Datasets:

Barrybw

/

ustc_test

like 0

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'toilet', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'mat', 'mousepad', 'closetdrawer', 'wall', 'nightstand', 'powersocket', 'check', 'television', 'wine', 'doorjamb', 'mouse', 'kitchen_counter', 'dresser', 'light', 'table', 'clothes_skirt'] Task:Write an email response: { "thoughts": enter office, find computer, turn it on,, "actions": ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <keyboard>', '[TOUCH] <keyboard>', '[TYPE] <keyboard>'] }

Scene_Objects:['sheets', 'toilet', 'freezer', 'walllamp', 'cat', 'drawing', 'orchid', 'floor', 'button', 'bookmark', 'ceilinglamp', 'window', 'couch', 'microphone', 'pillow', 'wall', 'pasta', 'tape', 'box', 'novel', 'curtain', 'doorjamb', 'hairbrush', 'door', 'home_office', 'table', 'bathroom_cabinet', 'soap', 'tooth_paste', 'clothes_shirt'] Task:Text friends while sitting on couch response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['microwave', 'chair', 'freezer', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'floor', 'keyboard', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'stereo', 'window', 'couch', 'candle', 'clothes_hat', 'pillow', 'wall', 'oven', 'coffe_maker', 'television', 'curtain', 'diary', 'towel_rack', 'mouse', 'dishrack', 'home_office', 'table'] Task:Relax on sofa response: { "thoughts": I walk to the living room. I see the couch. I sit down on the couch, then lie down and put my feet up., "actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[LIE] <couch>'] }

Scene_Objects:['sponge', 'food_pizza', 'juice', 'crayon', 'blow_dryer', 'bathroom', 'trashcan', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'bedroom', 'mat', 'tvstand', 'faucet', 'wall', 'powersocket', 'bench', 'tape', 'photoframe', 'clothes_gloves', 'food_donut', 'after_shave', 'doorjamb', 'dishrack', 'door', 'sink', 'bathroom_cabinet', 'soap'] Task:Clean sink response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['food_bread', 'scissors', 'crayon', 'freezer', 'walllamp', 'drawing', 'orchid', 'floor', 'ceiling', 'character', 'bookmark', 'toaster', 'ceilinglamp', 'stovefan', 'faucet', 'window', 'homework', 'couch', 'wall', 'child', 'bench', 'photoframe', 'newspaper', 'coffe_maker', 'razor', 'television', 'kitchen_counter', 'cupboard', 'table', 'coffee'] Task:Let baby learn how to walk response: { "thoughts": The baby tries to stand up and balances on the couch and there are no sharp edges so it's safe., "actions": ['[WALK] <home_office>', '[WALK] <child>', '[FIND] <child>', '[TOUCH] <child>', '[GREET] <child>', '[FIND] <couch>', '[TURNTO] <couch>', '[POINTAT] <couch>', '[TURNTO] <child>', '[LOOKAT] <child>'] }

Scene_Objects:['food_salt', 'microwave', 'walllamp', 'bathroom', 'trashcan', 'orchid', 'floor', 'ceiling', 'character', 'toaster', 'ceilinglamp', 'tvstand', 'stereo', 'deck_of_cards', 'oil', 'wall', 'bench', 'powersocket', 'novel', 'coffe_maker', 'food_food', 'television', 'tray', 'rag', 'pencil', 'kitchen_counter', 'cupboard', 'sink', 'dishwasher', 'scrabble'] Task:Make popcorn response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'chair', 'walllamp', 'detergent', 'knifeblock', 'orchid', 'cpuscreen', 'drawing', 'bathroom_counter', 'phone', 'folder', 'man', 'keyboard', 'mop_bucket', 'tvstand', 'faucet', 'picture', 'plate', 'mousepad', 'bench', 'oven', 'powersocket', 'photoframe', 'food_food', 'check', 'food_onion', 'clothes_scarf', 'spoon', 'light', 'dishwasher'] Task:Greet guests response: { "thoughts": When someone knocks I n the door walk through the hallway and greet them., "actions": ['[RUN] <home_office>', '[WALK] <man>', '[FIND] <man>', '[GREET] <man>', '[FIND] <man>', '[GREET] <man>'] }

Scene_Objects:['filing_cabinet', 'chair', 'freezer', 'walllamp', 'food_butter', 'toothbrush', 'knifeblock', 'floor', 'character', 'bookshelf', 'food_cake', 'mat', 'shoe-shine_kit', 'shower', 'mousepad', 'couch', 'microphone', 'cup', 'newspaper', 'mouthwash', 'television', 'coffee_filter', 'food_donut', 'console', 'kitchen_counter', 'headset', 'dresser', 'cupboard', 'clothes_dress', 'home_office'] Task:Answer door response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'sponge', 'scissors', 'chair', 'dog', 'drawing', 'bills', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'ceilinglamp', 'shoe-shine_kit', 'window', 'foundation', 'couch', 'wall', 'bench', 'basket_for_clothes', 'bed', 'novel', 'television', 'kitchen_counter', 'dresser', 'cupboard', 'bathroom_cabinet', 'light', 'table'] Task:Read book response: { "thoughts": Grab book. Read it., "actions": ['[WALK] <home_office>', '[WALK] <dresser>', '[OPEN] <dresser>', '[FIND] <novel>', '[GRAB] <novel>', '[CLOSE] <dresser>', '[FIND] <couch>', '[SIT] <couch>', '[READ] <novel>'] }

Scene_Objects:['fork', 'tablelamp', 'microwave', 'jelly', 'walllamp', 'trashcan', 'bathroom_counter', 'floor', 'ceiling', 'character', 'table_cloth', 'toaster', 'stovefan', 'mat', 'iron', 'pillow', 'dining_room', 'wall', 'powersocket', 'cup', 'photoframe', 'coffe_maker', 'television', 'pencil', 'kitchen_counter', 'hairbrush', 'cupboard', 'door', 'dishwasher', 'clothes_skirt'] Task:Make coffee response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'scissors', 'beer', 'microwave', 'bathroom', 'drawing', 'hanger', 'floor', 'ceiling', 'character', 'toaster', 'brush', 'plate', 'shower', 'clothes_socks', 'dining_room', 'wall', 'powersocket', 'tape', 'box', 'cup', 'coffe_maker', 'food_food', 'doorjamb', 'centerpiece', 'mouse', 'pencil', 'kitchen_counter', 'cupboard', 'dishwasher'] Task:Wash dishes with dishwasher response: { "thoughts": In the kitchen, open up the dishwasher. Take plates from the sink and put them in the dishwasher one by one. Close the dishwasher. Program it. Push start., "actions": ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>'] }

Scene_Objects:['beer', 'walllamp', 'drawing', 'orchid', 'food_egg', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'remote_control', 'toaster', 'ceilinglamp', 'tvstand', 'mat', 'faucet', 'window', 'couch', 'candle', 'pillow', 'wall', 'nightstand', 'powersocket', 'keys', 'television', 'curtain', 'doorjamb', 'door', 'sink', 'table'] Task:Watch movie response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'ground_coffee', 'walllamp', 'food_carrot', 'knifeblock', 'floor', 'ceiling', 'character', 'computer', 'piano_bench', 'stovefan', 'toaster', 'tvstand', 'faucet', 'oil', 'pillow', 'wall', 'oven', 'powersocket', 'food_food', 'water', 'tray', 'after_shave', 'doorjamb', 'kitchen_counter', 'dresser', 'cupboard', 'door', 'dishwasher'] Task:Make coffee response: { "thoughts": Get my coffee pot going, "actions": ['[WALK] <dining_room>', '[WALK] <coffee_pot>', '[FIND] <coffee_pot>', '[GRAB] <coffee_pot>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <coffee_pot>', '[FIND] <ground_coffee>', '[GRAB] <ground_coffee>', '[PUTBACK] <ground_coffee> <coffee_pot>', '[GRAB] <ground_coffee>', '[PUTOBJBACK] <ground_coffee>', '[WALK] <oven>', '[PUTBACK] <coffee_pot> <oven>', '[SWITCHON] <oven>'] }

Scene_Objects:['pot', 'filing_cabinet', 'jelly', 'freezer', 'walllamp', 'ground_coffee', 'knife', 'knifeblock', 'cpuscreen', 'orchid', 'needle', 'floor', 'ceiling', 'desk', 'stovefan', 'ceilinglamp', 'faucet', 'mousepad', 'clothes_hat', 'wall', 'oven', 'cup', 'food_food', 'toothbrush_holder', 'tray', 'rag', 'kitchen_counter', 'cupboard', 'sink', 'bag'] Task:Clean response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'food_pizza', 'food_salt', 'freezer', 'drawing', 'knife', 'cpuscreen', 'knifeblock', 'floor', 'character', 'bookshelf', 'laptop', 'plate', 'mousepad', 'candle', 'dining_room', 'wall', 'light_bulb', 'food_food', 'coffe_maker', 'tray', 'kitchen_counter', 'chessboard', 'dishrack', 'shoes', 'cupboard', 'laundry_detergent', 'dishwasher', 'instrument_violin'] Task:Wash dishes with dishwasher response: { "thoughts": I walk to the kitchen. I take plate. I open the dishwasher. I put plate in the dishwasher. I switch on the dishwasher., "actions": ['[WALK] <dining_room>', '[WALK] <plate>', '[FIND] <plate>', '[GRAB] <plate>', '[WALK] <dishwasher>', '[OPEN] <dishwasher>', '[PUTBACK] <plate> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>'] }

Scene_Objects:['tablelamp', 'measuring_cup', 'walllamp', 'trashcan', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'face', 'computer', 'bookmark', 'mat', 'faucet', 'mousepad', 'clothes_hat', 'towel', 'dining_room', 'wall', 'wall_clock', 'nightstand', 'face_soap', 'basket_for_clothes', 'newspaper', 'tray', 'rag', 'mouse', 'dishrack', 'sink', 'bathroom_cabinet'] Task:Wash face response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'drawing', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'dvd_player', 'folder', 'desk', 'bookshelf', 'keyboard', 'computer', 'mat', 'tvstand', 'shower', 'homework', 'oil', 'dustpan', 'dining_room', 'wall', 'powersocket', 'bench', 'curtain', 'doorjamb', 'towel_rack', 'mouse', 'door', 'home_office', 'light'] Task:Turn on light response: { "thoughts": Walk into the bedroom and walk to the light switch. Flip the switch., "actions": ['[WALK] <bedroom>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>'] }

Scene_Objects:['fork', 'pot', 'tablelamp', 'microwave', 'dog', 'walllamp', 'trashcan', 'knifeblock', 'knife', 'kitchen_cabinet', 'floor', 'ceiling', 'toaster', 'stovefan', 'plate', 'faucet', 'ceilinglamp', 'oil', 'wall', 'oven', 'coffe_maker', 'drinking_glass', 'tray', 'kitchen_counter', 'cupboard', 'sink', 'spoon', 'bag', 'dishwasher', 'colander'] Task:Unload dishwasher response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'microwave', 'walllamp', 'drawing', 'knifeblock', 'wallshelf', 'floor', 'ceiling', 'phone', 'keyboard', 'computer', 'stovefan', 'plate', 'faucet', 'tvstand', 'window', 'dish_soap', 'towel', 'dining_room', 'wall', 'wall_clock', 'oven', 'coffe_maker', 'food_food', 'curtain', 'kitchen_counter', 'cupboard', 'food_steak', 'sink'] Task:Wash dishes by hand response: { "thoughts": Walk to Kitchen, find sink, find dishes and dish soap. Put soap on plate. open faucet, rinse dishes close faucet., "actions": ['[WALK] <dining_room>', '[WALK] <sink>', '[FIND] <sink>', '[FIND] <plate>', '[GRAB] <plate>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[PUTBACK] <dish_soap> <plate>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[RINSE] <plate>'] }

Scene_Objects:['chair', 'walllamp', 'cat', 'orchid', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'bedroom', 'keyboard', 'computer', 'bookmark', 'mat', 'ceilinglamp', 'food_noodles', 'mousepad', 'wall', 'oven', 'check', 'video_game_controller', 'television', 'oven_mitts', 'after_shave', 'food_onion', 'centerpiece', 'mouse', 'door', 'table', 'coffee'] Task:Use computer response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'freezer', 'food_carrot', 'drawing', 'floor', 'ceiling', 'desk', 'envelope', 'table_cloth', 'mat', 'faucet', 'mousepad', 'couch', 'pillow', 'towel', 'wall', 'cup', 'food_food', 'mouthwash', 'television', 'water', 'tray', 'curtain', 'kitchen_counter', 'cupboard', 'food_steak', 'light', 'dishwasher', 'table'] 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:['food_carrot', 'milk', 'dough', 'knifeblock', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'bedroom', 'mat', 'faucet', 'shower', 'stereo', 'towel', 'pillow', 'wall', 'bench', 'cup', 'bed', 'photoframe', 'coffe_maker', 'wooden_spoon', 'after_shave', 'rag', 'mouse', 'sink', 'bathroom_cabinet', 'soap', 'hands_both'] Task:Wash hands response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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:['mop', 'freezer', 'trashcan', 'milk', 'knifeblock', 'orchid', 'clothes_underwear', 'bookshelf', 'purse', 'thread', 'computer', 'ceilinglamp', 'tvstand', 'iron', 'couch', 'microphone', 'wall', 'cutting_board', 'basket_for_clothes', 'keys', 'toothbrush_holder', 'oven_mitts', 'curtain', 'doorjamb', 'diary', 'chessboard', 'home_office', 'bathroom_cabinet', 'clothes_skirt', 'light'] Task:Hang up car keys response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'drawing', 'hanger', 'floor', 'phone', 'ceilinglamp', 'plate', 'iron', 'candle', 'pillow', 'wall', 'bench', 'powersocket', 'oven', 'food_food', 'video_game_controller', 'check', 'wooden_spoon', 'after_shave', 'doorjamb', 'shoes', 'dresser', 'cupboard', 'clothes_dress', 'door', 'conditioner', 'sink', 'table', 'light'] Task:Eat dinner response: { "thoughts": Put food on the table, sit down, and eat the food., "actions": ['[WALK] <dining_room>', '[WALK] <plate>', '[FIND] <plate>', '[GRAB] <plate>', '[FIND] <food_food>', '[GRAB] <food_food>', '[PUTBACK] <food_food> <plate>', '[WALK] <dining_room>', '[WALK] <table>', '[FIND] <table>', '[PUTBACK] <plate> <table>', '[FIND] <chair>', '[SIT] <chair>', '[EAT] <plate>'] }

