television', 'tray', 'headset', 'maindoor', 'napkin', 'vase', 'tooth_paste', 'dirt'] Task:Put groceries in Fridge response: | { Walk to kitchen. Open fridge. Put groceries in fridge. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'beer', 'toilet', 'freezer', 'cpuscreen', 'clothes_underwear', 'wallshelf', 'shampoo', 'character', 'bedroom', 'bookshelf', 'computer', 'stovefan', 'mat', 'ceilinglamp', 'shower', 'clothes_pants', 'dining_room', 'bench', 'powersocket', 'photoframe', 'coffe_maker', 'mouse', 'paper_towel', 'dresser', 'door', 'bathtub', 'bathroom_cabinet', 'light', 'hands_both'] Task:Go to toilet response: { thoughts : Walking towards Toilet room, And dispose of human waste. Cleaning your hands with tissue paper or water., actions : ['[WALK] <bathroom>', '[WALK] <paper_towel>', '[FIND] <paper_towel>', '[TURNTO] <paper_towel>', '[LOOKAT] <paper_towel>', '[GRAB] <paper_towel>', '[FIND] <hands_both>', '[WIPE] <hands_both>'] } Scene_Objects:['blow_dryer', 'trashcan', 'hanger', 'floor', 'ceiling', 'bedroom', 'bookmark', 'toaster', 'stovefan', 'tvstand', 'food_jam', 'pillow', 'dining_room', 'bowl', 'wall', 'powersocket', 'clothes_gloves', 'novel', 'coffe_maker', 'coffee_filter', 'tray', 'after_shave', 'curtain', 'cd', 'chessboard', 'cupboard', 'sink', 'dishwasher', 'scrabble', 'coffee'] Task:Make coffee response: | { Enter kitchen, find coffee maker, find coffee filter, pick up coffee filter, put it in coffee maker, find coffee, pour coffee into filter, turn 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:['filing_cabinet', 'tablelamp', 'tea', 'toilet', 'chair', 'detergent', 'trashcan', 'ceilingfan', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'mail', 'ceilinglamp', 'balanceball', 'mousepad', 'wall', 'nightstand', 'novel', 'food_onion', 'doorjamb', 'mouse', 'napkin', 'light', 'clothes_skirt'] Task:Browse internet response: { thoughts : I go to the living room, where my computer is. I locate it, switch it on and type desired URL adress in the web browser., actions : ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <keyboard>', '[TYPE] <keyboard>'] } Scene_Objects:['trashcan', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'longboard', 'bedroom', 'envelope', 'stovefan', 'brush', 'faucet', 'mousepad', 'towel', 'pillow', 'wall', 'photoframe', 'coffe_maker', 'kitchen_counter', 'headset', 'instrument_violin', 'sink', 'maindoor', 'bathroom_cabinet', 'light', 'home_office', 'table', 'soap', 'board_game', 'hands_both', 'creditcard'] Task:Wash hands response: | { Go to bathroom, turn on faucet, wet hands, apply soap, rub hands, rinse hands, turn off faucet, 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:['dry_pasta', 'bathroom', 'ceilingfan', 'knife', 'drawing', 'needle', 'knifeblock', 'bathroom_counter', 'shampoo', 'floor', 'ceiling', 'phone', 'piano_bench', 'faucet', 'window', 'teeth', 'clothes_pants', 'wall', 'photoframe', 'check', 'oven_mitts', 'tray', 'pencil', 'clothes_dress', 'sink', 'bathroom_cabinet', 'home_office', 'clothes_skirt', 'soap', 'hands_both'] Task:Wash hands response: { thoughts : Go to the bathroom and to the sink, turn the faucet on, push the bottle of soap onto your hands and scrub them. Then rinse your hands out and turn the faucet off., actions : ['[WALK] <bathroom>', '[WALK] <sink>', '[FIND] <sink>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <soap>', '[PUSH] <soap>', '[FIND] <hands_both>', '[SCRUB] <hands_both>', '[RINSE] <hands_both>', '[SWITCHOFF] <faucet>'] } Scene_Objects:['tablelamp', 'food_salt', 'microwave', 'jelly', 'detergent', 'food_carrot', 'toothbrush', 'needle', 'hanger', 'floor', 'phone', 'shampoo', 'character', 'tvstand', 'iron', 'balanceball', 'stereo', 'mousepad', 'food_jam', 'pillow', 'nightstand', 'toothbrush_holder', 'diary', 'console', 'shaving_cream', 'kitchen_counter', 'sink', 'light', 'dishwasher', 'vase'] Task:Listen to music response: | { Find the playback device you want to listen to. turn on. press play. enjoyu music. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['microwave', 'freezer', 'walllamp', 'bathroom', 'drawing', 'cpuscreen', 'wallshelf', 'hanger', 'bathroom_counter', 'floor', 'character', 'desk', 'computer', 'food_bacon', 'mat', 'tvstand', 'ceilinglamp', 'plate', 'window', 'shower', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'television', 'wine', 'curtain', 'home_office', 'table'] Task:Relax on sofa response: { thoughts : Walk into the living room. Walk to the sofa and sit on it. Put your feet up on the sofa and lay down., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[SIT] <couch>', '[LIE] <couch>'] } Scene_Objects:['sheets', 'food_bread', 'microwave', 'walllamp', 'ceilingfan', 'food_butter', 'drawing', 'bills', 'bathroom_counter', 'floor', 'ceiling', 'keyboard', 'remote_control', 'button', 'ceilinglamp', 'tvstand', 'balanceball', 'shower', 'window', 'couch', 'food_orange', 'wall', 'bench', 'photoframe', 'keys', 'check', 'food_food', 'television', 'curtain', 'table'] Task:Change TV channel response: | { Go to the living room, Switch on the television. Find the remote and press the change channel button, 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:['tablelamp', 'microwave', 'walllamp', 'nail_polish', 'trashcan', 'drawing', 'orchid', 'floor', 'desk', 'computer', 'food_bacon', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'faucet', 'window', 'mousepad', 'couch', 'pillow', 'wall', 'bench', 'coffe_maker', 'television', 'curtain', 'mouse', 'bathtub', 'home_office', 'table', 'bathroom_cabinet'] 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:['sheets', 'ceilingfan', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'folder', 'bedroom', 'remote_control', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'plate', 'window', 'oil', 'couch', 'clothes_hat', 'pillow', 'wall', 'nightstand', 'coffe_maker', 'television', 'curtain', 'food_onion', 'controller', 'clothes_dress', 'table', 'clothes_skirt', 'light'] Task:Watch TV response: | { I get home from work and decide to watch tv. I go to the living room and turn on the tv. I sit on the couch and use the remote to switch the channels to find what I want to 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:['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: { thoughts : Sit down at computer, Turn computer on. Go online to Amazon mechanical turk, Browse through surveys, Select a survey., actions : ['[WALK] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[FIND] <mouse>', '[GRAB] <mouse>', '[TURNTO] <computer>', '[POINTAT] <computer>', '[FIND] <check>', '[GRAB] <check>', '[READ] <check>', '[PUTOBJBACK] <mouse>', '[FIND] <keyboard>', '[TYPE] <keyboard>'] } Scene_Objects:['dry_pasta', 'pot', 'food_pizza', 'toilet', 'freezer', 'nail_polish', 'detergent', 'longboard', 'floor', 'ceiling', 'bedroom', 'computer', 'ceilinglamp', 'tvstand', 'faucet', 'mousepad', 'couch', 'food_peanut_butter', 'form', 'wall', 'nightstand', 'oven', 'food_food', 'ice', 'after_shave', 'doorjamb', 'lighter', 'coffee_pot', 'mouse', 'spoon'] Task:Put groceries in Fridge response: | { Put groceries into 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:['blender', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'clothes_jacket', 'table_cloth', 'mat', 'floor_lamp', 'window', 'couch', 'pillow', 'wall', 'nightstand', 'light_bulb', 'novel', 'mouthwash', 'television', 'ice', 'curtain', 'after_shave', 'doorjamb', 'console', 'kettle', 'conditioner', 'bathtub', 'sink', 'table', 'vase'] Task:Read book response: { thoughts : A person brings a book into the living room and sits down in a comfortable chair. If it is dark in the room the person turns on the lamp. The book is opened to the next page to be read. The person begins reading the book until they need to stop for some reason., actions : ['[WALK] <home_office>', '[WALK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <floor_lamp>', '[SWITCHON] <floor_lamp>', '[READ] <novel>'] } Scene_Objects:['sponge', 'pot', 'mop', 'band-aids', 'walllamp', 'trashcan', 'ceilingfan', 'knifeblock', 'kitchen_cabinet', 'floor', 'ceiling', 'bathroom_counter', 'desk', 'computer', 'stovefan', 'toaster', 'deck_of_cards', 'shower', 'wall', 'pasta', 'oven', 'cup', 'water', 'tray', 'doorjamb', 'shaving_cream', 'kitchen_counter', 'sauce_pan', 'cupboard', 'dishwasher'] Task:Cook some food response: | { Cook some pasta on the stove } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['microwave', 'freezer', 'walllamp', 'bathroom', 'dough', 'wallshelf', 'floor', 'ceiling', 'bedroom', 'bookmark', 'stovefan', 'brush', 'deck_of_cards', 'faucet', 'window', 'closetdrawer', 'dining_room', 'wall', 'oven', 'cutting_board', 'cup', 'bed', 'coffe_maker', 'food_food', 'tray', 'shaving_cream', 'kitchen_counter', 'chessboard', 'clothes_dress', 'conditioner'] 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:['pot', 'filing_cabinet', 'freezer', 'detergent', 'food_butter', 'ceilingfan', 'drawing', 'orchid', 'clothes_underwear', 'floor', 'ceiling', 'dvd_player', 'character', 'bedroom', 'remote_control', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'couch', 'wall', 'nightstand', 'bench', 'coffe_maker', 'television', 'curtain', 'console', 'kitchen_counter', 'door', 'table'] Task:Watch