Scene_Objects:['walllamp', 'food_carrot', 'drawing', 'orchid', 'knifeblock', 'cpuscreen', 'floor', 'ceiling', 'bedroom', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'couch', 'microphone', 'pillow', 'wall', 'wall_clock', 'photoframe', 'television', 'toothbrush_holder', 'food_donut', 'doorjamb', 'shaving_cream', 'mouse', 'door', 'sink', 'clothes_scarf', 'napkin', 'table'] Task:Straighten pictures on wall response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'food_pizza', 'dry_pasta', 'walllamp', 'trashcan', 'food_carrot', 'dough', 'knifeblock', 'orchid', 'bathroom_counter', 'floor', 'ceiling', 'table_cloth', 'stovefan', 'toaster', 'wall', 'wall_clock', 'oven', 'food_cheese', 'food_food', 'coffe_maker', 'tray', 'doorjamb', 'coffee_pot', 'kitchen_counter', 'cupboard', 'home_office', 'table', 'dishwasher'] Task:Keep an eye on stove as something is cooking response: { "thoughts": Watch whatever is cooking on the stove so it doesn't burn or pour. Turn off heat when done, "actions": ['[WALK] <dining_room>', '[WALK] <oven>', '[FIND] <pot>', '[TURNTO] <pot>', '[LOOKAT] <pot>', '[FIND] <wall_clock>', '[TURNTO] <wall_clock>', '[LOOKAT] <wall_clock>', '[SWITCHOFF] <oven>'] }

Scene_Objects:['food_ice_cream', 'measuring_cup', 'freezer', 'nail_polish', 'food_carrot', 'drawing', 'cpuscreen', 'kitchen_cabinet', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'plate', 'mat', 'mousepad', 'food_peanut_butter', 'pillow', 'wall', 'powersocket', 'bench', 'food_vegetable', 'food_food', 'doorjamb', 'mouse', 'door', 'light', 'table', 'scrabble'] Task:Fix snack response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'filing_cabinet', 'food_salt', 'measuring_cup', 'toilet', 'jelly', 'drawing', 'floor', 'phone', 'ceiling', 'character', 'bookshelf', 'alcohol', 'mat', 'shower', 'foundation', 'electric_shaver', 'mousepad', 'wall', 'toy', 'basket_for_clothes', 'photoframe', 'wine', 'dresser', 'laundry_detergent', 'food_steak', 'door', 'napkin', 'bathroom_cabinet', 'dishwasher'] Task:Pick up toys response: { "thoughts": Pickup toys from around the room. Organize toys back into their appropriate spaces on the shelves and into the toy boxes., "actions": ['[WALK] <bedroom>', '[WALK] <toy>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <filing_cabinet>', '[OPEN] <filing_cabinet>', '[PUTBACK] <toy> <filing_cabinet>', '[CLOSE] <filing_cabinet>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <dresser>', '[OPEN] <dresser>', '[PUTBACK] <toy> <dresser>', '[CLOSE] <dresser>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <filing_cabinet>', '[OPEN] <filing_cabinet>', '[PUTBACK] <toy> <filing_cabinet>', '[CLOSE] <filing_cabinet>'] }

Scene_Objects:['dry_pasta', 'sheets', 'pot', 'freezer', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'mail', 'tvstand', 'stereo', 'window', 'mousepad', 'clothes_socks', 'wall', 'nightstand', 'powersocket', 'pasta', 'oven', 'light_bulb', 'coffe_maker', 'food_rice', 'doorjamb', 'shaving_cream', 'mouse', 'kitchen_counter', 'door', 'light'] Task:Turn light off response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['juice', 'toilet', 'chair', 'freezer', 'detergent', 'food_carrot', 'drawing', 'knifeblock', 'floor', 'ceiling', 'food_chicken', 'bedroom', 'piano_bench', 'ceilinglamp', 'mat', 'shower', 'faucet', 'oil', 'food_orange', 'wall', 'nightstand', 'powersocket', 'photoframe', 'food_food', 'check', 'doorjamb', 'vacuum_cleaner', 'door', 'table', 'light'] Task:Put groceries in Fridge response: { "thoughts": Put the groceries on the table into the fridge, "actions": ['[WALK] <dining_room>', '[WALK] <table>', '[FIND] <food_chicken>', '[GRAB] <food_chicken>', '[FIND] <freezer>', '[OPEN] <freezer>', '[PUTBACK] <food_chicken> <freezer>', '[CLOSE] <freezer>', '[FIND] <food_carrot>', '[GRAB] <food_carrot>', '[FIND] <freezer>', '[OPEN] <freezer>', '[PUTIN] <food_carrot> <freezer>', '[CLOSE] <freezer>'] }

Scene_Objects:['tablelamp', 'walllamp', 'dough', 'drawing', 'orchid', 'needle', 'floor', 'ceiling', 'desk', 'bookshelf', 'computer', 'bookmark', 'stovefan', 'mat', 'tvstand', 'ceilinglamp', 'couch', 'pillow', 'food_kiwi', 'wall', 'oven', 'photoframe', 'novel', 'television', 'doorjamb', 'mouse', 'dresser', 'door', 'home_office', 'table'] Task:Admire art response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tea', 'microwave', 'toilet', 'jelly', 'bathroom_counter', 'floor', 'ceiling', 'toaster', 'mat', 'faucet', 'food_noodles', 'clothes_socks', 'mousepad', 'closetdrawer', 'food_kiwi', 'wall', 'cutting_board', 'cup', 'coffe_maker', 'toothbrush_holder', 'television', 'oven_mitts', 'water', 'kitchen_counter', 'dresser', 'cupboard', 'sink', 'home_office', 'soap', 'tooth_paste'] Task:Drink response: { "thoughts": Walk to kitchen, walk to cupboard, open cupboard, grab cup, walk to sink, pour water in cup, drink water., "actions": ['[WALK] <dining_room>', '[WALK] <cupboard>', '[FIND] <cupboard>', '[OPEN] <cupboard>', '[FIND] <cup>', '[GRAB] <cup>', '[WALK] <sink>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <cup>', '[DRINK] <cup>'] }

Scene_Objects:['tablelamp', 'chair', 'dough', 'drawing', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'dvd_player', 'desk', 'keyboard', 'bookshelf', 'computer', 'clothes_jacket', 'homework', 'mousepad', 'towel', 'wall', 'nightstand', 'bed', 'novel', 'coffe_maker', 'toothbrush_holder', 'ice', 'diary', 'kettle', 'mouse', 'door', 'spoon', 'instrument_violin'] Task:Study response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['measuring_cup', 'chair', 'trashcan', 'drawing', 'orchid', 'cpuscreen', 'longboard', 'floor', 'ceiling', 'desk', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'mat', 'window', 'mousepad', 'couch', 'wall', 'powersocket', 'bed', 'curtain', 'doorjamb', 'shaving_cream', 'mouse', 'comb', 'door', 'napkin', 'table', 'light'] 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:['microwave', 'walllamp', 'drawing', 'orchid', 'hanger', 'floor', 'ceiling', 'video_game_console', 'button', 'toaster', 'ceilinglamp', 'tvstand', 'mat', 'faucet', 'window', 'candle', 'broom', 'wall', 'powersocket', 'check', 'video_game_controller', 'television', 'rag', 'doorjamb', 'kitchen_counter', 'hairbrush', 'door', 'table', 'dishwasher', 'dirt'] Task:Play games response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'filing_cabinet', 'food_salt', 'chair', 'bathroom', 'drawing', 'food_egg', 'floor', 'desk', 'bookshelf', 'computer', 'mat', 'stereo', 'shower', 'couch', 'food_peanut_butter', 'wall', 'powersocket', 'oven', 'cup', 'doorjamb', 'mouse', 'kitchen_counter', 'pajamas', 'controller', 'door', 'clothes_scarf', 'light', 'dishwasher', 'board_game'] Task:Pull up carpet response: { "thoughts": Pry up a corner of your old dirty carpet. Tug as hard as you can until it comes off the tacs. Pull up the pad. Try not to be sick at all the dirt., "actions": ['[WALK] <home_office>', '[WALK] <mat>', '[FIND] <mat>', '[TOUCH] <mat>', '[PULL] <mat>'] }

Scene_Objects:['sheets', 'microwave', 'toilet', 'chair', 'band-aids', 'cat', 'food_carrot', 'knife', 'foundation', 'electric_shaver', 'mousepad', 'clothes_socks', 'pillow', 'dining_room', 'nightstand', 'oven', 'toy', 'check', 'coffe_maker', 'television', 'curtain', 'doorjamb', 'kitchen_counter', 'chessboard', 'cupboard', 'conditioner', 'door', 'food_steak', 'clothes_skirt', 'duster'] Task:Dust response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'blender', 'toilet', 'walllamp', 'cat', 'drawing', 'orchid', 'floor', 'ceiling', 'bedroom', 'toaster', 'ceilinglamp', 'tvstand', 'mat', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'toy', 'cup', 'bed', 'keys', 'television', 'curtain', 'doorjamb', 'shaving_cream', 'door', 'table', 'shoe_rack'] Task:Watch TV response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'glue', 'tablelamp', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'purse', 'computer', 'clothes_jacket', 'toaster', 'stereo', 'mousepad', 'closetdrawer', 'couch', 'wall', 'wall_clock', 'powersocket', 'nightstand', 'bed', 'novel', 'mouse', 'shoes', 'dresser', 'clothes_dress', 'light', 'table'] Task:Get ready for day response: { "thoughts": Grab shoes, purse etc and head out the door!, "actions": ['[WALK] <bedroom>', '[WALK] <dresser>', '[FIND] <dresser>', '[OPEN] <dresser>', '[FIND] <clothes_dress>', '[GRAB] <clothes_dress>', '[PUTON] <clothes_dress>', '[FIND] <shoes>', '[GRAB] <shoes>', '[PUTON] <shoes>', '[FIND] <purse>', '[GRAB] <purse>', '[CLOSE] <dresser>', '[WALK] <home_office>'] }

Scene_Objects:['pot', 'tablelamp', 'drawing', 'needle', 'knife', 'clothes_underwear', 'hanger', 'floor', 'envelope', 'computer', 'ceilinglamp', 'oil', 'mousepad', 'pillow', 'bowl', 'wall', 'nightstand', 'child', 'bed', 'novel', 'food_food', 'coffe_maker', 'television', 'doorjamb', 'dishrack', 'comb', 'laundry_detergent', 'conditioner', 'sink', 'instrument_violin'] Task:Story reading time response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['toilet', 'chair', 'walllamp', 'bathroom', 'wallshelf', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'phone', 'desk', 'keyboard', 'envelope', 'computer', 'mop_bucket', 'stovefan', 'mat', 'tvstand', 'toaster', 'foundation', 'mousepad', 'pillow', 'wall', 'standingmirror', 'photoframe', 'toilet_paper', 'oven_mitts', 'tray', 'mouse', 'sink'] Task:Read book response: { "thoughts": go to living room,find the text book on the self ,sat on the chair ,open and read the book, "actions": ['[WALK] <home_office>', '[WALK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[WALK] <home_office>', '[WALK] <chair>', '[FIND] <chair>', '[SIT] <chair>', '[READ] <novel>'] }

Scene_Objects:['sponge', 'pot', 'filing_cabinet', 'microwave', 'walllamp', 'drawing', 'orchid', 'bathroom_counter', 'floor', 'ceiling', 'keyboard', 'computer', 'piano_bench', 'mat', 'tvstand', 'faucet', 'shower', 'homework', 'clothes_socks', 'broom', 'wall', 'bench', 'cup', 'rag', 'kitchen_counter', 'laundry_detergent', 'door', 'sink', 'bathroom_cabinet', 'tooth_paste'] Task:Wipe down sink response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'spectacles', 'pot', 'microwave', 'knifeblock', 'floor', 'ceiling', 'folder', 'character', 'toaster', 'plate', 'drying_rack', 'faucet', 'dish_soap', 'couch', 'wall', 'powersocket', 'food_cheese', 'photoframe', 'bed', 'food_food', 'mouse', 'kitchen_counter', 'cupboard', 'door', 'sink', 'hairdryer', 'light', 'dirt', 'coffee'] 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:['glue', 'microwave', 'freezer', 'walllamp', 'drawing', 'hanger', 'floor', 'ceiling', 'bookshelf', 'purse', 'mail', 'ceilinglamp', 'window', 'mousepad', 'couch', 'pillow', 'wall', 'bed', 'light_bulb', 'check', 'food_food', 'curtain', 'kitchen_counter', 'chessboard', 'dishrack', 'dresser', 'laundry_detergent', 'door', 'light', 'shoe_rack'] Task:Open window response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'dog', 'walllamp', 'clothes_underwear', 'bathroom_counter', 'phone', 'character', 'desk', 'tea_bag', 'envelope', 'toaster', 'ceilinglamp', 'window', 'mousepad', 'food_kiwi', 'nightstand', 'cutting_board', 'photoframe', 'coffe_maker', 'television', 'tray', 'rag', 'doorjamb', 'diary', 'cupboard', 'hairdryer', 'home_office', 'light', 'table', 'creditcard'] Task:Receive credit card response: { "thoughts": hear the dooble, go to door, take de envelope, open it with a scissor, take the creditcard, "actions": ['[WALK] <home_office>', '[WALK] <envelope>', '[FIND] <envelope>', '[GRAB] <envelope>', '[WALK] <home_office>', '[WALK] <scissors>', '[FIND] <scissors>', '[OPEN] <envelope>', '[FIND] <creditcard>', '[GRAB] <creditcard>'] }