TV response: | { Walk to the living room. Sit on the sofa. Grab the remote and turn on 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:['juice', 'crayon', 'walllamp', 'trashcan', 'dough', 'floor', 'phone', 'bedroom', 'tea_bag', 'toaster', 'mat', 'plate', 'ceilinglamp', 'dish_soap', 'wall', 'pasta', 'oven', 'cutting_board', 'food_cheese', 'newspaper', 'coffe_maker', 'check', 'food_food', 'tray', 'towel_rack', 'pencil', 'dresser', 'conditioner', 'home_office', 'dishwasher'] Task:Wash dishes with dishwasher response: { thoughts : I walk to the kitchen. I search and find dishwasher. I search dishes. I put dishes inside the dishwasher. I put dish soap in dishwasher. I switch on dishwasher and wait for dishes to be washed., actions : ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[OPEN] <dishwasher>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[PUTBACK] <dish_soap> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>'] } Scene_Objects:['tablelamp', 'toilet', 'chair', 'walllamp', 'trashcan', 'ceilingfan', 'drawing', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'laptop', 'shoe-shine_kit', 'balanceball', 'picture', 'ceilinglamp', 'mousepad', 'wall', 'nightstand', 'newspaper', 'photoframe', 'doorjamb', 'mouse', 'dresser', 'cupboard', 'door', 'light'] Task:Work response: | { I need to finish some work on my computer in my home office to meet a deadline for tomorrow. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['microwave', 'freezer', 'walllamp', 'bathroom', 'orchid', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'dvd_player', 'character', 'bookshelf', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'laptop', 'couch', 'wall', 'powersocket', 'photoframe', 'television', 'curtain', 'doorjamb', 'lighter', 'dresser', 'sink', 'light'] Task:Change TV channel response: { thoughts : Walk to the living room. Find remote control. Grab remote control. Walk to television. Look at television. Switch on remote control., actions : ['[WALK] <home_office>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[WALK] <television>', '[TURNTO] <television>', '[LOOKAT] <television>', '[SWITCHON] <television>'] } Scene_Objects:['pot', 'scissors', 'juice', 'toilet', 'bills', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'character', 'desk', 'keyboard', 'bookshelf', 'table_cloth', 'brush', 'window', 'mousepad', 'clothes_hat', 'wall', 'nightstand', 'photoframe', 'razor', 'tray', 'mouse', 'cd', 'table', 'dishwasher', 'colander', 'scrabble', 'teeth'] Task:Go to toilet response: | { i go to the bathroom. I find the toilet } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['glue', 'walllamp', 'ceilingfan', 'drawing', 'hanger', 'floor', 'bedroom', 'computer', 'ceilinglamp', 'deck_of_cards', 'iron', 'window', 'electric_shaver', 'couch', 'food_orange', 'wall', 'wall_clock', 'bed', 'novel', 'check', 'television', 'toothbrush_holder', 'wooden_spoon', 'after_shave', 'towel_rack', 'dresser', 'conditioner', 'maindoor', 'table', 'vase'] Task:Relax on sofa response: { thoughts : Walk to the living room. Find the sofa. Walk to the sofa. Lie in the sofa., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[WALK] <couch>', '[LIE] <couch>'] } Scene_Objects:['water_glass', 'food_bread', 'bathroom', 'trashcan', 'food_carrot', 'drawing', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'phone', 'folder', 'bedroom', 'desk', 'keyboard', 'toaster', 'bench', 'tray', 'doorjamb', 'diary', 'console', 'mouse', 'towel_rack', 'cd', 'dresser', 'cupboard', 'controller', 'conditioner', 'table', 'vase'] Task:Drink response: | { walk to kitchen, walk to table, grab water glass and 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', 'tea', 'microwave', 'chair', 'walllamp', 'blow_dryer', 'bathroom', 'knifeblock', 'wallshelf', 'floor', 'ceiling', 'ceilinglamp', 'plate', 'mousepad', 'food_noodles', 'couch', 'closetdrawer', 'food_jam', 'form', 'pillow', 'wall', 'nightstand', 'razor', 'television', 'shaving_cream', 'kitchen_counter', 'bathroom_cabinet', 'dishwasher', 'soap', 'teeth'] Task:Text friends while sitting on couch response: { thoughts : Text while sitting, actions : ['[WALK] <home_office>', '[WALK] <phone>', '[FIND] <phone>', '[GRAB] <phone>', '[WALK] <couch>', '[SIT] <couch>', '[TURNTO] <phone>', '[LOOKAT] <phone>', '[TOUCH] <phone>'] } Scene_Objects:['blow_dryer', 'trashcan', 'drawing', 'needle', 'bathroom_counter', 'floor', 'ceiling', 'clothes_jacket', 'brush', 'tvstand', 'faucet', 'balanceball', 'iron', 'wall', 'bench', 'photoframe', 'check', 'razor', 'television', 'food_rice', 'console', 'hairdryer', 'sink', 'clothes_scarf', 'bathroom_cabinet', 'instrument_guitar', 'home_office', 'vase', 'teeth', 'shoe_rack'] Task:Wash teeth response: | { Walk to bathroom. Find mouthwash or turn on water. Put mouthwash or water in mouth. Swish around for 30 seconds. Spit mouthwash out. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'drawing', 'needle', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'bookshelf', 'envelope', 'computer', 'ceilinglamp', 'mousepad', 'closetdrawer', 'couch', 'dustpan', 'dining_room', 'wall', 'nightstand', 'powersocket', 'food_food', 'toilet_paper', 'doorjamb', 'coffee_pot', 'mouse', 'kettle', 'dresser', 'light'] Task:Turn on light response: { thoughts : walk into living room, walk to light, turn on light switch., actions : ['[WALK] <home_office>', '[WALK] <light>', '[SWITCHON] <light>'] } Scene_Objects:['sheets', 'toilet', 'freezer', 'cat', 'orchid', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'stovefan', 'ceilinglamp', 'tvstand', 'balanceball', 'oil', 'couch', 'clothes_hat', 'wall', 'basket_for_clothes', 'food_food', 'coffe_maker', 'curtain', 'doorjamb', 'towel_rack', 'comb', 'dresser', 'maindoor', 'soap'] Task:Put groceries in Fridge response: | { I put my groceries into 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:['chair', 'walllamp', 'drawing', 'cpuscreen', 'wallshelf', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'toaster', 'ceilinglamp', 'tvstand', 'stovefan', 'mousepad', 'wall', 'wall_clock', 'powersocket', 'nightstand', 'tape', 'newspaper', 'bed', 'television', 'doorjamb', 'mouse', 'sink', 'home_office', 'table', 'light'] Task:Work response: { thoughts : Walk to home office. Sit on chair. Switch on computer. type in keyboard., actions : ['[WALK] <home_office>', '[WALK] <chair>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <keyboard>', '[TYPE] <keyboard>'] } Scene_Objects:['spectacles', 'pot', 'tea', 'freezer', 'walllamp', 'trashcan', 'food_carrot', 'drawing', 'knifeblock', 'kitchen_cabinet', 'floor', 'ceiling', 'food_chicken', 'folder', 'stovefan', 'ceilinglamp', 'toaster', 'microphone', 'wall', 'bench', 'oven', 'cup', 'food_food', 'tray', 'doorjamb', 'kitchen_counter', 'cupboard', 'controller', 'table', 'dishwasher'] Task:Cook some food response: | { Walk to the kitchen and open the fridge. From the fridge take some chicken and close the fridge. Walk to the table and put the chicken on the table. Plug in oven and put the chicken into the oven. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'ceilingfan', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'folder', 'bedroom', 'remote_control', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'plate', 'window', 'oil', 'couch', 'clothes_hat', 'pillow', 'wall', 'nightstand', 'coffe_maker', 'television', 'curtain', 'food_onion', 'controller', 'clothes_dress', 'table', 'clothes_skirt', 'light'] Task:Watch TV response: { thoughts : I get home from work and decide to watch tv. I go to the living room and turn on the tv. I sit on the couch and use the remote to switch the channels to find what I want to watch., actions : ['[WALK] <home_office>', '[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[WALK] <couch>', '[SIT] <couch>', '[TURNTO] <television>', '[LOOKAT] <television>', '[FIND] <remote_control>', '[GRAB] <remote_control>'] } Scene_Objects:['filing_cabinet', 'food_ice_cream', 'bathroom', 'trashcan', 'knife', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'food_bacon', 'tvstand', 'faucet', 'oil', 'clothes_pants', 'wall', 'oven', 'photoframe', 'newspaper', 'after_shave', 'shaving_cream', 'sink', 'bathroom_cabinet', 'light', 'clothes_skirt', 'table', 'soap', 'hands_both'] Task:Wash hands response: | { Walk to the sink, turn on the faucet, put soap on hands, rub hands together under the water, rinse off hands, turn off faucet, 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:['sheets', 'blender', 'food_salt', 'crayon', 'tea', 'cat', 'milk', 'knifeblock', 'hanger', 'shampoo', 'bedroom', 'bookshelf', 'computer', 'brush', 'stovefan', 'toaster', 'foundation', 'window', 'mousepad', 'clothes_pants', 'clothes_hat', 'tape', 'bed', 'coffe_maker', 'food_onion', 'after_shave', 'dresser', 'light', 'dishwasher', 'laser_pointer'] Task:Pet cat response: { thoughts : Every time this animal is seen, you must approach it and show compassion for it by petting it in a gentle manner., actions : ['[WALK] <home_office>', '[WALK] <bedroom>', '[WALK] <bedroom>', '[WALK] <home_office>', '[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[FIND] <brush>', '[GRAB] <brush>'] } Scene_Objects:['mop', 'toilet', 'ceilingfan', 'orchid', 'drawing', 'cpuscreen', 