Scene_Objects:['sheets', 'toilet', 'walllamp', 'bathroom', 'detergent', 'knifeblock', 'bathroom_counter', 'purse', 'alcohol', 'bookmark', 'stovefan', 'toaster', 'stereo', 'food_jam', 'dining_room', 'powersocket', 'food_food', 'mouthwash', 'tray', 'after_shave', 'doorjamb', 'shaving_cream', 'mouse', 'kitchen_counter', 'cupboard', 'controller', 'hairdryer', 'sink', 'home_office', 'laser_pointer'] Task:Walk through response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'filing_cabinet', 'tablelamp', 'microwave', 'walllamp', 'trashcan', 'floor', 'tea_bag', 'thread', 'toaster', 'ceilinglamp', 'plate', 'dish_soap', 'wall', 'bed', 'coffe_maker', 'food_food', 'check', 'oven_mitts', 'tray', 'doorjamb', 'pencil', 'kitchen_counter', 'hairbrush', 'cupboard', 'hair', 'controller', 'bathroom_cabinet', 'dishwasher'] Task:Wash dishes with dishwasher response: { "thoughts": Walk to the kitchen. Open the dishwasher. Grab plate and put it in the dishwasher. Grab dish soap and put it in the dishwasher. Switch on the dishwasher., "actions": ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <dish_soap>', '[GRAB] <dish_soap>', '[PUTBACK] <dish_soap> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>'] }

Scene_Objects:['spectacles', 'tablelamp', 'toilet', 'walllamp', 'orchid', 'hanger', 'floor', 'ceiling', 'shampoo', 'bedroom', 'desk', 'envelope', 'table_cloth', 'bookmark', 'brush', 'toaster', 'window', 'couch', 'dustpan', 'food_jam', 'pillow', 'dining_room', 'wall', 'photoframe', 'check', 'tray', 'curtain', 'lighter', 'dresser', 'light'] Task:Gaze out window response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['glue', 'toilet', 'freezer', 'wallshelf', 'hanger', 'bathroom_counter', 'bookshelf', 'mail', 'brush', 'mat', 'shoe-shine_kit', 'homework', 'closetdrawer', 'couch', 'food_orange', 'towel', 'dining_room', 'wall', 'powersocket', 'box', 'novel', 'check', 'coffe_maker', 'tray', 'doorjamb', 'diary', 'cupboard', 'home_office', 'bathroom_cabinet', 'soap'] Task:Read book response: { "thoughts": Pick up the book, open to current page, read the words., "actions": ['[WALK] <home_office>', '[WALK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[READ] <novel>'] }

Scene_Objects:['glue', 'chair', 'bathroom', 'detergent', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'keyboard', 'purse', 'face', 'mat', 'tvstand', 'faucet', 'mousepad', 'wall', 'bench', 'face_soap', 'newspaper', 'novel', 'ice', 'curtain', 'doorjamb', 'chessboard', 'dresser', 'conditioner', 'sink', 'bathroom_cabinet', 'light', 'table'] Task:Wash face response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'walllamp', 'woman', 'drawing', 'phone', 'desk', 'man', 'toaster', 'laptop', 'mat', 'shower', 'electric_shaver', 'oil', 'form', 'pillow', 'dining_room', 'oven', 'shelf', 'bed', 'standingmirror', 'toothbrush_holder', 'tray', 'curtain', 'doorjamb', 'mouse', 'door', 'bathroom_cabinet', 'tooth_paste', 'scrabble'] Task:Greet guests response: { "thoughts": Answer the door. Smile and give a warm hello, or other appropriate greeting. With newcomers to your home, offer your hand to be shook. With old friends it is appropriate to hug, or kiss one another on the cheek., "actions": ['[WALK] <home_office>', '[WALK] <man>', '[FIND] <man>', '[GREET] <man>', '[FIND] <woman>', '[GREET] <woman>'] }

Scene_Objects:['spectacles', 'pot', 'filing_cabinet', 'measuring_cup', 'walllamp', 'detergent', 'cat', 'milk', 'knifeblock', 'floor', 'ceiling', 'character', 'folder', 'bookshelf', 'piano_bench', 'table_cloth', 'faucet', 'window', 'mousepad', 'dining_room', 'wall', 'powersocket', 'food_cheese', 'bed', 'check', 'kitchen_counter', 'cupboard', 'sink', 'clothes_scarf', 'clothes_skirt'] Task:Wipe down sink response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'food_pizza', 'tablelamp', 'mop', 'chair', 'freezer', 'walllamp', 'dough', 'drawing', 'knifeblock', 'wallshelf', 'orchid', 'floor', 'ceiling', 'mop_bucket', 'toaster', 'stovefan', 'faucet', 'bowl', 'wall', 'oven', 'bench', 'toy', 'tray', 'kitchen_counter', 'dresser', 'cupboard', 'door', 'sink'] 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:['pot', 'filing_cabinet', 'scissors', 'chair', 'freezer', 'walllamp', 'orchid', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'stovefan', 'mat', 'ceilinglamp', 'shower', 'faucet', 'mousepad', 'food_orange', 'wall', 'powersocket', 'wooden_spoon', 'after_shave', 'doorjamb', 'shaving_cream', 'mouse', 'door', 'table'] Task:Computer work response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'mop', 'toilet', 'cat', 'trashcan', 'ceilingfan', 'drawing', 'knifeblock', 'orchid', 'floor', 'ceiling', 'computer', 'clothes_jacket', 'table_cloth', 'stovefan', 'ceilinglamp', 'tvstand', 'faucet', 'window', 'couch', 'wall', 'nightstand', 'food_food', 'mouthwash', 'television', 'food_donut', 'curtain', 'after_shave', 'dresser', 'table'] Task:Look at painting response: { "thoughts": Walk to the painting. Look up at the painting. Admire it on the wall., "actions": ['[WALK] <home_office>', '[WALK] <drawing>', '[FIND] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>'] }

Scene_Objects:['walllamp', 'drawing', 'orchid', 'hanger', 'floor', 'ceiling', 'desk', 'remote_control', 'ceilinglamp', 'tvstand', 'mat', 'window', 'couch', 'clothes_pants', 'form', 'pillow', 'towel', 'wall', 'powersocket', 'bench', 'newspaper', 'television', 'curtain', 'doorjamb', 'mouse', 'hair', 'door', 'bathroom_cabinet', 'table', 'dishwasher'] Task:Watch TV response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['filing_cabinet', 'tablelamp', 'walllamp', 'cat', 'milk', 'orchid', 'drawing', 'bills', 'hanger', 'floor', 'ceiling', 'phone', 'character', 'bookshelf', 'toaster', 'ceilinglamp', 'mat', 'stereo', 'picture', 'closetdrawer', 'pillow', 'wall', 'nightstand', 'powersocket', 'basket_for_clothes', 'photoframe', 'doorjamb', 'door', 'light', 'table'] Task:Look at painting response: { "thoughts": Walk to the painting. Look up at the painting. Admire it on the wall., "actions": ['[WALK] <home_office>', '[WALK] <drawing>', '[FIND] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>'] }

Scene_Objects:['pot', 'filing_cabinet', 'tablelamp', 'chair', 'freezer', 'bathroom', 'food_butter', 'drawing', 'food_egg', 'floor', 'computer', 'mat', 'tvstand', 'stereo', 'laptop', 'clothes_pants', 'towel', 'wall', 'nightstand', 'tape', 'bed', 'food_food', 'coffe_maker', 'television', 'oven_mitts', 'tray', 'curtain', 'diary', 'cards', 'dishwasher'] Task:Listen to music response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'juice', 'microwave', 'chair', 'trashcan', 'drawing', 'cpuscreen', 'wallshelf', 'floor', 'ceiling', 'computer', 'table_cloth', 'tvstand', 'shower', 'mousepad', 'dining_room', 'wall', 'nightstand', 'powersocket', 'photoframe', 'food_food', 'television', 'tray', 'doorjamb', 'cupboard', 'sink', 'bathroom_cabinet', 'light', 'board_game'] 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:['food_bread', 'drawing', 'bathroom_counter', 'floor', 'ceiling', 'face', 'toaster', 'mat', 'faucet', 'foundation', 'mousepad', 'towel', 'dining_room', 'broom', 'wall', 'bowl', 'bench', 'face_soap', 'food_cheese', 'coin', 'water', 'after_shave', 'rag', 'curtain', 'mouse', 'conditioner', 'sink', 'napkin', 'bathroom_cabinet', 'hands_both'] Task:Wash face response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'pot', 'filing_cabinet', 'tablelamp', 'freezer', 'bathroom', 'milk', 'drawing', 'floor', 'ceiling', 'bedroom', 'alcohol', 'computer', 'table_cloth', 'stovefan', 'mat', 'shower', 'oil', 'couch', 'pillow', 'wall', 'cutting_board', 'newspaper', 'food_food', 'television', 'kettle', 'kitchen_counter', 'cupboard', 'clothes_dress', 'shoe_rack'] Task:Put groceries in Fridge response: { "thoughts": Walk to kitchen. Find groceries. Grab groceries. Find fridge. Walk to fridge. Put groceries in fridge., "actions": ['[WALK] <dining_room>', '[WALK] <food_food>', '[FIND] <food_food>', '[GRAB] <food_food>', '[FIND] <freezer>', '[WALK] <freezer>', '[OPEN] <freezer>', '[PUTIN] <food_food> <freezer>'] }

Scene_Objects:['food_bread', 'food_ice_cream', 'freezer', 'milk', 'drawing', 'knife', 'cpuscreen', 'kitchen_cabinet', 'floor', 'ceiling', 'dvd_player', 'stamp', 'desk', 'keyboard', 'computer', 'button', 'mat', 'plate', 'ceilinglamp', 'mousepad', 'candle', 'pillow', 'wall', 'bench', 'powersocket', 'cup', 'food_food', 'doorjamb', 'mouse', 'door', 'napkin', 'table', 'light'] Task:Cut bread response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'tablelamp', 'food_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: { "thoughts": Enter the Home office, then walk to the phone, pickup the phone., "actions": ['[WALK] <home_office>', '[WALK] <phone>', '[GRAB] <phone>'] }

Scene_Objects:['pot', 'juice', 'jelly', 'freezer', 'walllamp', 'nail_polish', 'knifeblock', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'button', 'stovefan', 'ceilinglamp', 'mat', 'faucet', 'mousepad', 'pillow', 'wall', 'oven', 'powersocket', 'bench', 'cup', 'food_food', 'food_rice', 'tray', 'doorjamb', 'mouse', 'kitchen_counter', 'cupboard', 'door', 'sink', 'light', 'table', 'board_game'] Task:Grab some juice response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'food_ice_cream', 'toilet', 'walllamp', 'dough', 'drawing', 'knifeblock', 'cpuscreen', 'clothes_underwear', 'floor', 'ceiling', 'character', 'bedroom', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'basket_for_clothes', 'bed', 'food_food', 'television', 'doorjamb', 'mouse', 'pencil', 'dishrack', 'door', 'home_office', 'light', 'bathroom_cabinet'] Task:Turn off light response: { "thoughts": Grasp light switch, flip light switch., "actions": ['[WALK] <bedroom>', '[WALK] <light>', '[FIND] <light>', '[TURNTO] <light>', '[SWITCHOFF] <light>'] }

Scene_Objects:['pot', 'crayon', 'tea', 'beer', 'microwave', 'toilet', 'trashcan', 'food_carrot', 'knifeblock', 'cpuscreen', 'bathroom_counter', 'floor', 'character', 'bedroom', 'desk', 'keyboard', 'bookshelf', 'computer', 'ceilinglamp', 'window', 'dining_room', 'food_kiwi', 'nightstand', 'bed', 'photoframe', 'doorjamb', 'dishrack', 'cupboard', 'sink', 'home_office'] Task:Open bathroom window response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'chair', 'walllamp', 'nail_polish', 'trashcan', 'orchid', 'drawing', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mousepad', 'closetdrawer', 'wall', 'powersocket', 'bench', 'bed', 'coffe_maker', 'television', 'food_donut', 'doorjamb', 'mouse', 'door', 'table', 'shoe_rack'] Task:Work response: { "thoughts": Walk to living-room. Look at the desk where Computer stays. Sit in chair. Switch on computer. Work on computer. Switch off computer., "actions": ['[WALK] <home_office>', '[WALK] <desk>', '[FIND] <desk>', '[TURNTO] <desk>', '[LOOKAT] <desk>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[TURNTO] <computer>', '[WATCH] <computer>', '[SWITCHOFF] <computer>'] }