'knifeblock', 'bathroom_counter', 'floor', 'desk', 'keyboard', 'food_cake', 'clothes_jacket', 'table_cloth', 'stovefan', 'mousepad', 'pillow', 'dining_room', 'wall', 'nightstand', 'cup', 'photoframe', 'clothes_gloves', 'light_bulb', 'toilet_paper', 'coin', 'ice', 'mouse', 'cupboard', 'vase'] Task:Go to toilet response: | { I walk into the bath room and go to the toilet } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sponge', 'pot', 'tablelamp', 'ground_coffee', 'walllamp', 'trashcan', 'knifeblock', 'longboard', 'floor', 'ceiling', 'character', 'bookmark', 'toaster', 'tvstand', 'wall', 'clothes_gloves', 'keys', 'coffe_maker', 'check', 'video_game_controller', 'coffee_filter', 'toilet_paper', 'food_onion', 'curtain', 'kitchen_counter', 'controller', 'hairdryer', 'dishwasher', 'vase', 'soap'] Task:Make coffee response: { thoughts : You walk into the kitchen and turn to the coffee maker. You grab the coffee filter and put into the coffee machine, you also grab the ground coffee and put it into the coffee machine. You turn on the coffee machine., actions : ['[WALK] <dining_room>', '[WALK] <coffe_maker>', '[FIND] <coffe_maker>', '[TURNTO] <coffe_maker>', '[FIND] <coffee_filter>', '[GRAB] <coffee_filter>', '[OPEN] <coffe_maker>', '[PUTBACK] <coffee_filter> <coffe_maker>', '[FIND] <ground_coffee>', '[GRAB] <ground_coffee>', '[PUTBACK] <ground_coffee> <coffe_maker>', '[SWITCHON] <coffe_maker>'] } Scene_Objects:['fork', 'tablelamp', 'walllamp', 'bathroom', 'trashcan', 'food_carrot', 'clothes_underwear', 'floor', 'desk', 'toaster', 'plate', 'shower', 'tvstand', 'food_noodles', 'clothes_socks', 'mousepad', 'wall', 'oven', 'cup', 'newspaper', 'coffe_maker', 'toilet_paper', 'food_donut', 'water', 'tray', 'food_onion', 'lighter', 'maindoor', 'spoon', 'dishwasher'] Task:Wash dishes with dishwasher response: | { first i will take all the dishes to the dish washer and with the help of dishwasher and water i will clean all the dishes } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'ground_coffee', 'walllamp', 'knife', 'knifeblock', 'hanger', 'bathroom_counter', 'floor', 'desk', 'bedroom', 'button', 'stovefan', 'mat', 'shower', 'clothes_socks', 'pillow', 'wall', 'nightstand', 'basket_for_clothes', 'bed', 'light_bulb', 'check', 'video_game_controller', 'mouthwash', 'food_onion', 'vacuum_cleaner', 'pajamas', 'cupboard', 'hair', 'instrument_guitar'] Task:Go to sleep response: { thoughts : go to bedroom, put pajamas on, lie in bed, sleep, actions : ['[WALK] <bedroom>', '[WALK] <pajamas>', '[FIND] <pajamas>', '[GRAB] <pajamas>', '[PUTON] <pajamas>', '[FIND] <bed>', '[LIE] <bed>'] } Scene_Objects:['food_salt', 'toilet', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'desk', 'bedroom', 'keyboard', 'tvstand', 'stereo', 'balanceball', 'picture', 'mousepad', 'couch', 'clothes_hat', 'pillow', 'dining_room', 'wall', 'nightstand', 'bench', 'photoframe', 'bed', 'toilet_paper', 'coffe_maker', 'cards', 'mouse', 'kitchen_counter', 'cd', 'vase'] Task:Go to toilet response: | { Walk to the bathroom. Find the toilet. Lift the top of the toilet. Sit on the toilet. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['fork', 'pot', 'microwave', 'walllamp', 'bathroom', 'detergent', 'knifeblock', 'knife', 'clothes_underwear', 'kitchen_cabinet', 'floor', 'ceiling', 'phone', 'toaster', 'stovefan', 'plate', 'faucet', 'tvstand', 'wall', 'nightstand', 'oven', 'coffe_maker', 'drinking_glass', 'tray', 'kitchen_counter', 'cupboard', 'sink', 'spoon', 'home_office', 'dishwasher'] Task:Unload dishwasher response: { thoughts : 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., actions : ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[FIND] <drinking_glass>', '[GRAB] <drinking_glass>', '[FIND] <cupboard>', '[OPEN] <cupboard>', '[PUTBACK] <drinking_glass> <cupboard>', '[FIND] <fork>', '[GRAB] <fork>', '[FIND] <kitchen_cabinet>', '[OPEN] <kitchen_cabinet>', '[PUTIN] <fork> <kitchen_cabinet>', '[FIND] <knife>', '[GRAB] <knife>', '[PUTIN] <knife> <kitchen_cabinet>', '[FIND] <spoon>', '[GRAB] <spoon>', '[PUTIN] <spoon> <kitchen_cabinet>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTIN] <plate> <kitchen_cabinet>', '[CLOSE] <kitchen_cabinet>', '[CLOSE] <dishwasher>'] } Scene_Objects:['fork', 'chair', 'cloth_napkin', 'dog', 'nail_polish', 'dough', 'drawing', 'knife', 'hanger', 'bathroom_counter', 'floor', 'phone', 'computer', 'plate', 'bowl', 'food_kiwi', 'wall', 'bench', 'powersocket', 'cup', 'bed', 'video_game_controller', 'television', 'curtain', 'doorjamb', 'dresser', 'cupboard', 'door', 'table', 'light'] Task:Set up table response: | { Walk to dining room, walk to dining table, arrange chairs, set napkin, set plate, set knife, set fork and glass on table. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'food_salt', 'chair', 'walllamp', 'toothbrush', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'remote_control', 'computer', 'toaster', 'mat', 'tvstand', 'ceilinglamp', 'oil', 'closetdrawer', 'couch', 'food_jam', 'pillow', 'food_kiwi', 'wall', 'photoframe', 'check', 'television', 'doorjamb', 'dresser', 'door'] Task:Change TV channel response: { thoughts : Walk to living room. Walk to and sit at the sofa. Grab remote control and switch on TV., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>'] } Scene_Objects:['toilet', 'dog', 'walllamp', 'bathroom', 'orchid', 'longboard', 'floor', 'phone', 'desk', 'bookshelf', 'keyboard', 'food_bacon', 'table_cloth', 'bookmark', 'piano_bench', 'shower', 'floor_lamp', 'homework', 'mousepad', 'food_kiwi', 'bed', 'photoframe', 'curtain', 'doorjamb', 'kitchen_counter', 'dishrack', 'dresser', 'napkin', 'table', 'dishwasher'] Task:Turn on light response: | { Turning on lights } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'juice', 'tea', 'toilet', 'freezer', 'walllamp', 'dough', 'drawing', 'food_egg', 'floor', 'dvd_player', 'character', 'alcohol', 'stovefan', 'mat', 'shower', 'closetdrawer', 'clothes_hat', 'food_jam', 'wall', 'powersocket', 'curtain', 'doorjamb', 'mouse', 'kitchen_counter', 'laundry_detergent', 'door', 'light', 'dishwasher', 'table'] Task:Go to toilet response: { thoughts : I walk to the entrance of the bathroom. I turn to the door. I open the door to the bathroom. I walk inside of the bathroom. I find the toilet inside of the bathroom and walk over to it. I turn and look at the toilet., actions : ['[WALK] <bathroom>', '[WALK] <toilet>', '[FIND] <toilet>', '[TURNTO] <toilet>', '[LOOKAT] <toilet>', '[WALK] <toilet>', '[TURNTO] <toilet>'] } Scene_Objects:['fork', 'water_glass', 'pot', 'freezer', 'walllamp', 'bathroom', 'food_butter', 'food_carrot', 'milk', 'knifeblock', 'knife', 'floor', 'ceiling', 'mail', 'computer', 'stovefan', 'ceilinglamp', 'brush', 'faucet', 'wall', 'nightstand', 'cutting_board', 'cup', 'photoframe', 'water', 'pencil', 'kitchen_counter', 'cupboard', 'sink', 'soap'] Task:Drink response: | { I enter the kitchen and grab a waterglass from the cupboard. I open the fridge and grap some water. I pour the water into the cup and drink it. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['scissors', 'microwave', 'toilet', 'walllamp', 'drawing', 'bills', 'wallshelf', 'floor', 'ceiling', 'character', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'couch', 'pillow', 'dining_room', 'wall', 'nightstand', 'oven', 'bench', 'television', 'tray', 'curtain', 'towel_rack', 'pencil', 'kitchen_counter', 'bathtub', 'spoon', 'table'] Task:Watch TV response: { thoughts : Walk to the room, in which the TV is located. Turn on TV pressing the power button for the TV. Watch TV., actions : ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>'] } Scene_Objects:['sponge', 'tablelamp', 'microwave', 'chair', 'trashcan', 'ceilingfan', 'drawing', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'balanceball', 'mousepad', 'wall', 'nightstand', 'bench', 'cup', 'doorjamb', 'mouse', 'address_book', 'hairbrush', 'hairdryer', 'light', 'creditcard'] Task:Work response: | { Walk to home office. Walk to computer. Switch on computer. Open the address book. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tea', 'cat', 'drawing', 'bills', 'bathroom_counter', 'floor', 'ceiling', 'character', 'bedroom', 'mail', 'alcohol', 'mat', 'faucet', 'clothes_pants', 'pillow', 'wall', 'wall_clock', 'oven', 'pasta', 'bench', 'coffee_filter', 'ice', 'paper_towel', 'conditioner', 'sink', 'bathroom_cabinet', 'clothes_skirt', 'soap', 'hands_both', 'shoe_rack'] Task:Wash hands response: { thoughts : I walk to the bathroom and find the sink. I grab the soap and rub some on my hands. I turn the faucet on and put my hands in the water. I rinse my hands and then turn off the faucet. Then I dry my hands on a paper towel., actions : ['[WALK] <bathroom>', '[WALK] <sink>', '[FIND] <sink>', '[FIND] <soap>', '[GRAB] <soap>', '[FIND] <hands_both>', '[SCRUB] <hands_both>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[RINSE] <hands_both>', '[FIND] <paper_towel>', '[GRAB] <paper_towel>', '[WIPE] <hands_both>'] } 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: | { 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. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['filing_cabinet', 'mop', 'microwave', 'toilet', 'chair', 'dog', 'walllamp', 'floor', 'desk', 'bookshelf', 'keyboard', 'mat', 'plate', 'shower', 'window', 'bowl', 'wall', 'nightstand', 'powersocket', 'cutting_board', 'shelf', 'check', 'food_food', 'cards', 'towel_rack', 'kitchen_counter', 'maindoor', 'table', 'vase', 'dirt'] Task:Go to toilet response: { thoughts : Walk to the bathroom. Find the toilet. Lift the top of the toilet. Sit on the toilet., actions : ['[WALK] <bathroom>', '[WALK] <toilet>', '[FIND] <toilet>', '[OPEN] <toilet>', '[SIT] <toilet>'] } Scene_Objects:['blender', 'food_ice_cream', 'microwave', 'toilet', 'freezer', 'ceilingfan', 'knife', 'character', 'desk', 'bookshelf', 'table_cloth', 'stovefan', 'mat', 'tvstand', 'couch', 'candle', 'clothes_pants', 'food_orange', 'wall', 'nightstand', 'bench', 'tape', 'check', 'curtain', 'doorjamb', 'dishrack', 'clothes_dress', 'food_steak', 'scrabble', 'coffee'] Task:Read book response: | { Pick up the book, open to current page, read the words. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'toilet', 'freezer', 'food_butter', 'knife', 'floor', 'table_cloth', 'toaster', 'plate', 'faucet', 'stereo', 'dish_soap', 'oil', 'wall', 'wall_clock', 'oven', 'powersocket', 'cutting_board', 'cup', 'coffe_maker', 'food_food', 'coffee_filter', 'wooden_spoon', 'tray', 'kitchen_counter', 'sink', 'dishwasher', 'laser_pointer'] 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:['spectacles', 'pot', 'food_ice_cream', 'measuring_cup', 'chair', 'freezer', 'knifeblock', 'hanger', 'floor', 'ceiling', 'phone', 'food_cake', 'computer', 'toaster', 'tvstand', 'food_noodles', 'couch', 'wall', 'powersocket', 'toy', 'tray', 'after_shave', 'doorjamb', 'chessboard', 'dresser', 'cupboard', 'hairbrush', 'door', 'napkin', 'light'] Task:Turn on light response: | { walk into living room, walk to light, turn 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:['dry_pasta', 'scissors', 'crayon', 'toilet', 'jelly', 'walllamp', 'nail_polish', 'detergent', 'food_cake', 'alcohol', 'piano_bench', 'toaster', 'food_noodles', 'garbage_can', 'pillow', 'broom', 'oven', 'toy', 'food_vegetable', 'food_food', 'television', 'oven_mitts', 'doorjamb', 'pencil', 'headset', 'sink', 'bathroom_cabinet', '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:['microwave', 'toilet', 'ground_coffee', 'bathroom', 'trashcan', 'food_butter', 'knifeblock', 'needle', 'floor', 'ceiling', 'character', 'clothes_jacket', 'toaster', 'ceilinglamp', 'balanceball', 'mousepad', 'broom', 'wall', 'pasta', 'photoframe', 'coffe_maker', 'coffee_filter', 'water', 'rag', 'coffee_pot', 'laundry_detergent', 'maindoor', 'napkin', 'table', 'dishwasher'] Task:Make coffee response: | { Walk to Kitchen and find coffee maker, find coffee filter and place it in coffee maker. Find ground coffee and water. put both in coffee maker. Close the coffee maker and switch it on. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'freezer', 'walllamp', 'knifeblock', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'bedroom', 'bookshelf', 'plate', 'faucet', 'drying_rack', 'dish_soap', 'couch', 'dining_room', 'wall', 'oven', 'newspaper', 'photoframe', 'check', 'toilet_paper', 'kitchen_counter', 'cupboard', 'sink', 'bathtub', 'table'] Task:Wash dishes by hand response: { thoughts : I walk in to the Kitchen. I find a plate, a sponge, and the dish soap. I find the faucet. I turn the faucet on. I pour water on the sponge and plate. I add dish soap to the sponge. I put the dish soap back. I scrub the plate. I rinse the plate. I place the plate on the drying rack. I rinse the sponge. I turn the faucet off., actions : ['[WALK] <dining_room>', '[WALK] <faucet>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <sponge>', '[GRAB] <sponge>', '[RINSE] <sponge>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[POUR] <dish_soap> <sponge>', '[PUTOBJBACK] <dish_soap>', '[FIND] <plate>', '[GRAB] <plate>', '[WASH] <plate>', '[RINSE] <plate>', '[FIND] <drying_rack>', '[PUTBACK] <plate> <plate>', '[RINSE] <sponge>', '[PUTOBJBACK] <sponge>', '[SWITCHOFF] <faucet>'] } Scene_Objects:['microwave', 'chair', 'detergent', 'cat', 'drawing', 'floor', 'stamp', 'computer', 'ceilinglamp', 'mat', 'balanceball', 'picture', 'window', 'foundation', 'faucet', 'couch', 'pillow', 'wall', 'powersocket', 'oven', 'mouthwash', 'television', 'ice', 'centerpiece', 'towel_rack', 'mouse', 'kitchen_counter', 'dresser', 'table', 'dishwasher'] Task:Pet cat response: | { I walk into the living room. I see my cat on the couch. I go sit next to the cat on the couch. I pet the cat on the back. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'juice', 'toilet', 'freezer', 'knifeblock', 'drawing', 'hanger', 'floor', 'ceiling', 'bedroom', 'keyboard', 'computer', 'mat', 'shower', 'dining_room', 'nightstand', 'wall', 'powersocket', 'oven', 'photoframe', 'newspaper', 'food_food', 'curtain', 'doorjamb', 'cupboard', 'door', 'napkin', 'home_office', 'light', 'instrument_guitar'] Task:Put groceries in Fridge response: { thoughts : Walk to the kitchen. Open the fridge, take the groceries and put in it. Closed 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:['sheets', 'glue', 'toilet', 'chair', 'bathroom', 'drawing', 'longboard', 'floor', 'ceiling', 'food_cake', 'mat', 'ceilinglamp', 'shower', 'deck_of_cards', 'balanceball', 'shoe-shine_kit', 'tvstand', 'candle', 'food_kiwi', 'wall', 'nightstand', 'powersocket', 'bench', 'food_cheese', 'novel', 'coffe_maker', 'curtain', 'towel_rack', 'home_office', 'dishwasher'] Task:Take shower response: | { Walk to the bathroom and wash with the shower. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'food_pizza', 'tea', 'toilet', 'walllamp', 'nail_polish', 'cpuscreen', 'floor', 'phone', 'ceiling', 'keyboard', 'toaster', 'mat', 'oil', 'pillow', 'bowl', 'wall', 'powersocket', 'oven', 'photoframe', 'television', 'rag', 'doorjamb', 'headset', 'door', 'sink', 'home_office', 'light', 'bathroom_cabinet', 'coffee'] Task:Turn light off response: { thoughts : Put the light switch into the down, or off, position., actions : ['[WALK] <dining_room>', '[WALK] <light>', '[FIND] <light>', '[SWITCHOFF] <light>'] } Scene_Objects:['food_salt', 'freezer', 'ceilingfan', 'clothes_underwear', 'bathroom_counter', 'phone', 'keyboard', 'computer', 'table_cloth', 'mop_bucket', 'tvstand', 'mousepad', 'candle', 'clothes_pants', 'basket_for_clothes', 'cup', 'bed', 'food_food', 'curtain', 'kettle', 'mouse', 'kitchen_counter', 'shoes', 'controller', 'clothes_dress', 'clothes_scarf', 'light', 'soap', 'clothes_shirt', 'washing_machine'] Task:Wash clothes response: | { I need to get the dirty clothes basket. Walk to bathroom. Put all the clothes in washing machine. Add soap. Turn on 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:['dry_pasta', 'pot', 'food_pizza', 'toilet', 'freezer', 'nail_polish', 'detergent', 'longboard', 'floor', 'ceiling', 'bedroom', 'computer', 'ceilinglamp', 'tvstand', 'faucet', 'mousepad', 'couch', 'food_peanut_butter', 'form', 'wall', 'nightstand', 'oven', 'food_food', 'ice', 'after_shave', 'doorjamb', 'lighter', 'coffee_pot', 'mouse', 'spoon'] Task:Put groceries in Fridge response: { thoughts : Put groceries into the fridge, actions : ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <food_food>', '[GRAB] <food_food>', '[PUTIN] <food_food> <freezer>', '[CLOSE] <freezer>'] } Scene_Objects:['food_salt', 'chair', 'walllamp', 'bills', 'hanger', 'longboard', 'floor', 'ceiling', 'phone', 'bathroom_counter', 'computer', 'tvstand', 'form', 'towel', 'wall', 'oven', 'photoframe', 'clothes_gloves', 'bed', 'food_food', 'doorjamb', 'towel_rack', 'dishrack', 'dresser', 'cupboard', 'door', 'light', 'table', 'colander', 'instrument_violin'] Task:Pick up phone response: | { I walk over to the phone and pick it up. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['food_ice_cream', 'microwave', 'toilet', 'chair', 'knifeblock', 'hanger', 'floor', 'toaster', 'stovefan', 'shoe-shine_kit', 'faucet', 'homework', 'food_noodles', 'mousepad', 'couch', 'wall', 'nightstand', 'powersocket', 'cup', 'newspaper', 'coffee_filter', 'food_rice', 'console', 'mouse', 'kitchen_counter', 'dishrack', 'comb', 'cupboard', 'door', 'sink'] Task:Drink response: { thoughts : go to the kitchen, walk to the cabinet, pic up a glass. carry the glass to the sink. turn on the water and fill up the glass. drink the water., actions : ['[WALK] <dining_room>', '[WALK] <sink>', '[FIND] <cup>', '[GRAB] <cup>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <cup>', '[DRINK] <cup>'] } Scene_Objects:['sheets', 'tablelamp', 'chair', 'freezer', 'trashcan', 'ceilingfan', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'character', 'desk', 'keyboard', 'bookshelf', 'computer', 'stovefan', 'ceilinglamp', 'balanceball', 'window', 'mousepad', 'wall', 'nightstand', 'bench', 'photoframe', 'mouthwash', 'doorjamb', 'mouse', 'pencil', 'light'] Task:Write an email response: | { Find the computer. Turn on the computer. Open the e-mail program. Create a new message. Write the message. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', '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: { thoughts : Cut up veggies with knife, actions : ['[WALK] <dining_room>', '[WALK] <kitchen_cabinet>', '[FIND] <kitchen_cabinet>', '[OPEN] <kitchen_cabinet>', '[FIND] <knife>', '[GRAB] <knife>', '[FIND] <cutting_board>', '[GRAB] <cutting_board>', '[CLOSE] <kitchen_cabinet>', '[WALK] <table>', '[PUTBACK] <knife> <table>', '[PUTBACK] <cutting_board> <table>', '[WALK] <freezer>', '[OPEN] <freezer>', '[FIND] <food_vegetable>', '[GRAB] <food_vegetable>', '[CLOSE] <freezer>', '[WALK] <table>', '[PUTBACK] <food_vegetable> <cutting_board>', '[GRAB] <knife>', '[CUT] <food_vegetable>', '[PUTOBJBACK] <knife>'] } Scene_Objects:['food_pizza', 'juice', 'food_salt', 'mop', 'jelly', 'ceilingfan', 'drawing', 'ceiling', 'character', 'desk', 'food_bacon', 'faucet', 'balanceball', 'powersocket', 'cutting_board', 'cup', 'coffe_maker', 'food_food', 'ice', 'tray', 'cards', 'towel_rack', 'hairbrush', 'cupboard', 'dresser', 'controller', 'door', 'napkin', 'home_office', 'vase'] Task:Pet cat response: | { I go looking for the cat in the living room where he usually sleeps. Once I find the cat I just pet him for a few minutes. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['walllamp', 'ceilingfan', 'drawing', 'needle', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'homework', 'clothes_socks', 'couch', 'pillow', 'wall', 'powersocket', 'food_cheese', 'bed', 'television', 'wooden_spoon', 'curtain', 'doorjamb', 'bathroom_cabinet', 'table', 'laser_pointer'] Task:Watch TV response: { thoughts : Walk into the living room. Sit down on the sofa. Pick up the remote control. Turn on the television with the remote control. Put down the remote control. Watch the television., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>', '[PUTOBJBACK] <remote_control>', '[TURNTO] <television>', '[WATCH] <television>'] } Scene_Objects:['freezer', 'cat', 'drawing', 'knife', 'knifeblock', 'hanger', 'floor', 'bedroom', 'keyboard', 'computer', 'piano_bench', 'ceilinglamp', 'faucet', 'iron', 'window', 'mousepad', 'couch', 'form', 'dining_room', 'wall', 'oven', 'box', 'newspaper', 'bed', 'novel', 'toilet_paper', 'television', 'tray', 'sink', 'table'] Task:Pet cat response: | { I walk to the living room. I locate the cat. I walk to the couch and sit down beside the cat. I pet the cat. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['filing_cabinet', 'tablelamp', 'chair', 'walllamp', 'drawing', 'needle', 'cpuscreen', 'bills', 'floor', 'ceiling', 'phone', 'desk', 'bookshelf', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'mousepad', 'tooth_paste', 'couch', 'pillow', 'towel', 'wall', 'nightstand', 'powersocket', 'television', 'coin', 'razor', 'doorjamb', 'centerpiece', 'mouse', 'door', 'light', 'board_game'] 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:['fork', 'beer', 'toilet', 'chair', 'ceilingfan', 'drawing', 'cpuscreen', 'longboard', 'floor', 'ceiling', 'folder', 'desk', 'remote_control', 'ceilinglamp', 'tvstand', 'balanceball', 'iron', 'window', 'couch', 'microphone', 'wall', 'bench', 'light_bulb', 'television', 'curtain', 'food_steak', 'sink', 'napkin', 'home_office', 'table'] Task:Watch TV response: | { I walk into my living room, find the remote and sit on my sofa. I look at the remote and switch on the television. I look at the Television. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'tablelamp', 'microwave', 'walllamp', 'detergent', 'knifeblock', 'floor', 'ceiling', 'keyboard', 'food_cake', 'computer', 'mat', 'faucet', 'mousepad', 'bowl', 'wall', 'nightstand', 'oven', 'bench', 'box', 'check', 'coffee_filter', 'tray', 'doorjamb', 'towel_rack', 'kitchen_counter', 'cupboard', 'sink', 'bathroom_cabinet', 'home_office'] Task:Wipe down sink response: { thoughts : Use a cloth to wipe the edge of the sink. Then wipe the bowl of the sink as well., actions : ['[WALK] <dining_room>', '[WALK] <rag>', '[FIND] <rag>', '[GRAB] <rag>', '[WALK] <sink>', '[WIPE] <sink>', '[PUTOBJBACK] <rag>'] } Scene_Objects:['dry_pasta', 'mop', 'microwave', 'trashcan', 'food_egg', 'keyboard', 'mop_bucket', 'bookmark', 'mat', 'tvstand', 'mousepad', 'tooth_paste', 'food_noodles', 'food_jam', 'form', 'pillow', 'dining_room', 'food_kiwi', 'toy', 'keys', 'check', 'mouthwash', 'coffee_filter', 'shaving_cream', 'comb', 'maindoor', 'light', 'board_game', 'teeth', 'creditcard'] Task:Pick up phone response: | { walk to living room, walk to the phone reach for the phone and 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:['filing_cabinet', 'detergent', 'cat', 'drawing', 'bills', 'wallshelf', 'cpuscreen', 'phone', 'character', 'shower', 'food_orange', 'form', 'pillow', 'nightstand', 'photoframe', 'food_food', 'tray', 'lighter', 'shaving_cream', 'mouse', 'towel_rack', 'dishrack', 'laundry_detergent', 'spoon', 'bathroom_cabinet', 'light', 'home_office', 'soap', 'instrument_violin', 'shoe_rack'] Task:Pet cat response: { thoughts : Go into the living room and pet the cat, actions : ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[WALK] <cat>', '[TURNTO] <cat>', '[LOOKAT] <cat>', '[TOUCH] <cat>', '[TOUCH] <cat>', '[TOUCH] <cat>'] } Scene_Objects:['toilet', 'freezer', 'ceilingfan', 'dough', 'drawing', 'longboard', 'floor', 'ceiling', 'character', 'remote_control', 'table_cloth', 'stovefan', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'homework', 'couch', 'food_orange', 'bowl', 'wall', 'television', 'toothbrush_holder', 'tray', 'curtain', 'food_onion', 'mouse', 'door', 'home_office', 'table'] Task:Change TV channel response: | { I push my body to be near to the table in front of me, without stand up. I move my right hand to near the TV remote control on the table. I take the TV remote control. I look the number on the remote control. I touch number 3 button. I put back the remote control to the table. I put my body back to the sofa } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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:['spectacles', 'drawing', 'knife', 'orchid', 'hanger', 'floor', 'keyboard', 'purse', 'bookshelf', 'mail', 'toaster', 'ceilinglamp', 'shower', 'balanceball', 'window', 'couch', 'clothes_pants', 'wall', 'oven', 'powersocket', 'television', 'coin', 'diary', 'cd', 'dresser', 'hairbrush', 'hair', 'conditioner', 'table', 'soap'] Task:Relax on sofa response: | { Open coffee maker. Put filter in main basket, put ground coffee in filter, fill reservoir with water, turn on coffee maker. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['dry_pasta', 'filing_cabinet', 'food_pizza', 'measuring_cup', 'microwave', 'nail_polish', 'bathroom', 'dough', 'bills', 'bathroom_counter', 'food_bacon', 'table_cloth', 'stovefan', 'ceilinglamp', 'tvstand', 'stereo', 'window', 'pillow', 'nightstand', 'bench', 'bed', 'clothes_gloves', 'keys', 'television', 'food_rice', 'lighter', 'cd', 'chessboard', 'table', 'light'] Task:Listen to music response: { thoughts : Walk into living room. Turn on radio., actions : ['[WALK] <home_office>', '[WALK] <stereo>', '[FIND] <stereo>', '[SWITCHON] <stereo>'] } Scene_Objects:['toilet', 'cat', 'ceilingfan', 'food_butter', 'drawing', 'longboard', 'floor', 'ceiling', 'shampoo', 'remote_control', 'ceilinglamp', 'tvstand', 'balanceball', 'stereo', 'window', 'couch', 'clothes_pants', 'wall', 'wall_clock', 'bench', 'television', 'curtain', 'kettle', 'towel_rack', 'hair', 'pajamas', 'maindoor', 'home_office', 'table', 'vase'] Task:Change TV channel response: | { Changing 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:['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:['scissors', 'microwave', 'dog', 'freezer', 'nail_polish', 'trashcan', 'knifeblock', 'floor', 'shower', 'picture', 'window', 'microphone', 'dining_room', 'broom', 'nightstand', 'photoframe', 'bed', 'clothes_gloves', 'lighter', 'console', 'pencil', 'kitchen_counter', 'cd', 'hair', 'maindoor', 'door', 'food_steak', 'home_office', 'table', 'sink'] Task:Read book response: | { Walk to living room. Find book. Grab book. Open book. Read book. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'food_pizza', 'chair', 'cat', 'drawing', 'floor', 'tea_bag', 'bookshelf', 'thread', 'toaster', 'ceilinglamp', 'stovefan', 'window', 'couch', 'food_orange', 'wall', 'food_food', 'television', 'oven_mitts', 'food_onion', 'curtain', 'after_shave', 'comb', 'napkin', 'home_office', 'table', 'dishwasher', 'bathroom_cabinet', 'laser_pointer', 'scrabble'] Task:Relax on sofa response: { thoughts : go to the living room,find the sofa,sat down in the sofa,take some relaxation., actions : ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>'] } Scene_Objects:['filing_cabinet', 'tablelamp', 'measuring_cup', 'walllamp', 'ceilingfan', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'clothes_socks', 'food_noodles', 'couch', 'broom', 'wall', 'newspaper', 'light_bulb', 'novel', 'television', 'curtain', 'doorjamb', 'lighter', 'cupboard', 'table', 'light'] Task:Change TV channel response: | { Walk to the living room. Find remote control. Grab remote control. Walk to television. Look at 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:['tablelamp', 'blender', 'mop', 'bathroom', 'cat', 'trashcan', 'knifeblock', 'stamp', 'button', 'piano_bench', 'faucet', 'mousepad', 'bowl', 'nightstand', 'wall_clock', 'oven', 'wall', 'bench', 'photoframe', 'novel', 'food_food', 'coffe_maker', 'curtain', 'pencil', 'shoes', 'hairbrush', 'hair', 'instrument_guitar', 