Scene_Objects:['pot', 'food_ice_cream', 'freezer', 'walllamp', 'milk', 'knifeblock', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'alcohol', 'computer', 'stovefan', 'ceilinglamp', 'faucet', 'mousepad', 'wall', 'oven', 'powersocket', 'cup', 'ice', 'tray', 'doorjamb', 'mouse', 'kitchen_counter', 'cupboard', 'door', 'sink', 'light'] Task:Get something to drink response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['blender', 'freezer', 'walllamp', 'bathroom', 'drawing', 'clothes_underwear', 'hanger', 'floor', 'ceiling', 'character', 'keyboard', 'brush', 'tvstand', 'stereo', 'window', 'closetdrawer', 'towel', 'wall', 'powersocket', 'tape', 'food_food', 'television', 'curtain', 'doorjamb', 'vacuum_cleaner', 'dresser', 'door', 'clothes_scarf', 'dishwasher', 'board_game'] Task:vacuum carpet response: { "thoughts": I bring my vacuum cleaner into the living room. I plug it into the wall. I press the on switch on the vacuum cleaner. I push the vacuum cleaner back and forth over the length and width of the carpet until I have vacuumed the entire carpet. I turn the vacuum cleaner off. I take the vacuum cleaner back to the hall closet., "actions": ['[WALK] <home_office>', '[WALK] <dresser>', '[OPEN] <dresser>', '[FIND] <vacuum_cleaner>', '[GRAB] <vacuum_cleaner>', '[PULL] <vacuum_cleaner>', '[PLUGIN] <vacuum_cleaner>', '[SWITCHON] <vacuum_cleaner>', '[PULL] <vacuum_cleaner>', '[PUSH] <vacuum_cleaner>', '[PULL] <vacuum_cleaner>', '[PUSH] <vacuum_cleaner>', '[PULL] <vacuum_cleaner>', '[PUSH] <vacuum_cleaner>', '[SWITCHOFF] <vacuum_cleaner>', '[PLUGOUT] <vacuum_cleaner>', '[WALK] <dresser>', '[PUTIN] <vacuum_cleaner> <dresser>', '[CLOSE] <dresser>'] }

Scene_Objects:['tablelamp', 'chair', 'freezer', 'cat', 'drawing', 'knifeblock', 'cpuscreen', 'floor', 'folder', 'desk', 'keyboard', 'computer', 'faucet', 'stereo', 'mousepad', 'food_peanut_butter', 'wall', 'nightstand', 'powersocket', 'bed', 'novel', 'check', 'toothbrush_holder', 'curtain', 'doorjamb', 'mouse', 'kitchen_counter', 'door', 'napkin', 'light'] Task:Read response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'pot', 'filing_cabinet', 'tea', 'chair', 'freezer', 'ground_coffee', 'drawing', 'orchid', 'floor', 'purse', 'faucet', 'balanceball', 'food_noodles', 'food_peanut_butter', 'wall', 'powersocket', 'toy', 'bed', 'food_food', 'check', 'food_donut', 'doorjamb', 'pencil', 'laundry_detergent', 'door', 'bag', 'napkin', 'light', 'table'] Task:Pick up toys response: { "thoughts": Grab toys off floor. Put it in a container., "actions": ['[WALK] <bedroom>', '[WALK] <toy>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <filing_cabinet>', '[OPEN] <filing_cabinet>', '[PUTBACK] <toy> <filing_cabinet>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <filing_cabinet>', '[PUTBACK] <toy> <filing_cabinet>', '[FIND] <toy>', '[GRAB] <toy>', '[WALK] <filing_cabinet>', '[PUTBACK] <toy> <filing_cabinet>', '[CLOSE] <filing_cabinet>'] }

Scene_Objects:['pot', 'tablelamp', 'microwave', 'freezer', 'walllamp', 'food_carrot', 'drawing', 'clothes_underwear', 'bathroom_counter', 'floor', 'bookshelf', 'keyboard', 'computer', 'stovefan', 'ceilinglamp', 'tvstand', 'floor_lamp', 'foundation', 'couch', 'pillow', 'bowl', 'dining_room', 'wall', 'nightstand', 'oven', 'bed', 'food_donut', 'console', 'cupboard', 'bathroom_cabinet'] Task:Turn on lights response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'scissors', 'jelly', 'walllamp', 'bathroom', 'ceilingfan', 'drawing', 'hanger', 'floor', 'ceiling', 'desk', 'remote_control', 'computer', 'ceilinglamp', 'tvstand', 'balanceball', 'shoe-shine_kit', 'window', 'couch', 'food_jam', 'wall', 'novel', 'television', 'curtain', 'doorjamb', 'comb', 'clothes_dress', 'sink', 'home_office', 'table'] 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:['glue', 'food_bread', 'filing_cabinet', 'bathroom', 'ceiling', 'phone', 'keyboard', 'purse', 'bookshelf', 'laptop', 'ceilinglamp', 'faucet', 'nightstand', 'bench', 'photoframe', 'bed', 'clothes_gloves', 'food_food', 'coffe_maker', 'television', 'toothbrush_holder', 'curtain', 'shaving_cream', 'pencil', 'dresser', 'conditioner', 'door', 'spoon', 'bathroom_cabinet', 'table'] Task:Shut front door response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'drawing', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'mat', 'window', 'clothes_socks', 'couch', 'pillow', 'towel', 'broom', 'wall', 'bench', 'oven', 'toy', 'bed', 'coffe_maker', 'television', 'wooden_spoon', 'curtain', 'rag', 'doorjamb', 'food_onion', 'towel_rack', 'mouse', 'bathroom_cabinet', 'table', 'scrabble'] Task:Relax on sofa response: { "thoughts": Walk to living room. Find couch. Sit on couch, "actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>'] }

Scene_Objects:['tablelamp', 'juice', 'food_ice_cream', 'chair', 'walllamp', 'detergent', 'drawing', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'tvstand', 'mousepad', 'clothes_hat', 'towel', 'wall', 'powersocket', 'bench', 'photoframe', 'television', 'curtain', 'doorjamb', 'mouse', 'shoes', 'door', 'bathroom_cabinet'] Task:Put in chair response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'microwave', 'chair', 'freezer', 'walllamp', 'floor', 'character', 'bookshelf', 'computer', 'toaster', 'mat', 'plate', 'window', 'food_noodles', 'food_orange', 'wall', 'oven', 'photoframe', 'keys', 'bed', 'coffe_maker', 'toothbrush_holder', 'doorjamb', 'kitchen_counter', 'comb', 'cupboard', 'clothes_dress', 'napkin', 'home_office', 'dishwasher'] Task:Wash dishes with dishwasher response: { "thoughts": In the kitchen, open up the dishwasher. Take plates from the sink and put them in the dishwasher one by one. Close the dishwasher. Program it. Push start., "actions": ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[PUTBACK] <plate> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>'] }

Scene_Objects:['sponge', 'band-aids', 'toothbrush', 'orchid', 'phone', 'desk', 'keyboard', 'bookshelf', 'computer', 'toaster', 'faucet', 'picture', 'shower', 'mousepad', 'candle', 'food_orange', 'oven', 'basket_for_clothes', 'bed', 'check', 'food_food', 'television', 'tray', 'after_shave', 'headset', 'comb', 'dresser', 'laundry_detergent', 'napkin', 'bathroom_cabinet'] Task:Sit in chair response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'microwave', 'freezer', 'detergent', 'drawing', 'floor', 'ceiling', 'table_cloth', 'stovefan', 'ceilinglamp', 'iron', 'faucet', 'window', 'homework', 'bowl', 'wall', 'wall_clock', 'bench', 'shelf', 'newspaper', 'mouthwash', 'food_donut', 'doorjamb', 'coffee_pot', 'door', 'sink', 'bathroom_cabinet', 'light', 'board_game'] Task:Turn light off response: { "thoughts": Put the light switch into the down, or off, position., "actions": ['[WALK] <bedroom>', '[WALK] <light>', '[SWITCHOFF] <light>'] }

Scene_Objects:['pot', 'filing_cabinet', 'freezer', 'blow_dryer', 'walllamp', 'drawing', 'knifeblock', 'cpuscreen', 'bathroom_counter', 'ceiling', 'character', 'faucet', 'picture', 'iron', 'mousepad', 'bowl', 'wall', 'powersocket', 'bench', 'photoframe', 'toilet_paper', 'coffe_maker', 'toothbrush_holder', 'tray', 'doorjamb', 'dishrack', 'sink', 'bathroom_cabinet', 'home_office', 'light'] Task:Get toilet paper response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['crayon', 'trashcan', 'orchid', 'cpuscreen', 'ceiling', 'bedroom', 'table_cloth', 'ceilinglamp', 'tvstand', 'mousepad', 'closetdrawer', 'dining_room', 'wall', 'nightstand', 'powersocket', 'bench', 'bed', 'novel', 'food_food', 'mouthwash', 'coffe_maker', 'oven_mitts', 'curtain', 'doorjamb', 'cards', 'dresser', 'cupboard', 'bathtub', 'home_office', 'light'] Task:Read book response: { "thoughts": Go to the book shelf, get a book, open the book and read the book., "actions": ['[WALK] <home_office>', '[WALK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[READ] <novel>'] }

Scene_Objects:['spectacles', 'pot', 'sheets', 'walllamp', 'knifeblock', 'drawing', 'orchid', 'floor', 'bedroom', 'mail', 'food_bacon', 'laptop', 'mat', 'plate', 'faucet', 'food_orange', 'pillow', 'wall', 'bench', 'box', 'bed', 'photoframe', 'mouse', 'kitchen_counter', 'cupboard', 'sink', 'napkin', 'bathroom_cabinet', 'table', 'tooth_paste'] Task:Bring dirty plate to sink response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'ground_coffee', 'cpuscreen', 'floor', 'ceiling', 'keyboard', 'toaster', 'ceilinglamp', 'mat', 'faucet', 'food_orange', 'bowl', 'wall', 'wall_clock', 'cutting_board', 'bed', 'photoframe', 'coffe_maker', 'mouthwash', 'coffee_filter', 'water', 'doorjamb', 'pencil', 'kitchen_counter', 'hair', 'controller', 'sink', 'soap'] Task:Make coffee response: { "thoughts": Open coffee maker. Put filter in main basket, put ground coffee in filter, fill reservoir with water, turn on coffee maker., "actions": ['[WALK] <dining_room>', '[WALK] <coffe_maker>', '[FIND] <coffe_maker>', '[OPEN] <coffe_maker>', '[FIND] <coffee_filter>', '[GRAB] <coffee_filter>', '[PUTBACK] <coffee_filter> <coffe_maker>', '[FIND] <ground_coffee>', '[GRAB] <ground_coffee>', '[PUTBACK] <ground_coffee> <coffe_maker>', '[GRAB] <ground_coffee>', '[PUTOBJBACK] <ground_coffee>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <coffe_maker>', '[CLOSE] <coffe_maker>', '[SWITCHON] <coffe_maker>'] }

Scene_Objects:['sponge', 'food_pizza', 'filing_cabinet', 'microwave', 'chair', 'walllamp', 'orchid', 'knifeblock', 'bathroom_counter', 'ceiling', 'phone', 'stamp', 'keyboard', 'thread', 'computer', 'stovefan', 'toaster', 'plate', 'shower', 'mousepad', 'form', 'wall', 'food_cheese', 'bed', 'console', 'headset', 'dresser', 'spoon', 'bathroom_cabinet', 'bag'] Task:Walk to room response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'filing_cabinet', 'toilet', 'freezer', 'bathroom', 'detergent', 'bathroom_counter', 'floor', 'bedroom', 'toaster', 'plate', 'shower', 'dining_room', 'nightstand', 'oven', 'cup', 'coffe_maker', 'food_food', 'television', 'tray', 'kitchen_counter', 'dresser', 'door', 'sink', 'bathtub', 'home_office', 'table', 'dishwasher', 'soap', 'board_game'] Task:Wash dishes with dishwasher response: { "thoughts": Walk to Kitchen, find dishwasher. Find vessels to be washed. Open dishwasher, put vessels in dish washer, close dish washer and switch it on., "actions": ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[FIND] <cup>', '[GRAB] <cup>', '[PUTBACK] <cup> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[GRAB] <cup>', '[PUTBACK] <cup> <plate>', '[GRAB] <cup>', '[PUTBACK] <cup> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>'] }

Scene_Objects:['juice', 'beer', 'freezer', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'character', 'desk', 'folder', 'keyboard', 'computer', 'ceilinglamp', 'window', 'mousepad', 'couch', 'pillow', 'bowl', 'food_kiwi', 'wall', 'powersocket', 'food_food', 'curtain', 'doorjamb', 'mouse', 'door', 'light', 'table'] Task:Drink response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'toilet', 'chair', 'bathroom', 'drawing', 'knife', 'clothes_underwear', 'floor', 'mail', 'food_bacon', 'piano_bench', 'stovefan', 'ceilinglamp', 'plate', 'deck_of_cards', 'toaster', 'oil', 'wall', 'wall_clock', 'oven', 'cup', 'novel', 'food_food', 'television', 'oven_mitts', 'cards', 'cupboard', 'conditioner', 'table'] Task:Eat dinner response: { "thoughts": Sit down at the dinning table with my family and eat dinner., "actions": ['[WALK] <dining_room>', '[WALK] <table>', '[FIND] <chair>', '[PULL] <chair>', '[SIT] <chair>', '[FIND] <food_food>', '[TURNTO] <food_food>', '[LOOKAT] <food_food>', '[GRAB] <food_food>', '[FIND] <plate>', '[PUTBACK] <food_food> <plate>', '[GRAB] <food_food>', '[PUTOBJBACK] <food_food>', '[FIND] <fork>', '[GRAB] <fork>', '[EAT] <plate>'] }

Scene_Objects:['chair', 'ground_coffee', 'bathroom', 'detergent', 'dough', 'knifeblock', 'drawing', 'food_egg', 'floor', 'bedroom', 'keyboard', 'purse', 'mop_bucket', 'stovefan', 'mousepad', 'food_orange', 'bed', 'check', 'toilet_paper', 'food_rice', 'tray', 'shaving_cream', 'mouse', 'cd', 'dresser', 'cupboard', 'door', 'bathroom_cabinet', 'clothes_skirt', 'creditcard'] Task:Turn on light response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'toilet', 'detergent', 'hanger', 'floor', 'phone', 'stamp', 'toaster', 'balanceball', 'oil', 'pillow', 'dining_room', 'wall_clock', 'toy', 'newspaper', 'keys', 'photoframe', 'food_food', 'clothes_gloves', 'rag', 'doorjamb', 'mouse', 'dishrack', 'dresser', 'cupboard', 'hairdryer', 'spoon', 'table', 'light', 'scrabble'] Task:Pet cat response: { "thoughts": Pet Cat, "actions": ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[WALK] <cat>', '[TURNTO] <cat>', '[LOOKAT] <cat>', '[TOUCH] <cat>'] }

Scene_Objects:['dry_pasta', 'pot', 'jelly', 'freezer', 'bathroom', 'trashcan', 'milk', 'toothbrush', 'drawing', 'bathroom_counter', 'floor', 'desk', 'bookshelf', 'alcohol', 'table_cloth', 'faucet', 'shower', 'form', 'powersocket', 'bench', 'bed', 'food_food', 'kitchen_counter', 'headset', 'vacuum_cleaner', 'cupboard', 'door', 'clothes_scarf', 'food_steak', 'soap'] Task:Grab things response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'chair', 'orchid', 'drawing', 'cpuscreen', 'bills', 'floor', 'ceiling', 'phone', 'character', 'desk', 'keyboard', 'computer', 'mail', 'mat', 'ceilinglamp', 'tvstand', 'laptop', 'mousepad', 'clothes_socks', 'wall', 'nightstand', 'oven', 'powersocket', 'television', 'mouse', 'shoes', 'comb', 'door', 'light'] Task:Check email response: { "thoughts": Turn on laptop. Connect to Internet. Type in the url. Check for new email messages., "actions": ['[WALK] <home_office>', '[WALK] <chair>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <laptop>', '[SWITCHON] <laptop>', '[FIND] <keyboard>', '[TYPE] <keyboard>', '[TURNTO] <laptop>', '[LOOKAT] <laptop>', '[FIND] <mail>', '[GRAB] <mail>', '[READ] <mail>'] }

Scene_Objects:['dry_pasta', 'tablelamp', 'food_salt', 'chair', 'walllamp', 'detergent', 'drawing', 'clothes_underwear', 'floor', 'bedroom', 'toaster', 'ceilinglamp', 'tvstand', 'shower', 'food_noodles', 'garbage_can', 'mousepad', 'microphone', 'wall', 'nightstand', 'food_vegetable', 'bed', 'food_food', 'coffee_filter', 'mouse', 'sink', 'home_office', 'table', 'dishwasher', 'pantry'] Task:Organize pantry response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'scissors', 'microwave', 'ceilingfan', 'drawing', 'knifeblock', 'orchid', 'floor', 'ceiling', 'desk', 'bookshelf', 'purse', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'window', 'couch', 'wall', 'nightstand', 'child', 'cup', 'television', 'curtain', 'centerpiece', 'food_steak', 'hairdryer', 'table', 'vase'] Task:Watch TV response: { "thoughts": Turn on tv. Sit with kids., "actions": ['[WALK] <home_office>', '[WALK] <television>', '[SWITCHON] <television>', '[WALK] <couch>', '[FIND] <child>', '[GREET] <child>', '[FIND] <child>', '[GREET] <child>', '[SIT] <couch>', '[TURNTO] <television>', '[WATCH] <television>', '[TURNTO] <television>', '[WATCH] <television>', '[TURNTO] <television>', '[WATCH] <television>'] }

Scene_Objects:['tablelamp', 'juice', 'chair', 'freezer', 'walllamp', 'cpuscreen', 'food_egg', 'floor', 'ceiling', 'desk', 'bedroom', 'keyboard', 'computer', 'toaster', 'mat', 'ceilinglamp', 'faucet', 'picture', 'homework', 'mousepad', 'wall', 'oven', 'toy', 'newspaper', 'check', 'television', 'mouse', 'laundry_detergent', 'conditioner', 'laser_pointer'] Task:Push in desk chair response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sponge', 'food_salt', 'chair', 'detergent', 'trashcan', 'dough', 'drawing', 'character', 'computer', 'button', 'brush', 'mat', 'couch', 'clothes_pants', 'clothes_hat', 'wall', 'nightstand', 'basket_for_clothes', 'food_cheese', 'rag', 'kitchen_counter', 'shoes', 'vacuum_cleaner', 'laundry_detergent', 'conditioner', 'sink', 'home_office', 'table', 'clothes_shirt', 'washing_machine'] Task:Wash clothes response: { "thoughts": Walk to bathroom, open wash-machine, lift laundry basket, grab cloth and put into wash-machine one by one, put down laundry basket, pour detergent, close wash-machine, turn on wash-machine., "actions": ['[WALK] <bathroom>', '[WALK] <washing_machine>', '[FIND] <washing_machine>', '[OPEN] <washing_machine>', '[FIND] <basket_for_clothes>', '[GRAB] <basket_for_clothes>', '[FIND] <clothes_pants>', '[GRAB] <clothes_pants>', '[PUTBACK] <clothes_pants> <washing_machine>', '[FIND] <clothes_shirt>', '[GRAB] <clothes_shirt>', '[PUTBACK] <clothes_shirt> <washing_machine>', '[PUTOBJBACK] <basket_for_clothes>', '[WALK] <laundry_detergent>', '[FIND] <laundry_detergent>', '[GRAB] <laundry_detergent>', '[POUR] <laundry_detergent> <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>'] }

Scene_Objects:['sheets', 'filing_cabinet', 'juice', 'microwave', 'chair', 'walllamp', 'orchid', 'cpuscreen', 'floor', 'ceiling', 'desk', 'bedroom', 'keyboard', 'computer', 'ceilinglamp', 'mat', 'shower', 'faucet', 'window', 'mousepad', 'food_orange', 'wall', 'television', 'curtain', 'after_shave', 'mouse', 'dresser', 'door', 'napkin', 'table'] Task:Clean screen response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'detergent', 'knifeblock', 'bathroom_counter', 'floor', 'ceiling', 'character', 'stamp', 'keyboard', 'toaster', 'plate', 'faucet', 'tvstand', 'bowl', 'wall', 'oven', 'photoframe', 'coffe_maker', 'food_food', 'ice', 'curtain', 'shaving_cream', 'kitchen_counter', 'shoes', 'dishrack', 'cupboard', 'sink', 'bathroom_cabinet', 'dishwasher'] Task:Wash dishes with dishwasher response: { "thoughts": Walk to the kitchen. Open the dishwasher and turn on the faucet. Rinse off the dishes. Put the dishes in the dishwasher. Put detergent in the dishwasher. Close the dishwasher. Switch on the dishwasher., "actions": ['[WALK] <dining_room>', '[WALK] <dishwasher>', '[FIND] <dishwasher>', '[OPEN] <dishwasher>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <plate>', '[GRAB] <plate>', '[RINSE] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[RINSE] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <plate>', '[GRAB] <plate>', '[RINSE] <plate>', '[PUTBACK] <plate> <dishwasher>', '[FIND] <detergent>', '[GRAB] <detergent>', '[PUTBACK] <detergent> <dishwasher>', '[CLOSE] <dishwasher>', '[SWITCHON] <dishwasher>'] }

Scene_Objects:['chair', 'walllamp', 'blow_dryer', 'orchid', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'brush', 'ceilinglamp', 'mat', 'laptop', 'mousepad', 'dining_room', 'wall', 'powersocket', 'food_food', 'oven_mitts', 'kettle', 'mouse', 'cd', 'door', 'hairdryer', 'napkin', 'sink', 'table', 'light'] Task:Wash monitor response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['food_pizza', 'tablelamp', 'toilet', 'chair', 'detergent', 'trashcan', 'orchid', 'floor', 'ceiling', 'stamp', 'man', 'bookshelf', 'purse', 'toaster', 'mat', 'oil', 'mousepad', 'nightstand', 'cup', 'photoframe', 'newspaper', 'coffe_maker', 'tray', 'curtain', 'mouse', 'headset', 'cupboard', 'door', 'bathroom_cabinet', 'dishwasher'] Task:Answer door response: { "thoughts": Wait until doorbell rings, look to see who it is outside and open the door if you feel so inclined., "actions": ['[WALK] <home_office>', '[WALK] <man>', '[FIND] <man>', '[GREET] <man>'] }

Scene_Objects:['sheets', 'filing_cabinet', 'food_salt', 'measuring_cup', 'toilet', 'jelly', 'drawing', 'floor', 'phone', 'ceiling', 'character', 'bookshelf', 'alcohol', 'mat', 'shower', 'foundation', 'electric_shaver', 'mousepad', 'wall', 'toy', 'basket_for_clothes', 'photoframe', 'wine', 'dresser', 'laundry_detergent', 'food_steak', 'door', 'napkin', 'bathroom_cabinet', 'dishwasher'] Task:Pick up toys response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['dog', 'food_egg', 'bathroom_counter', 'folder', 'bedroom', 'computer', 'table_cloth', 'piano_bench', 'stovefan', 'tvstand', 'faucet', 'foundation', 'homework', 'couch', 'nightstand', 'powersocket', 'oven', 'basket_for_clothes', 'cup', 'keys', 'food_food', 'mouthwash', 'after_shave', 'doorjamb', 'shoes', 'controller', 'maindoor', 'bag', 'dirt', 'coffee'] Task:Get ready to leave response: { "thoughts": Get your jacket and shoes on, locate the keys off the side table, walk out the front door and secure building with keys when you leave, "actions": ['[WALK] <home_office>', '[WALK] <shoes>', '[FIND] <shoes>', '[GRAB] <shoes>', '[PUTON] <shoes>', '[FIND] <keys>', '[GRAB] <keys>'] }

Scene_Objects:['dry_pasta', 'food_ice_cream', 'walllamp', 'nail_polish', 'cat', 'orchid', 'drawing', 'floor', 'ceiling', 'purse', 'alcohol', 'mail', 'table_cloth', 'mat', 'tvstand', 'ceilinglamp', 'window', 'couch', 'pillow', 'towel', 'wall', 'oven', 'cup', 'food_cheese', 'television', 'curtain', 'doorjamb', 'door', 'table', 'clothes_shirt'] Task:Straighten paintings on wall response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['microwave', 'toilet', 'floor', 'ceiling', 'phone', 'bedroom', 'bookshelf', 'keyboard', 'toaster', 'ceilinglamp', 'plate', 'faucet', 'shower', 'window', 'tvstand', 'pillow', 'wall', 'wall_clock', 'powersocket', 'photoframe', 'coffe_maker', 'water', 'doorjamb', 'mouse', 'kitchen_counter', 'dresser', 'cupboard', 'sink', 'light', 'table'] Task:Drink response: { "thoughts": Walk to kitchen, grab a glass, walk to sink, turn on tap and pour water into glass, drink from glass., "actions": ['[WALK] <dining_room>', '[WALK] <cup>', '[FIND] <cup>', '[GRAB] <cup>', '[WALK] <sink>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <cup>', '[DRINK] <cup>'] }

Scene_Objects:['pot', 'filing_cabinet', 'food_salt', 'toilet', 'chair', 'bathroom', 'food_carrot', 'cpuscreen', 'shampoo', 'phone', 'ceiling', 'bedroom', 'desk', 'computer', 'toaster', 'shower', 'foundation', 'dustpan', 'photoframe', 'coffe_maker', 'food_rice', 'tray', 'curtain', 'doorjamb', 'console', 'cupboard', 'bathroom_cabinet', 'light', 'dishwasher', 'creditcard'] Task:Put umbrella away response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['juice', 'toilet', 'chair', 'freezer', 'detergent', 'food_carrot', 'drawing', 'knifeblock', 'floor', 'ceiling', 'food_chicken', 'bedroom', 'piano_bench', 'ceilinglamp', 'mat', 'shower', 'faucet', 'oil', 'food_orange', 'wall', 'nightstand', 'powersocket', 'photoframe', 'food_food', 'check', 'doorjamb', 'vacuum_cleaner', 'door', 'table', 'light'] Task:Put groceries in Fridge response: { "thoughts": Put the groceries on the table into the fridge, "actions": ['[WALK] <dining_room>', '[WALK] <table>', '[FIND] <food_chicken>', '[GRAB] <food_chicken>', '[FIND] <freezer>', '[OPEN] <freezer>', '[PUTBACK] <food_chicken> <freezer>', '[CLOSE] <freezer>', '[FIND] <food_carrot>', '[GRAB] <food_carrot>', '[FIND] <freezer>', '[OPEN] <freezer>', '[PUTIN] <food_carrot> <freezer>', '[CLOSE] <freezer>'] }