'dishwasher', 'tooth_paste'] Task:Read book response: { thoughts : pick up the book open the book and read, actions : ['[WALK] <bedroom>', '[WALK] <novel>', '[GRAB] <novel>', '[READ] <novel>'] } Scene_Objects:['ceilingfan', 'trashcan', 'drawing', 'clothes_underwear', 'floor', 'ceiling', 'phone', 'keyboard', 'button', 'stovefan', 'ceilinglamp', 'tvstand', 'balanceball', 'brush', 'window', 'couch', 'wall', 'pasta', 'newspaper', 'television', 'wine', 'curtain', 'lighter', 'diary', 'hairbrush', 'dresser', 'controller', 'laundry_detergent', 'hairdryer', 'table'] Task:Watch TV response: | { I walk to the living room. I reach for the remote. I push the on button on the remote. I sit down on the couch and 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:['food_bread', 'freezer', 'walllamp', 'trashcan', 'food_carrot', 'cpuscreen', 'floor', 'ceiling', 'folder', 'bedroom', 'character', 'ceilinglamp', 'tvstand', 'faucet', 'dustpan', 'dining_room', 'wall', 'nightstand', 'oven', 'bench', 'photoframe', 'bed', 'food_food', 'television', 'food_donut', 'food_rice', 'doorjamb', 'shaving_cream', 'table', 'vase'] Task:Put groceries in Fridge response: { thoughts : walk to kitchen and seprate the groceries and arrange in fridge., actions : ['[WALK] <dining_room>', '[WALK] <food_food>', '[FIND] <food_food>', '[GRAB] <food_food>', '[FIND] <freezer>', '[OPEN] <freezer>', '[PUTIN] <food_food> <freezer>'] } Scene_Objects:['sponge', 'beer', 'dog', 'freezer', 'trashcan', 'ceilingfan', 'food_carrot', 'bills', 'hanger', 'longboard', 'floor', 'ceiling', 'thread', 'mail', 'stovefan', 'ceilinglamp', 'toaster', 'faucet', 'couch', 'wall', 'bench', 'powersocket', 'food_food', 'check', 'doorjamb', 'towel_rack', 'pencil', 'cupboard', 'door', 'table'] Task:Put groceries in Fridge response: | { Find groceries. Grab groceries. Walk to refrigerator. Open refrigerator door. Place groceries into refrigerator. Close refrigerator 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:['filing_cabinet', 'cat', 'ceilingfan', 'trashcan', 'drawing', 'orchid', 'floor', 'ceiling', 'dvd_player', 'remote_control', 'button', 'ceilinglamp', 'tvstand', 'balanceball', 'shower', 'window', 'foundation', 'oil', 'couch', 'towel', 'wall', 'pasta', 'powersocket', 'television', 'curtain', 'doorjamb', 'shoes', 'pajamas', 'maindoor', 'table'] Task:Change TV channel response: { thoughts : I go to the livingroom. The TV is on. I pick up the remote and press the next channel button. I look at the television, and see that the channel has changed., actions : ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[TURNTO] <television>', '[LOOKAT] <television>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <button>', '[PUSH] <button>', '[TURNTO] <television>', '[LOOKAT] <television>'] } Scene_Objects:['pot', 'tablelamp', 'food_ice_cream', 'microwave', 'freezer', 'bathroom', 'trashcan', 'cpuscreen', 'bathroom_counter', 'ceiling', 'keyboard', 'tvstand', 'teeth', 'wall', 'oven', 'bench', 'toy', 'bed', 'photoframe', 'coffe_maker', 'food_food', 'television', 'food_donut', 'water', 'tray', 'doorjamb', 'towel_rack', 'dresser', 'door', 'hands_both'] Task:Wash hands response: | { walk to bathroom, look at the water, 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:['filing_cabinet', 'detergent', 'cat', 'drawing', 'bills', 'wallshelf', 'cpuscreen', 'phone', 'character', 'shower', 'food_orange', 'form', 'pillow', 'nightstand', 'photoframe', 'food_food', 'tray', 'lighter', 'shaving_cream', 'mouse', 'towel_rack', 'dishrack', 'laundry_detergent', 'spoon', 'bathroom_cabinet', 'light', 'home_office', 'soap', 'instrument_violin', 'shoe_rack'] Task:Pet cat response: { thoughts : Go into the living room and pet the cat, actions : ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[WALK] <cat>', '[TURNTO] <cat>', '[LOOKAT] <cat>', '[TOUCH] <cat>', '[TOUCH] <cat>', '[TOUCH] <cat>'] } Scene_Objects:['filing_cabinet', 'walllamp', 'ceilingfan', 'milk', 'drawing', 'orchid', 'food_egg', 'ceiling', 'phone', 'keyboard', 'food_cake', 'remote_control', 'table_cloth', 'mop_bucket', 'window', 'food_kiwi', 'light_bulb', 'check', 'wooden_spoon', 'curtain', 'shaving_cream', 'pencil', 'hair', 'controller', 'clothes_dress', 'spoon', 'bag', 'home_office', 'dishwasher', 'vase'] Task:Change TV channel response: | { 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. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'chair', 'freezer', 'walllamp', 'knifeblock', 'clothes_underwear', 'floor', 'ceiling', 'character', 'stovefan', 'toaster', 'plate', 'ceilinglamp', 'faucet', 'pillow', 'wall', 'pasta', 'oven', 'cup', 'food_cheese', 'food_food', 'tray', 'curtain', 'kitchen_counter', 'sauce_pan', 'cupboard', 'sink', 'spoon', 'coffee'] 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:['crayon', 'microwave', 'toilet', 'freezer', 'ground_coffee', 'longboard', 'shampoo', 'character', 'thread', 'food_bacon', 'piano_bench', 'balanceball', 'stereo', 'window', 'picture', 'mousepad', 'pillow', 'toy', 'basket_for_clothes', 'photoframe', 'novel', 'coffe_maker', 'oven_mitts', 'colander', 'doorjamb', 'shaving_cream', 'dresser', 'soap', 'washing_machine', 'creditcard'] Task:Wash clothes response: | { walk to the bathroom, grab the basket for clothes, find soap, put in washing machine, turn 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:['fork', 'filing_cabinet', 'chair', 'dog', 'toothbrush', 'drawing', 'bills', 'ceiling', 'folder', 'desk', 'bedroom', 'remote_control', 'button', 'clothes_jacket', 'stovefan', 'mat', 'faucet', 'dining_room', 'broom', 'nightstand', 'wall', 'cutting_board', 'novel', 'mouse', 'kitchen_counter', 'cd', 'pajamas', 'sink', 'bathroom_cabinet', 'home_office'] Task:Change TV channel response: { thoughts : I pick up the remote. I press button on remote., actions : ['[WALK] <bedroom>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <button>', '[PUSH] <button>'] } Scene_Objects:['filing_cabinet', 'trashcan', 'dough', 'orchid', 'knife', 'clothes_underwear', 'phone', 'tea_bag', 'envelope', 'mat', 'faucet', 'clothes_socks', 'clothes_pants', 'clothes_hat', 'bench', 'powersocket', 'basket_for_clothes', 'food_food', 'food_rice', 'tray', 'curtain', 'after_shave', 'doorjamb', 'pencil', 'laundry_detergent', 'bathroom_cabinet', 'table', 'light', 'clothes_shirt', 'washing_machine'] Task:Wash clothes response: | { I go to the bathroom and open the washing machine there. I take my laundry basket and put each item of laundry into the machine. Then I take the laundry detergent and pour some into the machine. Finally I close the machine and switch it on. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'chair', 'dog', 'drawing', 'wallshelf', 'cpuscreen', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'bookshelf', 'computer', 'tvstand', 'mousepad', 'closetdrawer', 'couch', 'food_orange', 'wall', 'powersocket', 'shelf', 'cup', 'doorjamb', 'console', 'mouse', 'shoes', 'dresser', 'bathtub', 'light'] Task:Turn on light response: { thoughts : I open the room door and press the light button on, actions : ['[WALK] <home_office>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>'] } Scene_Objects:['filing_cabinet', 'tablelamp', 'juice', 'cd_player', 'bathroom', 'trashcan', 'food_carrot', 'drawing', 'bathroom_counter', 'floor', 'longboard', 'character', 'bookmark', 'ceilinglamp', 'balanceball', 'window', 'couch', 'towel', 'wall', 'oven', 'bench', 'television', 'after_shave', 'towel_rack', 'door', 'sink', 'bathroom_cabinet', 'table', 'light', 'scrabble'] Task:Listen to music response: | { I go to the living room, switch on the CD player (then choose the music cd and insert into the player) and sit on the sofa } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'microwave', 'toilet', 'freezer', 'walllamp', 'trashcan', 'drawing', 'wallshelf', 'floor', 'ceiling', 'food_chicken', 'stovefan', 'mat', 'toaster', 'shower', 'faucet', 'window', 'closetdrawer', 'couch', 'wall', 'wall_clock', 'oven', 'coffe_maker', 'tray', 'doorjamb', 'mouse', 'kitchen_counter', 'cupboard', 'door', 'sink'] Task:Cook some food response: { thoughts : I walk in the kitchen, I open the fridge and remove the Chicken. I grab frying fan and put it on stove. I put chicken in the frying pan and I cook food., actions : ['[WALK] <dining_room>', '[WALK] <freezer>', '[FIND] <freezer>', '[OPEN] <freezer>', '[FIND] <food_chicken>', '[GRAB] <food_chicken>', '[FIND] <pot>', '[GRAB] <pot>', '[FIND] <oven>', '[PUTBACK] <pot> <oven>', '[PUTBACK] <food_chicken> <oven>'] } Scene_Objects:['sheets', 'fork', 'blender', 'food_ice_cream', 'food_butter', 'phone', 'character', 'bookshelf', 'brush', 'ceilinglamp', 'plate', 'shower', 'iron', 'stereo', 'toaster', 'oil', 'food_orange', 'pillow', 'cup', 'food_food', 'check', 'oven_mitts', 'food_donut', 'food_onion', 'after_shave', 'mouse', 'hairdryer', 'bag', 'bathroom_cabinet', 'home_office'] Task:Set up table response: | { Walk into kitchen, find plate, drop plate on table in living room, walk into kitchen, find cup, bring cup to table in living room, walk into kitchen find fork, bring fork to table in living room } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'crayon', 'chair', 'bathroom', 'food_butter', 'phone', 'ceiling', 'bedroom', 'tea_bag', 'laptop', 