Scene_Objects:['sheets', 'pot', 'filing_cabinet', 'crayon', 'cat', 'food_butter', 'trashcan', 'bathroom_counter', 'floor', 'folder', 'mail', 'tvstand', 'window', 'mousepad', 'towel', 'wall', 'nightstand', 'bench', 'toy', 'basket_for_clothes', 'cup', 'food_cheese', 'light_bulb', 'food_food', 'television', 'curtain', 'shoes', 'dresser', 'door', 'sink'] Task:Pick up toys response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['fork', 'filing_cabinet', 'food_pizza', 'knifeblock', 'food_egg', 'hanger', 'phone', 'desk', 'tea_bag', 'purse', 'envelope', 'clothes_jacket', 'table_cloth', 'faucet', 'window', 'closetdrawer', 'clothes_pants', 'food_jam', 'wall', 'basket_for_clothes', 'bed', 'cd', 'comb', 'laundry_detergent', 'clothes_scarf', 'napkin', 'home_office', 'bathroom_cabinet', 'washing_machine', 'teeth'] Task:Wash clothes response: { "thoughts": Walk to bathroom. Open washing maschine. Grab pants and put it into washing maschine. Pour laundry detergent into washing machine and close the washing maschine. Plug in washing machine., "actions": ['[WALK] <bathroom>', '[WALK] <washing_machine>', '[FIND] <washing_machine>', '[OPEN] <washing_machine>', '[FIND] <clothes_pants>', '[GRAB] <clothes_pants>', '[PUTBACK] <clothes_pants> <washing_machine>', '[WALK] <laundry_detergent>', '[FIND] <laundry_detergent>', '[GRAB] <laundry_detergent>', '[POUR] <laundry_detergent> <washing_machine>', '[CLOSE] <washing_machine>', '[PLUGIN] <washing_machine>'] }

Scene_Objects:['beer', 'chair', 'band-aids', 'walllamp', 'bathroom', 'detergent', 'food_carrot', 'drawing', 'floor', 'ceiling', 'mat', 'faucet', 'mousepad', 'food_noodles', 'couch', 'wall', 'basket_for_clothes', 'photoframe', 'light_bulb', 'novel', 'television', 'coffee_filter', 'tray', 'diary', 'mouse', 'pencil', 'cd', 'chessboard', 'bathroom_cabinet', 'creditcard'] Task:Wipe down baseboards please response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['tablelamp', 'toilet', 'chair', 'trashcan', 'ceilingfan', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'desk', 'bedroom', 'keyboard', 'bookshelf', 'computer', 'alcohol', 'ceilinglamp', 'balanceball', 'mousepad', 'wall', 'nightstand', 'food_cheese', 'toothbrush_holder', 'doorjamb', 'towel_rack', 'mouse', 'cupboard', 'bathroom_cabinet', 'light', 'home_office'] Task:Work response: { "thoughts": Type on a computer in the home office., "actions": ['[WALK] <home_office>', '[WALK] <computer>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <keyboard>', '[TYPE] <keyboard>'] }

Scene_Objects:['walllamp', 'food_carrot', 'drawing', 'orchid', 'food_egg', 'bathroom_counter', 'floor', 'phone', 'character', 'desk', 'bookshelf', 'stovefan', 'ceilinglamp', 'shower', 'faucet', 'window', 'oil', 'couch', 'clothes_pants', 'pillow', 'wall', 'tape', 'cup', 'novel', 'tray', 'curtain', 'mouse', 'chessboard', 'controller', 'table'] Task:Read book response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['ground_coffee', 'nail_polish', 'ceilingfan', 'drawing', 'knifeblock', 'cpuscreen', 'floor', 'ceiling', 'phone', 'remote_control', 'computer', 'button', 'mail', 'ceilinglamp', 'tvstand', 'balanceball', 'shower', 'window', 'couch', 'pillow', 'dining_room', 'wall', 'bench', 'tape', 'television', 'curtain', 'food_onion', 'cupboard', 'table', 'shoe_rack'] Task:Watch TV response: { "thoughts": Go to the living room, sit on the couch, find the remote, switch on the TV and watch, "actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>', '[TURNTO] <television>', '[WATCH] <television>'] }

Scene_Objects:['pot', 'food_bread', 'food_ice_cream', 'tea', 'walllamp', 'drawing', 'bills', 'knifeblock', 'orchid', 'bathroom_counter', 'floor', 'keyboard', 'bookshelf', 'envelope', 'computer', 'ceilinglamp', 'iron', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'oven', 'toy', 'television', 'tray', 'curtain', 'sink', 'bathroom_cabinet', 'table'] Task:Read magazine response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['microwave', 'toilet', '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: { "thoughts": Walk to Kitchen and find coffee maker, find coffee filter and place it in coffee maker. Find ground coffee and water. put both in coffee maker. Close the coffee maker and switch it on., "actions": ['[WALK] <dining_room>', '[WALK] <coffe_maker>', '[FIND] <coffe_maker>', '[OPEN] <coffe_maker>', '[FIND] <coffee_filter>', '[GRAB] <coffee_filter>', '[PUTBACK] <coffee_filter> <coffe_maker>', '[FIND] <ground_coffee>', '[GRAB] <ground_coffee>', '[PUTBACK] <ground_coffee> <coffe_maker>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <coffe_maker>', '[CLOSE] <coffe_maker>', '[SWITCHON] <coffe_maker>'] }

Scene_Objects:['pot', 'food_pizza', 'jelly', 'chair', 'freezer', 'nail_polish', 'milk', 'hanger', 'floor', 'phone', 'ceiling', 'clothes_jacket', 'piano_bench', 'window', 'oil', 'wall', 'cup', 'keys', 'food_food', 'curtain', 'doorjamb', 'cards', 'pencil', 'vacuum_cleaner', 'dresser', 'pajamas', 'hairdryer', 'door', 'bag', 'bathroom_cabinet'] Task:Vacuum response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'juice', 'blow_dryer', 'walllamp', 'detergent', 'floor', 'ceiling', 'bedroom', 'keyboard', 'purse', 'tvstand', 'deck_of_cards', 'clothes_pants', 'dining_room', 'wall', 'nightstand', 'powersocket', 'oven', 'keys', 'tray', 'kettle', 'shoes', 'hair', 'sink', 'home_office', 'table', 'dishwasher', 'soap', 'board_game', 'dirt'] Task:Hang up car keys response: { "thoughts": Open the front door. Enter the entrance hall. Take out car keys from purse. Hang car keys up on hook on the wall., "actions": ['[WALK] <home_office>', '[WALK] <purse>', '[FIND] <purse>', '[OPEN] <purse>', '[FIND] <keys>', '[GRAB] <keys>', '[CLOSE] <purse>'] }

Scene_Objects:['dry_pasta', 'food_bread', 'freezer', 'food_carrot', 'milk', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'piano_bench', 'ceilinglamp', 'mousepad', 'garbage_can', 'clothes_hat', 'food_orange', 'food_dessert', 'wall', 'powersocket', 'food_vegetable', 'food_cheese', 'doorjamb', 'lighter', 'mouse', 'coffee', 'door', 'light', 'colander', 'teeth'] Task:Rotate stock in refrigerator response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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_bread', 'microwave', 'freezer', 'ground_coffee', 'dough', 'orchid', 'hanger', 'floor', 'ceiling', 'character', 'desk', 'tea_bag', 'toaster', 'faucet', 'shower', 'closetdrawer', 'wall', 'wall_clock', 'powersocket', 'oven', 'cutting_board', 'photoframe', 'coffe_maker', 'coffee_filter', 'water', 'curtain', 'kitchen_counter', 'cupboard', 'sink'] Task:Make coffee response: { "thoughts": I walk to the kitchen and find the coffee machine. I open the coffee machine and pour a filter in it. I open the cupboard and grab ground coffee. I put ground coffee in the filter and water in the coffee machine. I close the coffee machine. I switch on the coffee machine and wait, "actions": ['[WALK] <dining_room>', '[WALK] <coffe_maker>', '[FIND] <coffe_maker>', '[OPEN] <coffe_maker>', '[FIND] <coffee_filter>', '[GRAB] <coffee_filter>', '[PUTBACK] <coffee_filter> <coffe_maker>', '[FIND] <cupboard>', '[OPEN] <cupboard>', '[FIND] <ground_coffee>', '[GRAB] <ground_coffee>', '[PUTBACK] <ground_coffee> <coffe_maker>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <coffe_maker>', '[CLOSE] <coffe_maker>', '[SWITCHON] <coffe_maker>'] }

Scene_Objects:['spectacles', 'dog', 'detergent', 'trashcan', 'orchid', 'needle', 'bathroom_counter', 'computer', 'button', 'table_cloth', 'deck_of_cards', 'stereo', 'shower', 'floor_lamp', 'towel', 'wall', 'love_seat', 'cup', 'newspaper', 'basket_for_clothes', 'photoframe', 'food_rice', 'wooden_spoon', 'doorjamb', 'dresser', 'controller', 'door', 'napkin', 'home_office', 'clothes_skirt'] Task:Read response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'food_pizza', 'tablelamp', 'microwave', 'floor', 'ceiling', 'desk', 'bookshelf', 'stovefan', 'mat', 'ceilinglamp', 'laptop', 'window', 'homework', 'oil', 'closetdrawer', 'couch', 'nightstand', 'wall', 'cup', 'bed', 'food_food', 'mouthwash', 'toothbrush_holder', 'oven_mitts', 'razor', 'food_donut', 'check', 'clothes_scarf', 'bathroom_cabinet'] Task:Go to sleep response: { "thoughts": Walk to bedroom. Walk to bed, lie in bed., "actions": ['[WALK] <bedroom>', '[WALK] <bed>', '[LIE] <bed>'] }

Scene_Objects:['glue', 'crayon', 'freezer', 'nail_polish', 'food_carrot', 'milk', 'cpuscreen', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'tvstand', 'mousepad', 'dining_room', 'wall', 'powersocket', 'cup', 'bed', 'food_food', 'doorjamb', 'mouse', 'pajamas', 'controller', 'door', 'spoon', 'napkin', 'light', 'dirt'] Task:Get glass of milk response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['filing_cabinet', 'chair', 'walllamp', 'bathroom', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'remote_control', 'computer', 'clothes_jacket', 'mat', 'tvstand', 'ceilinglamp', 'picture', 'closetdrawer', 'couch', 'pillow', 'wall', 'pasta', 'photoframe', 'coffe_maker', 'television', 'doorjamb', 'cards', 'dresser', 'door', 'colander'] Task:Change TV channel response: { "thoughts": I walk into the living room. I sit on the couch and grab the remote. Then I turn on the TV and change the channel., "actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>'] }

Scene_Objects:['fork', 'filing_cabinet', 'tablelamp', 'toilet', 'jelly', 'walllamp', 'drawing', 'orchid', 'floor', 'ceiling', 'desk', 'remote_control', 'computer', 'ceilinglamp', 'tvstand', 'mat', 'faucet', 'window', 'mousepad', 'couch', 'pillow', 'wall', 'powersocket', 'television', 'coffee_filter', 'curtain', 'doorjamb', 'centerpiece', 'door', 'table'] Task:Watch TV response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'food_salt', 'freezer', 'orchid', 'drawing', 'wallshelf', 'clothes_underwear', 'floor', 'phone', 'bookshelf', 'stovefan', 'pillow', 'wall', 'wall_clock', 'cutting_board', 'box', 'shelf', 'newspaper', 'bed', 'novel', 'coffe_maker', 'toilet_paper', 'wooden_spoon', 'hairbrush', 'door', 'home_office', 'table', 'light', 'vase'] Task:Read book response: { "thoughts": Pick up the book, open to current page, read the words., "actions": ['[WALK] <home_office>', '[WALK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[READ] <novel>'] }

Scene_Objects:['ironing_board', 'dry_pasta', 'food_pizza', 'beer', 'dog', 'chair', 'walllamp', 'orchid', 'cpuscreen', 'phone', 'folder', 'character', 'keyboard', 'stovefan', 'laptop', 'iron', 'picture', 'mousepad', 'microphone', 'powersocket', 'cup', 'novel', 'food_food', 'food_donut', 'wine', 'pencil', 'bag', 'table', 'soap', 'clothes_shirt'] Task:Iron shirt response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'chair', 'walllamp', 'drawing', 'wallshelf', 'hanger', 'floor', 'ceiling', 'desk', 'bookshelf', 'remote_control', 'keyboard', 'computer', 'mat', 'tvstand', 'ceilinglamp', 'picture', 'closetdrawer', 'couch', 'pillow', 'wall', 'powersocket', 'photoframe', 'television', 'rag', 'doorjamb', 'cards', 'dresser', 'sink', 'dishwasher'] Task:Watch TV response: { "thoughts": Sit on my couch directly opposite my tv , switch on my tv with the remote control and watch, "actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>', '[PUTOBJBACK] <remote_control>', '[TURNTO] <television>', '[WATCH] <television>'] }

Scene_Objects:['food_pizza', 'food_ice_cream', 'tea', 'knifeblock', 'drawing', 'orchid', 'bathroom_counter', 'floor', 'ceiling', 'envelope', 'alcohol', 'mat', 'faucet', 'shower', 'towel', 'wall', 'toy', 'bed', 'wooden_spoon', 'doorjamb', 'vacuum_cleaner', 'pajamas', 'laundry_detergent', 'door', 'sink', 'bathroom_cabinet', 'light', 'clothes_skirt', 'soap', 'hands_both'] Task:Hand washing response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['filing_cabinet', 'blender', 'food_ice_cream', 'toilet', 'walllamp', 'detergent', 'drawing', 'orchid', 'wallshelf', 'floor', 'ceiling', 'computer', 'toaster', 'mat', 'tvstand', 'laptop', 'ceilinglamp', 'brush', 'couch', 'pillow', 'dining_room', 'wall', 'child', 'oven', 'photoframe', 'bed', 'television', 'doorjamb', 'mouse', 'dishwasher'] Task:Let baby learn how to walk response: { "thoughts": The baby tries to stand up and balances on the couch and there are no sharp edges so it's safe., "actions": ['[WALK] <home_office>', '[WALK] <child>', '[FIND] <child>', '[TOUCH] <child>', '[GREET] <child>', '[FIND] <couch>', '[TURNTO] <couch>', '[POINTAT] <couch>', '[TURNTO] <child>', '[LOOKAT] <child>'] }

Scene_Objects:['food_bread', 'filing_cabinet', 'tablelamp', 'scissors', 'microwave', 'chair', 'freezer', 'food_butter', 'drawing', 'knife', 'cpuscreen', 'floor', 'folder', 'desk', 'keyboard', 'computer', 'mail', 'mat', 'shower', 'mousepad', 'wall', 'nightstand', 'bed', 'ice', 'after_shave', 'doorjamb', 'mouse', 'kitchen_counter', 'food_steak', 'light'] Task:Work response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'filing_cabinet', 'measuring_cup', 'mop', 'microwave', 'toilet', 'bathroom', 'drawing', 'orchid', 'floor', 'ceiling', 'bedroom', 'computer', 'piano_bench', 'ceilinglamp', 'plate', 'deck_of_cards', 'mat', 'mousepad', 'couch', 'pillow', 'wall', 'bed', 'novel', 'television', 'doorjamb', 'door', 'coffee_cup', 'table', 'light'] Task:Relax on sofa response: { "thoughts": you walk to the living room, open the door, find a comfy sofa, sit on it, read a book or sip a cup of coffee and relax., "actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[FIND] <coffee_cup>', '[GRAB] <coffee_cup>', '[SIT] <couch>', '[FIND] <novel>', '[GRAB] <novel>', '[READ] <novel>', '[DRINK] <coffee_cup>'] }

Scene_Objects:['spectacles', 'pot', 'walllamp', 'nail_polish', 'knifeblock', 'kitchen_cabinet', 'floor', 'ceiling', 'bookshelf', 'computer', 'faucet', 'oil', 'dining_room', 'wall', 'nightstand', 'oven', 'powersocket', 'toy', 'cup', 'coffee_filter', 'shaving_cream', 'kitchen_counter', 'dresser', 'cupboard', 'door', 'sink', 'home_office', 'table', 'dishwasher', 'bathroom_cabinet'] Task:Get glass of water response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'pot', 'tablelamp', 'chair', 'dog', 'walllamp', 'ceilingfan', 'knifeblock', 'needle', 'bathroom_counter', 'floor', 'computer', 'shoe-shine_kit', 'dustpan', 'box', 'cup', 'bed', 'keys', 'television', 'food_donut', 'tray', 'curtain', 'doorjamb', 'kettle', 'kitchen_counter', 'shoes', 'comb', 'sink', 'bathroom_cabinet', 'board_game'] Task:Brush teeth response: { "thoughts": go to the bathroom and brush your teeth, "actions": ['[WALK] <bathroom>', '[WALK] <toothbrush>', '[FIND] <toothbrush>', '[GRAB] <toothbrush>', '[WALK] <tooth_paste>', '[FIND] <tooth_paste>', '[GRAB] <tooth_paste>', '[POUR] <tooth_paste> <toothbrush>'] }

Scene_Objects:['pot', 'walllamp', 'toothbrush', 'knifeblock', 'orchid', 'cpuscreen', 'drawing', 'shampoo', 'floor', 'ceiling', 'desk', 'mop_bucket', 'stovefan', 'laptop', 'tvstand', 'faucet', 'wall', 'nightstand', 'oven', 'tape', 'food_food', 'tray', 'curtain', 'kettle', 'kitchen_counter', 'cupboard', 'conditioner', 'sink', 'bathroom_cabinet', 'table'] Task:Wipe down counter response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'picture', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'tape', 'check', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'pencil', 'comb', 'dresser', 'door', 'light'] Task:Work response: { "thoughts": Walk to home office, walk to desk, sit in chair, turn on computer, look at computer, click mouse and type on keyboard., "actions": ['[WALK] <home_office>', '[WALK] <desk>', '[FIND] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[SWITCHON] <computer>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[FIND] <mouse>', '[TOUCH] <mouse>', '[FIND] <keyboard>', '[TYPE] <keyboard>', '[TURNTO] <computer>', '[LOOKAT] <computer>'] }

Scene_Objects:['fork', 'food_bread', 'dog', 'ground_coffee', 'drawing', 'knifeblock', 'cpuscreen', 'floor', 'desk', 'bedroom', 'alcohol', 'mop_bucket', 'stovefan', 'laptop', 'tvstand', 'ceilinglamp', 'shoe-shine_kit', 'window', 'mat', 'mousepad', 'food_orange', 'pillow', 'powersocket', 'coffe_maker', 'fly', 'coffee_pot', 'kitchen_counter', 'cupboard', 'dishwasher', 'soap'] Task:Watch fly response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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:['filing_cabinet', 'tablelamp', 'chair', 'detergent', 'food_carrot', 'orchid', 'drawing', 'needle', 'hanger', 'floor', 'computer', 'bookmark', 'mat', 'laptop', 'faucet', 'shower', 'couch', 'candle', 'wall', 'nightstand', 'pasta', 'bed', 'photoframe', 'toilet_paper', 'toothbrush_holder', 'tray', 'kitchen_counter', 'controller', 'spoon', 'table'] Task:Read book response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'freezer', 'bathroom', 'food_carrot', 'drawing', 'orchid', 'wallshelf', 'food_egg', 'bathroom_counter', 'shampoo', 'phone', 'mat', 'ceilinglamp', 'shower', 'electric_shaver', 'clothes_socks', 'couch', 'microphone', 'dining_room', 'food_kiwi', 'nightstand', 'wall', 'check', 'food_food', 'after_shave', 'mouse', 'kitchen_counter', 'cupboard', 'home_office', 'laser_pointer'] Task:Turn on light response: { "thoughts": I go home and it's dark so I can not see anything, "actions": ['[WALK] <home_office>', '[WALK] <floor_lamp>', '[FIND] <floor_lamp>', '[SWITCHON] <floor_lamp>'] }

Scene_Objects:['filing_cabinet', 'band-aids', 'walllamp', 'drawing', 'food_egg', 'bathroom_counter', 'ceiling', 'stamp', 'desk', 'cleaning_solution', 'computer', 'stovefan', 'deck_of_cards', 'faucet', 'tvstand', 'window', 'couch', 'wall', 'nightstand', 'coffe_maker', 'television', 'mirror', 'after_shave', 'paper_towel', 'clothes_dress', 'sink', 'bag', 'bathroom_cabinet', 'dishwasher', 'laser_pointer'] Task:Clean mirror response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'ground_coffee', 'walllamp', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'phone', 'bedroom', 'ceilinglamp', 'tvstand', 'stereo', 'food_orange', 'cup', 'bed', 'keys', 'novel', 'food_food', 'coffe_maker', 'mouthwash', 'coin', 'check', 'diary', 'coffee_pot', 'mouse', 'dresser', 'hair', 'table', 'light'] Task:Listen to music response: { "thoughts": I go to my bedroom, and then I switch on the radio, "actions": ['[WALK] <bedroom>', '[WALK] <stereo>', '[FIND] <stereo>', '[SWITCHON] <stereo>'] }

Scene_Objects:['freezer', 'walllamp', 'bathroom', 'drawing', 'orchid', 'floor', 'ceiling', 'video_game_console', 'desk', 'keyboard', 'stovefan', 'ceilinglamp', 'tvstand', 'mat', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'video_game_controller', 'television', 'food_rice', 'ice', 'curtain', 'doorjamb', 'dresser', 'door', 'bathroom_cabinet', 'table', 'laser_pointer'] Task:Play games response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'crayon', 'microwave', 'toilet', 'knife', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'shampoo', 'computer', 'mat', 'tvstand', 'picture', 'oil', 'couch', 'pillow', 'wall', 'powersocket', 'cup', 'food_food', 'tray', 'doorjamb', 'mouse', 'kitchen_counter', 'shoes', 'cupboard', 'bathroom_cabinet', 'light', 'instrument_violin'] Task:Pick up phone response: { "thoughts": I walk over to the phone. .I reach my arm out. I open my hand. I place my hand on the phone. I close my fingers around the phone. I pick up the phone., "actions": ['[WALK] <phone>', '[TOUCH] <phone>', '[GRAB] <phone>'] }

Scene_Objects:['pot', 'food_pizza', 'filing_cabinet', 'microwave', 'toilet', 'dog', 'freezer', 'bathroom', 'drawing', 'cpuscreen', 'floor', 'ceiling', 'phone', 'folder', 'keyboard', 'thread', 'computer', 'mat', 'window', 'dining_room', 'wall', 'nightstand', 'bench', 'cup', 'wine', 'curtain', 'kitchen_counter', 'hairbrush', 'clothes_dress', 'food_steak'] Task:Look out window response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['glue', 'toilet', 'chair', 'walllamp', 'drawing', 'wallshelf', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'computer', 'mail', 'mat', 'tvstand', 'ceilinglamp', 'closetdrawer', 'couch', 'pillow', 'dining_room', 'wall', 'cutting_board', 'photoframe', 'bed', 'television', 'doorjamb', 'dishrack', 'dresser', 'door', 'dishwasher'] Task:Watch TV response: { "thoughts": go to the living room to watch TV, "actions": ['[RUN] <home_office>', '[WALK] <remote_control>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[WALK] <couch>', '[SIT] <couch>', '[FIND] <television>', '[TURNTO] <television>', '[POINTAT] <television>', '[TOUCH] <remote_control>', '[SWITCHON] <television>', '[TURNTO] <television>', '[LOOKAT] <television>', '[WATCH] <television>', '[DROP] <remote_control>', '[TURNTO] <television>', '[LOOKAT] <television>', '[WATCH] <television>'] }

Scene_Objects:['fork', 'sheets', 'scissors', 'microwave', 'walllamp', 'bathroom', 'detergent', 'trashcan', 'toothbrush', 'floor', 'phone', 'toaster', 'mat', 'tvstand', 'dustpan', 'wall', 'box', 'photoframe', 'coffe_maker', 'check', 'oven_mitts', 'food_rice', 'curtain', 'coffee_pot', 'kitchen_counter', 'cupboard', 'hairdryer', 'dishwasher', 'soap', 'coffee'] Task:Take dishes out of dishwasher response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'picture', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'check', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'door', 'light'] Task:Browse internet response: { "thoughts": I walk into my home office and walk up to my desk. I pull out the chair and sit down. I turn on the computer. After the computer is turned on I click on the google icon. I enter Disney Cruise Line into the search bar and browse the internet., "actions": ['[WALK] <home_office>', '[WALK] <desk>', '[FIND] <chair>', '[PULL] <chair>', '[SIT] <chair>', '[FIND] <computer>', '[TURNTO] <computer>', '[SWITCHON] <computer>', '[FIND] <keyboard>', '[TURNTO] <keyboard>', '[LOOKAT] <keyboard>', '[TYPE] <keyboard>'] }

Scene_Objects:['toilet', 'chair', 'dog', 'trashcan', 'orchid', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'stamp', 'bookshelf', 'thread', 'computer', 'food_bacon', 'brush', 'ceilinglamp', 'shower', 'window', 'mousepad', 'food_jam', 'pillow', 'wall', 'check', 'curtain', 'doorjamb', 'shoes', 'dresser', 'light', 'laser_pointer'] Task:Dust response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'blender', 'freezer', 'walllamp', 'nail_polish', 'trashcan', 'knifeblock', 'orchid', 'hanger', 'floor', 'bedroom', 'keyboard', 'computer', 'stereo', 'window', 'oil', 'couch', 'pillow', 'wall', 'cup', 'bed', 'food_donut', 'curtain', 'centerpiece', 'console', 'shoes', 'dresser', 'maindoor', 'home_office', 'light'] Task:Listen to music response: { "thoughts": Turn on radio, put on favorite channel, listen to music., "actions": ['[WALK] <bedroom>', '[WALK] <stereo>', '[FIND] <stereo>', '[SWITCHON] <stereo>', '[FIND] <bed>', '[LIE] <bed>'] }

Scene_Objects:['pot', 'toilet', 'freezer', 'drawing', 'knifeblock', 'bathroom_counter', 'floor', 'ceiling', 'bookshelf', 'alcohol', 'stovefan', 'brush', 'tvstand', 'picture', 'dustpan', 'wall', 'powersocket', 'cup', 'keys', 'light_bulb', 'food_food', 'doorjamb', 'controller', 'door', 'clothes_scarf', 'bathroom_cabinet', 'light', 'dishwasher', 'home_office', 'clothes_shirt'] Task:Turn on light response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'cd_player', 'knife', 'character', 'tea_bag', 'remote_control', 'button', 'table_cloth', 'ceilinglamp', 'shoe-shine_kit', 'shower', 'food_peanut_butter', 'candle', 'nightstand', 'bench', 'cutting_board', 'shelf', 'bed', 'photoframe', 'oven_mitts', 'food_rice', 'doorjamb', 'shaving_cream', 'mouse', 'dresser', 'controller', 'sink', 'table', 'clothes_skirt'] Task:Listen to music response: { "thoughts": I walk to my living room. Find CD player. Plugin the CD player to Power. Also find the remote control. Push the Botton, "actions": ['[WALK] <home_office>', '[WALK] <cd_player>', '[FIND] <cd_player>', '[PLUGIN] <cd_player>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <button>', '[PUSH] <button>'] }

Scene_Objects:['food_salt', 'freezer', 'walllamp', 'drawing', 'floor', 'ceiling', 'bookshelf', 'mail', 'table_cloth', 'shower', 'foundation', 'dustpan', 'microphone', 'wall', 'powersocket', 'food_food', 'check', 'television', 'rag', 'doorjamb', 'kitchen_counter', 'shoes', 'cupboard', 'door', 'sink', 'hairdryer', 'light', 'clothes_skirt', 'scrabble', 'creditcard'] Task:Turn off light response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'blender', 'walllamp', 'ceilingfan', 'dough', 'drawing', 'floor', 'ceiling', 'desk', 'stamp', 'remote_control', 'food_cake', 'computer', 'toaster', 'ceilinglamp', 'tvstand', 'balanceball', 'iron', 'window', 'couch', 'wall', 'oven', 'photoframe', 'novel', 'television', 'curtain', 'home_office', 'table', 'instrument_guitar'] Task:Watch TV response: { "thoughts": Sit on the couch nd watch t.V, "actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[FIND] <television>', '[SWITCHON] <television>', '[TURNTO] <television>', '[LOOKAT] <television>'] }