'ceilinglamp', 'shower', 'iron', 'clothes_socks', 'closetdrawer', 'clothes_pants', 'pillow', 'wall', 'powersocket', 'standingmirror', 'photoframe', 'toothbrush_holder', 'food_donut', 'curtain', 'doorjamb', 'towel_rack', 'pencil', 'controller', 'door', 'table'] Task:Switch on lamp response: { thoughts : Press the button so the light comes on., actions : ['[WALK] <bedroom>', '[WALK] <floor_lamp>', '[FIND] <floor_lamp>', '[SWITCHON] <floor_lamp>'] } Scene_Objects:['pot', 'walllamp', 'trashcan', 'drawing', 'knifeblock', 'cpuscreen', 'floor', 'ceiling', 'toaster', 'laptop', 'plate', 'stovefan', 'shower', 'dish_soap', 'wall', 'bench', 'oven', 'powersocket', 'photoframe', 'food_food', 'coffe_maker', 'tray', 'kettle', 'pencil', 'kitchen_counter', 'cupboard', 'home_office', 'table', 'dishwasher', 'coffee'] Task:Wash dishes with dishwasher response: | { Put the dishes on dinner table in the dishwasher and wash them } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['fork', 'pot', 'filing_cabinet', 'beer', 'bathroom', 'detergent', 'trashcan', 'cpuscreen', 'ceiling', 'bedroom', 'desk', 'keyboard', 'clothes_jacket', 'tvstand', 'couch', 'pillow', 'food_kiwi', 'oven', 'bench', 'coffe_maker', 'oven_mitts', 'towel_rack', 'pencil', 'cupboard', 'hair', 'clothes_dress', 'food_steak', 'napkin', 'vase', 'laser_pointer'] Task:Listen to music response: { thoughts : I walk into the bedroom. I walk to stereo. I turn on stereo., actions : ['[WALK] <bedroom>', '[WALK] <stereo>', '[SWITCHON] <stereo>'] } Scene_Objects:['pot', 'filing_cabinet', 'tablelamp', 'toilet', 'chair', 'freezer', 'food_egg', 'cpuscreen', 'floor', 'desk', 'tea_bag', 'keyboard', 'bookshelf', 'computer', 'alcohol', 'stovefan', 'laptop', 'picture', 'mousepad', 'dining_room', 'wall', 'nightstand', 'photoframe', 'bed', 'mouse', 'kitchen_counter', 'maindoor', 'home_office', 'light', 'clothes_skirt'] Task:Write an email response: | { walk to home office and switch on laptop and with the useof mouse and keyboard send mail } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'tablelamp', 'chair', 'ground_coffee', 'dough', 'knifeblock', 'needle', 'floor', 'ceiling', 'phone', 'mop_bucket', 'toaster', 'stovefan', 'tvstand', 'mat', 'food_peanut_butter', 'clothes_pants', 'pillow', 'dining_room', 'wall', 'nightstand', 'oven', 'coffe_maker', 'food_food', 'check', 'coffee_filter', 'water', 'pajamas', 'light', 'dishwasher'] Task:Make coffee response: | { I walk into the kitchen. I find the coffee maker and open it. I find the coffee filter, grab it and put it into the coffee maker. I find ground coffee, grab it and put it into the coffee maker. I find some water, then I pour it into the coffee maker. I close the coffee maker, I plug it in and I switch it on. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'freezer', 'walllamp', 'bathroom', 'hanger', 'phone', 'desk', 'bookshelf', 'ceilinglamp', 'shoe-shine_kit', 'balanceball', 'faucet', 'couch', 'nightstand', 'wall', 'bench', 'powersocket', 'clothes_gloves', 'check', 'television', 'food_onion', 'after_shave', 'curtain', 'shaving_cream', 'mouse', 'maindoor', 'sink', 'bag', 'home_office'] Task:Open front door response: { thoughts : Walk over to the front door, turn the knob, and open the door., actions : ['[WALK] <home_office>'] } Scene_Objects:['tablelamp', 'microwave', 'dough', 'drawing', 'knifeblock', 'floor', 'desk', 'bookshelf', 'ceilinglamp', 'tvstand', 'stereo', 'balanceball', 'mousepad', 'couch', 'food_orange', 'wall', 'powersocket', 'box', 'cup', 'basket_for_clothes', 'coffe_maker', 'television', 'food_rice', 'tray', 'doorjamb', 'console', 'food_steak', 'sink', 'napkin', 'table'] Task:Set up table response: | { walk to entrance hall. find a table. pull table. walk to living rook. push 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:['filing_cabinet', 'microwave', 'freezer', 'drawing', 'bills', 'hanger', 'floor', 'ceiling', 'keyboard', 'computer', 'toaster', 'tvstand', 'floor_lamp', 'window', 'closetdrawer', 'couch', 'towel', 'wall', 'wall_clock', 'food_food', 'doorjamb', 'mouse', 'headset', 'shoes', 'dresser', 'controller', 'bathtub', 'sink', 'home_office', 'light'] Task:Turn night light on response: { thoughts : I walk to the dresser and in the middle Io to small battery operated lamp and switch it on, actions : ['[WALK] <bedroom>', '[WALK] <dresser>', '[FIND] <floor_lamp>', '[TURNTO] <floor_lamp>', '[SWITCHON] <floor_lamp>'] } Scene_Objects:['scissors', 'chair', 'dog', 'bathroom', 'knifeblock', 'knife', 'bathroom_counter', 'longboard', 'folder', 'bedroom', 'desk', 'keyboard', 'food_cake', 'computer', 'plate', 'tvstand', 'shoe-shine_kit', 'homework', 'dish_soap', 'couch', 'form', 'powersocket', 'food_food', 'oven_mitts', 'water', 'tray', 'doorjamb', 'mouse', 'dishrack', 'clothes_scarf'] Task:Wash dishes by hand response: | { walk to kitchen, fins soap, arrange dishes, wash dishes } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'toilet', 'walllamp', 'orchid', 'knifeblock', 'wallshelf', 'floor', 'ceiling', 'character', 'video_game_console', 'bedroom', 'computer', 'button', 'table_cloth', 'tvstand', 'window', 'closetdrawer', 'couch', 'pillow', 'nightstand', 'wall', 'powersocket', 'box', 'video_game_controller', 'television', 'curtain', 'pencil', 'dresser', 'door', 'table'] Task:Play games response: { thoughts : Turn on the television. Turn on the video game system. Insert desired game into gaming system. Follow directions on game to and push needed buttons on video game remote controller., actions : ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <video_game_console>', '[SWITCHON] <video_game_console>', '[FIND] <video_game_controller>', '[GRAB] <video_game_controller>', '[FIND] <button>', '[PUSH] <button>', '[TURNTO] <television>', '[WATCH] <television>'] } Scene_Objects:['sheets', 'pot', 'glue', 'tablelamp', 'microwave', 'walllamp', 'knife', 'knifeblock', 'longboard', 'floor', 'phone', 'computer', 'toaster', 'plate', 'shoe-shine_kit', 'dish_soap', 'mousepad', 'food_orange', 'wall', 'nightstand', 'oven', 'toy', 'newspaper', 'coffe_maker', 'tray', 'vacuum_cleaner', 'dresser', 'hairdryer', 'dishwasher', 'vase'] Task:Wash dishes with dishwasher response: | { Walk to the kitchen. Open the dishwasher. Put plates into the dishwasher. Put dish soap into the dishwasher. Close the dishwasher. Turn on the dishwasher. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'walllamp', 'needle', 'wallshelf', 'cpuscreen', 'hanger', 'bedroom', 'keyboard', 'bookmark', 'stovefan', 'shower', 'oil', 'dining_room', 'wall', 'powersocket', 'bench', 'love_seat', 'standingmirror', 'novel', 'coffe_maker', 'check', 'after_shave', 'towel_rack', 'mouse', 'pencil', 'kitchen_counter', 'maindoor', 'bathtub', 'soap'] Task:Read book response: { thoughts : Obtain a book from the book shelf. Sit in the easy chair. Read the book. Mark the stopping point with a bookmark. Put the book back on the book shelf., actions : ['[WALK] <home_office>', '[WALK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[FIND] <love_seat>', '[SIT] <love_seat>', '[READ] <novel>', '[FIND] <bookmark>', '[GRAB] <bookmark>', '[PUTBACK] <bookmark> <novel>', '[PUTOBJBACK] <novel>'] } Scene_Objects:['filing_cabinet', 'toilet', 'walllamp', 'bathroom', 'drawing', 'orchid', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'character', 'desk', 'bookshelf', 'keyboard', 'computer', 'stovefan', 'mat', 'floor_lamp', 'electric_shaver', 'wall', 'nightstand', 'powersocket', 'bed', 'doorjamb', 'shoes', 'hairbrush', 'door', 'light', 'table', 'soap'] Task:Turn on light response: | { walk to wall, find light switch, turn on lights } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['walllamp', 'orchid', 'drawing', 'wallshelf', 'floor', 'ceiling', 'phone', 'bookshelf', 'remote_control', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'shower', 'window', 'couch', 'clothes_hat', 'pillow', 'wall', 'nightstand', 'powersocket', 'photoframe', 'newspaper', 'television', 'curtain', 'doorjamb', 'door', 'home_office', 'light', 'table'] Task:Watch TV response: { thoughts : walk to living room. look at remote control. grab remote control. plug in television. switch on television. lie in sofa. point at remote control. watch television., actions : ['[WALK] <home_office>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[TURNTO] <remote_control>', '[LOOKAT] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[PLUGIN] <television>', '[SWITCHON] <television>', '[FIND] <couch>', '[LIE] <couch>', '[TURNTO] <remote_control>', '[POINTAT] <remote_control>', '[TURNTO] <television>', '[WATCH] <television>'] } Scene_Objects:['sheets', 'measuring_cup', 'microwave', 'freezer', 'ceilingfan', 'milk', 'floor', 'ceiling', 'character', 'bedroom', 'computer', 'button', 'toaster', 'faucet', 'picture', 'wall', 'nightstand', 'oven', 'photoframe', 'clothes_gloves', 'coffe_maker', 'food_food', 'curtain', 'centerpiece', 'food_sugar', 'vacuum_cleaner', 'chessboard', 'coffee_cup', 'dishwasher', 'light'] Task:Make coffee response: | { walk to kitchen, look at the coffee maker, open the coffee maker, find milk, suger and water, mix that all, put into coffee maker, switch on the coffee maker, wait for few mins, push the coffee button in coffee maker, we get coffee in coffee cup, drink coffee } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'filing_cabinet', 'band-aids', 'freezer', 'nail_polish', 'bathroom', 'cat', 'orchid', 'cpuscreen', 'phone', 'character', 'keyboard', 'mat', 'faucet', 'wall', 'oven', 'bed', 'keys', 'coffe_maker', 'mouthwash', 'food_onion', 'curtain', 'centerpiece', 'console', 'towel_rack', 'kitchen_counter', 'dresser', 'cupboard', 'door', 'home_office'] Task:Pet cat response: { thoughts : First I need to find the cat in the living room. Then I walk over to the cat and pet it gently., actions : ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[WALK] <cat>', '[TOUCH] <cat>'] } Scene_Objects:['sheets', 'tablelamp', 'microwave', 'toilet', 'chair', 'dog', 'walllamp', 'trashcan', 'cpuscreen', 'floor', 'ceiling', 'folder', 'desk', 'bookshelf', 'keyboard', 'thread', 'computer', 'mail', 'bookmark', 'mousepad', 'wall', 'nightstand', 'photoframe', 'novel', 'toilet_paper', 'tray', 'towel_rack', 'mouse', 'door', 'light'] Task:Read book response: | { Walk to the living room. Find a desk and grab a book. Walk to the chair, sit in the chair and 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:['blender', 'chair', 'dog', 'bathroom', 'drawing', 'orchid', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'folder', 'desk', 'computer', 'ceilinglamp', 'window', 'mousepad', 'couch', 'towel', 'wall', 'cup', 'television', 'curtain', 'doorjamb', 'dresser', 'cupboard', 'door', 'sink', 'light', 'table'] Task:Relax on sofa response: { thoughts : I walk into the living room and turn on the light. I walk to the couch then sit on the couch., actions : ['[WALK] <home_office>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>', '[WALK] <couch>', '[SIT] <couch>'] } Scene_Objects:['dry_pasta', 'microwave', 'toilet', 'jelly', 'drawing', 'floor', 'ceiling', 'character', 'desk', 'bookshelf', 'ceilinglamp', 'deck_of_cards', 'stereo', 'shower', 'window', 'couch', 'candle', 'microphone', 'wall', 'powersocket', 'box', 'photoframe', 'television', 'tray', 'towel_rack', 'sink', 'napkin', 'bathroom_cabinet', 'table', 'home_office'] Task:Relax on sofa response: | { walk to living room, walk to sofa, sit on sofa. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['filing_cabinet', 'food_salt', 'chair', 'bathroom', 'knifeblock', 'orchid', 'cpuscreen', 'bathroom_counter', 'floor', 'phone', 'character', 'bedroom', 'desk', 'stovefan', 'ceilinglamp', 'mat', 'faucet', 'homework', 'mousepad', 'form', 'powersocket', 'bench', 'light_bulb', 'check', 'television', 'tray', 'curtain', 'chessboard', 'cupboard', 'home_office'] Task:Pick up phone response: { thoughts : I walk to the home office, find where the phone is and lift the reciever., actions : ['[WALK] <home_office>', '[WALK] <phone>', '[FIND] <phone>', '[GRAB] <phone>'] } Scene_Objects:['toilet', 'ceilingfan', 'drawing', 'floor', 'ceiling', 'bedroom', 'remote_control', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'mousepad', 'couch', 'dining_room', 'wall', 'wall_clock', 'powersocket', 'oven', 'television', 'toothbrush_holder', 'curtain', 'doorjamb', 'console', 'dresser', 'cupboard', 'home_office', 'table', 'clothes_skirt', 'vase'] Task:Watch TV response: | { 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:['pot', 'microwave', 'toilet', 'freezer', 'walllamp', 'trashcan', 'knifeblock', 'kitchen_cabinet', 'floor', 'ceiling', 'bathroom_counter', 'bookshelf', 'deck_of_cards', 'faucet', 'mousepad', 'pillow', 'wall', 'oven', 'box', 'cup', 'toilet_paper', 'rag', 'kitchen_counter', 'cupboard', 'sink', 'bag', 'bathroom_cabinet', 'bathtub', 'table', 'home_office'] Task:Drink response: { thoughts : I walk the kitchen and walk up to the kitchen cabinet. I open the cabinet and take out a cup. I walk to sink and I turn the faucet on using the cold water handle. I put my cup under the running water until it is full. I turn off the cold water handle and bring the cup to my mouth and take a drink., actions : ['[WALK] <dining_room>', '[WALK] <kitchen_cabinet>', '[FIND] <kitchen_cabinet>', '[OPEN] <kitchen_cabinet>', '[FIND] <cup>', '[GRAB] <cup>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[WALK] <sink>', '[FIND] <faucet>', '[PUSH] <faucet>', '[PUTBACK] <cup> <sink>', '[GRAB] <cup>', '[SWITCHOFF] <faucet>', '[DRINK] <cup>'] } Scene_Objects:['food_ice_cream', 'ceilingfan', 'drawing', 'longboard', 'floor', 'ceiling', 'phone', 'folder', 'character', 'computer', 'food_bacon', 'toaster', 'brush', 'ceilinglamp', 'balanceball', 'tvstand', 'stereo', 'oil', 'couch', 'wall', 'coffe_maker', 'coffee_filter', 'water', 'tray', 'rag', 'clothes_dress', 'bathroom_cabinet', 'dishwasher', 'coffee', 'shoe_rack'] Task:Make coffee response: | { I find the coffee machine, fill it with water and coffee then press the button to make the coffee } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'drawing', 'knife', 'orchid', 'hanger', 'floor', 'keyboard', 'purse', 'bookshelf', 'mail', 'toaster', 'ceilinglamp', 'shower', 'balanceball', 'window', 'couch', 'clothes_pants', 'wall', 'oven', 'powersocket', 'television', 'coin', 'diary', 'cd', 'dresser', 'hairbrush', 'hair', 'conditioner', 'table', 'soap'] 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', 'crayon', 'detergent', 'ceilingfan', 'food_carrot', 'milk', 'drawing', 'knifeblock', 'food_egg', 'floor', 'phone', 'desk', 'bookshelf', 'envelope', 'ceilinglamp', 'window', 'mousepad', 'couch', 'wall', 'food_cheese', 'novel', 'television', 'food_rice', 'after_shave', 'towel_rack', 'kitchen_counter', 'comb', 'table', 'dishwasher', 'creditcard'] Task:Relax on sofa response: | { I walk to the living room and find the sofa. I sit on the sofa and get comfortable. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'tea', 'microwave', 'chair', 'freezer', 'walllamp', 'milk', 'knifeblock', 'knife', 'drawing', 'floor', 'ceiling', 'shampoo', 'desk', 'bookshelf', 'stovefan', 'toaster', 'faucet', 'food_jam', 'pillow', 'wall', 'oven', 'powersocket', 'cup', 'photoframe', 'tray', 'kitchen_counter', 'cupboard', 'controller', 'sink'] Task:Get something to drink response: { thoughts : Walk into the kitchen and to the cupboard to get a cup, walk to the fridge to look for a beverage to enjoy, open the freezer and get ice, pour beverage and enjoy, actions : ['[WALK] <dining_room>', '[WALK] <cupboard>', '[FIND] <cupboard>', '[OPEN] <cupboard>', '[FIND] <cup>', '[GRAB] <cup>', '[CLOSE] <cupboard>', '[WALK] <freezer>', '[OPEN] <freezer>', '[FIND] <milk>', '[GRAB] <milk>', '[CLOSE] <freezer>', '[POUR] <milk> <cup>', '[DRINK] <cup>'] } Scene_Objects:['pot', 'ceilingfan', 'drawing', 'food_egg', 'floor', 'ceiling', 'bookshelf', 'remote_control', 'button', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'couch', 'food_jam', 'pillow', 'dining_room', 'wall', 'nightstand', 'photoframe', 'television', 'food_rice', 'curtain', 'kitchen_counter', 'hair', 'home_office', 'table', 'light', 'dishwasher', 'dirt'] Task:Change TV channel response: | { I go to the living room where the TV is located. I plug in the TV to the outlet. I search for the remote control. I point the remote control directly to the TV, turn it on and push the number of the channel that I want. } |
You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format [verb] <target1> <target2> , where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['microwave', 'chair', 'freezer', 'orchid', 'drawing', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'bookshelf', 'keyboard', 'food_cake', 'envelope', 'computer', 'ceilinglamp', 'window', 'mousepad', 'clothes_socks', 'closetdrawer', 'wall', 'toy', 'cup', 'coffe_maker', 'doorjamb', 'mouse', 'dresser', 'door', 'light', 'table'] Task:Browse internet response: { thoughts : I turn on computer. I use keyboard to type. I open browser. I search., actions : ['[WALK] <bedroom>', '[WALK] <computer>', '[FIND] <keyboard>', '[TYPE] <keyboard>', '[TURNTO] <computer>', '[LOOKAT] <computer>'] } 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: | { walk to phone, grab phone, pick up phone, put to 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:['glue', 'filing_cabinet', 'tablelamp', 'microwave', 'toilet', 'dog', 'walllamp', 'bathroom', 'knifeblock', 'food_egg', 'food_bacon', 'brush', 'mat', 'deck_of_cards', 'balanceball', 'tvstand', 'ceilinglamp', 'picture', 'couch', 'wall', 'tape', 'cup', 'toilet_paper', 'food_food', 'video_game_controller', 'water', 'cupboard', 'bathroom_cabinet', 'table', 'vase'] Task:Drink response: { thoughts : I go to the kitchen. I get a glass. I fill it with water. I take a drink from the glass., actions : ['[WALK] <dining_room>', '[WALK] <cup>', '[FIND] <cup>', '[GRAB] <cup>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <cup>', '[DRINK] <cup>'] } Scene_Objects:['dry_pasta', 'chair', 'ceilingfan', 'dough', 'hanger', 'longboard', 'floor', 'ceiling', 'phone', 'folder', 'bedroom', 'character', 'ceilinglamp', 'mat', 'balanceball', 'mousepad', 'wall', 'nightstand', 'box', 'check', 'television', 'doorjamb', 'pencil', 'vacuum_cleaner', 'dresser', 'cupboard', 'conditioner', 'door', 'light', 'table'] Task:Turn on light response: | { I walk into the kitchen, I find the light switch, and then i switch on the lights in the kitchen. } |
Subsets and Splits