Scene_Objects:['fork', 'filing_cabinet', 'food_bread', 'microwave', 'trashcan', 'drawing', 'knifeblock', 'cpuscreen', 'hanger', 'bathroom_counter', 'bedroom', 'tea_bag', 'tvstand', 'window', 'form', 'pillow', 'broom', 'bench', 'basket_for_clothes', 'newspaper', 'bed', 'check', 'coffe_maker', 'tray', 'door', 'home_office', 'light', 'bathroom_cabinet', 'tooth_paste', 'coffee'] Task:Get dressed response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'freezer', 'detergent', 'trashcan', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'phone', 'bedroom', 'desk', 'bookshelf', 'mail', 'toaster', 'ceilinglamp', 'faucet', 'window', 'pillow', 'dining_room', 'wall', 'powersocket', 'oven', 'novel', 'television', 'wooden_spoon', 'curtain', 'doorjamb', 'pencil', 'vacuum_cleaner', 'light'] Task:Turn on light response: { "thoughts": switching on light in an area, "actions": ['[WALK] <home_office>', '[WALK] <light>', '[FIND] <light>', '[SWITCHON] <light>'] }

Scene_Objects:['pot', 'food_pizza', 'food_ice_cream', 'chair', 'band-aids', 'toothbrush', 'orchid', 'needle', 'hanger', 'bedroom', 'desk', 'bookshelf', 'piano_bench', 'ceilinglamp', 'mat', 'clothes_socks', 'microphone', 'dining_room', 'bowl', 'nightstand', 'tray', 'curtain', 'diary', 'dresser', 'cupboard', 'spoon', 'bathroom_cabinet', 'table', 'dishwasher', 'light'] Task:Open door response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['sheets', 'tablelamp', 'toilet', 'walllamp', 'bathroom', 'trashcan', 'wallshelf', 'clothes_underwear', 'floor', 'desk', 'mail', 'button', 'stovefan', 'toaster', 'mousepad', 'soap', 'pillow', 'dining_room', 'photoframe', 'television', 'doorjamb', 'towel_rack', 'mouse', 'dresser', 'controller', 'bathtub', 'bathroom_cabinet', 'colander', 'clothes_shirt', 'coffee'] Task:Pet cat response: { "thoughts": Find a cat in the kitchen and touch it, "actions": ['[WALK] <dining_room>', '[WALK] <cat>', '[FIND] <cat>', '[WALK] <cat>', '[TOUCH] <cat>'] }

Scene_Objects:['pot', 'filing_cabinet', 'tablelamp', 'microwave', 'chair', 'band-aids', 'orchid', 'drawing', 'bathroom_counter', 'floor', 'envelope', 'computer', 'ceilinglamp', 'tvstand', 'stereo', 'form', 'wall', 'nightstand', 'powersocket', 'cup', 'bed', 'photoframe', 'coffe_maker', 'check', 'centerpiece', 'dresser', 'food_steak', 'napkin', 'tooth_paste', 'shoe_rack'] Task:Listen to music response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'food_carrot', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'thread', 'mail', 'ceilinglamp', 'mat', 'iron', 'balanceball', 'faucet', 'food_orange', 'pillow', 'wall', 'pasta', 'box', 'cup', 'newspaper', 'food_food', 'check', 'toilet_paper', 'chessboard', 'maindoor', 'napkin', 'creditcard'] Task:Put groceries in Fridge response: { "thoughts": Putting groceries in refridgerator, "actions": ['[WALK] <dining_room>', '[WALK] <food_food>', '[FIND] <food_food>', '[GRAB] <food_food>', '[FIND] <freezer>', '[OPEN] <freezer>', '[PUTIN] <food_food> <freezer>', '[CLOSE] <freezer>'] }

Scene_Objects:['microwave', 'chair', 'walllamp', 'orchid', 'bills', 'cpuscreen', 'knifeblock', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'ceilinglamp', 'mat', 'mousepad', 'microphone', 'form', 'towel', 'wall', 'oven', 'food_food', 'television', 'ice', 'cards', 'mouse', 'pencil', 'cupboard', 'door', 'clothes_scarf', 'table'] Task:Clean response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['band-aids', 'trashcan', 'wallshelf', 'clothes_underwear', 'desk', 'keyboard', 'mail', 'computer', 'tvstand', 'shower', 'window', 'clothes_socks', 'couch', 'food_peanut_butter', 'pillow', 'basket_for_clothes', 'keys', 'coffe_maker', 'television', 'food_donut', 'tray', 'rag', 'headset', 'clothes_scarf', 'bathtub', 'sink', 'light', 'dishwasher', 'soap', 'washing_machine'] Task:Wash clothes response: { "thoughts": Get dirty clothes out of basket for clothes in bedroom, carry dirty clothes to laundry room, place dirty clothes in washing machine, add laundry detergent to washing machine, turn washing machine on, set type of wash, start washing machine, "actions": ['[WALK] <bedroom>', '[WALK] <basket_for_clothes>', '[FIND] <basket_for_clothes>', '[OPEN] <basket_for_clothes>', '[GRAB] <basket_for_clothes>', '[WALK] <bathroom>', '[WALK] <washing_machine>', '[FIND] <washing_machine>', '[OPEN] <washing_machine>', '[PUTBACK] <basket_for_clothes> <washing_machine>', '[FIND] <soap>', '[GRAB] <soap>', '[PUTBACK] <soap> <washing_machine>', '[FIND] <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>'] }

Scene_Objects:['sheets', 'mop', 'bathroom', 'knife', 'hanger', 'bathroom_counter', 'ceiling', 'bedroom', 'desk', 'food_cake', 'window', 'electric_shaver', 'microphone', 'food_jam', 'dining_room', 'wall', 'photoframe', 'food_food', 'television', 'curtain', 'mouse', 'kitchen_counter', 'cd', 'chessboard', 'dresser', 'hairbrush', 'clothes_scarf', 'bathroom_cabinet', 'dishwasher', 'instrument_violin'] Task:Put on coat response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'freezer', 'walllamp', 'bathroom', 'toothbrush', 'orchid', 'hanger', 'longboard', 'phone', 'desk', 'computer', 'food_bacon', 'table_cloth', 'clothes_jacket', 'brush', 'ceilinglamp', 'faucet', 'foundation', 'mousepad', 'clothes_pants', 'pasta', 'light_bulb', 'toothbrush_holder', 'coin', 'coffee_filter', 'towel_rack', 'hair', 'vase', 'tooth_paste'] Task:Wash teeth response: { "thoughts": WALK TO THE BATHROOM USE PASTE AND BRUSH TO WASH YOUR TEETH, "actions": ['[WALK] <bathroom>', '[WALK] <toothbrush_holder>', '[FIND] <toothbrush_holder>', '[FIND] <tooth_paste>', '[GRAB] <tooth_paste>', '[FIND] <toothbrush>', '[GRAB] <toothbrush>'] }

Scene_Objects:['tablelamp', 'toilet', 'jelly', 'chair', 'trashcan', 'woman', 'orchid', 'bathroom_counter', 'thread', 'mail', 'toaster', 'mousepad', 'clothes_socks', 'candle', 'towel', 'dining_room', 'broom', 'pasta', 'powersocket', 'oven', 'food_food', 'after_shave', 'pencil', 'hair', 'hairdryer', 'door', 'napkin', 'home_office', 'colander', 'shoe_rack'] Task:Greet guests response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'tablelamp', 'chair', 'walllamp', 'drawing', 'orchid', 'cpuscreen', 'wallshelf', 'hanger', 'floor', 'phone', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'ceilinglamp', 'tvstand', 'picture', 'mousepad', 'couch', 'pillow', 'wall', 'nightstand', 'oven', 'powersocket', 'television', 'tray', 'doorjamb', 'towel_rack', 'mouse', 'pencil', 'dresser', 'door', 'light'] Task:Write an email response: { "thoughts": I need to write an e-mail to my boss about the meeting at work tomorrow., "actions": ['[WALK] <home_office>', '[WALK] <desk>', '[FIND] <keyboard>', '[GRAB] <keyboard>', '[OPEN] <desk>', '[PUTBACK] <keyboard> <desk>', '[FIND] <mouse>', '[GRAB] <mouse>', '[FIND] <mousepad>', '[PUTBACK] <mouse> <mousepad>', '[PLUGIN] <keyboard>', '[PLUGIN] <mouse>', '[FIND] <computer>', '[SWITCHON] <computer>', '[FIND] <chair>', '[SIT] <chair>', '[TURNTO] <computer>', '[LOOKAT] <computer>', '[TYPE] <keyboard>', '[GRAB] <mouse>', '[TOUCH] <mouse>', '[TURNTO] <computer>', '[LOOKAT] <computer>'] }

Scene_Objects:['microwave', 'walllamp', 'bathroom', 'detergent', 'food_carrot', 'orchid', 'drawing', 'cpuscreen', 'food_egg', 'hanger', 'bathroom_counter', 'floor', 'ceiling', 'brush', 'ceilinglamp', 'tvstand', 'mat', 'stereo', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'basket_for_clothes', 'television', 'curtain', 'doorjamb', 'door', 'sink', 'table'] Task:Watch TV response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['toilet', '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: { "thoughts": Changing channel, "actions": ['[WALK] <home_office>', '[WALK] <television>', '[FIND] <television>', '[SWITCHON] <television>', '[FIND] <couch>', '[SIT] <couch>', '[FIND] <remote_control>', '[GRAB] <remote_control>', '[TURNTO] <television>', '[POINTAT] <television>', '[DROP] <remote_control>'] }

Scene_Objects:['filing_cabinet', 'toilet', 'chair', 'ground_coffee', 'detergent', 'drawing', 'clothes_underwear', 'hanger', 'floor', 'bookshelf', 'envelope', 'mat', 'shower', 'faucet', 'homework', 'mousepad', 'wall', 'toy', 'photoframe', 'check', 'coffee_filter', 'food_onion', 'shaving_cream', 'cards', 'mouse', 'dresser', 'hairbrush', 'door', 'soap', 'scrabble'] Task:Clean response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['microwave', 'walllamp', 'dough', 'drawing', 'orchid', 'cpuscreen', 'food_egg', 'hanger', 'floor', 'keyboard', 'bookshelf', 'food_bacon', 'ceilinglamp', 'window', 'couch', 'pillow', 'wall', 'cup', 'novel', 'check', 'curtain', 'doorjamb', 'diary', 'pencil', 'kitchen_counter', 'bag', 'home_office', 'table', 'dishwasher', 'soap'] Task:Relax on sofa response: { "thoughts": move to living room, locate sofa, move to sofa, sit on sofa, lie on sofa, "actions": ['[WALK] <home_office>', '[WALK] <couch>', '[FIND] <couch>', '[WALK] <couch>', '[SIT] <couch>', '[LIE] <couch>'] }

Scene_Objects:['tablelamp', 'microwave', 'toilet', 'food_carrot', 'knife', 'drawing', 'bills', 'floor', 'desk', 'computer', 'food_bacon', 'bookmark', 'homework', 'candle', 'dining_room', 'wall', 'nightstand', 'toy', 'basket_for_clothes', 'bed', 'check', 'coffe_maker', 'television', 'mouse', 'hair', 'controller', 'conditioner', 'sink', 'spoon', 'home_office'] Task:Breakfast response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'water_glass', 'pot', 'glue', 'walllamp', 'trashcan', 'knifeblock', 'ceiling', 'clothes_jacket', 'stovefan', 'toaster', 'mat', 'faucet', 'microphone', 'wall', 'cup', 'bed', 'food_food', 'check', 'water', 'food_donut', 'curtain', 'kitchen_counter', 'chessboard', 'cupboard', 'laundry_detergent', 'sink', 'spoon', 'bathroom_cabinet', 'dirt'] Task:Drink response: { "thoughts": I walk to the kitchen. open the cupboard. Find the water glass, grab it. Fill the glass with water and drink water., "actions": ['[WALK] <dining_room>', '[WALK] <cupboard>', '[FIND] <cupboard>', '[OPEN] <cupboard>', '[FIND] <water_glass>', '[GRAB] <water_glass>', '[WALK] <water>', '[FIND] <water>', '[GRAB] <water>', '[POUR] <water> <water_glass>', '[DRINK] <water_glass>'] }

Scene_Objects:['walllamp', 'nail_polish', 'bathroom', 'detergent', 'knife', 'cpuscreen', 'dvd_player', 'bedroom', 'computer', 'table_cloth', 'mop_bucket', 'brush', 'toaster', 'shower', 'window', 'couch', 'dining_room', 'wall', 'pasta', 'cup', 'photoframe', 'after_shave', 'pencil', 'kitchen_counter', 'dresser', 'clothes_dress', 'sink', 'instrument_guitar', 'light', 'creditcard'] Task:Sit response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['spectacles', 'food_salt', 'chair', 'jelly', 'walllamp', 'milk', 'floor', 'bedroom', 'keyboard', 'button', 'plate', 'tvstand', 'shower', 'window', 'dustpan', 'dining_room', 'nightstand', 'oven', 'basket_for_clothes', 'check', 'coffe_maker', 'tray', 'controller', 'clothes_dress', 'food_steak', 'napkin', 'soap', 'clothes_shirt', 'scrabble', 'washing_machine'] Task:Wash clothes response: { "thoughts": Walk to Bathroom. Find basket for clothes. Lift clothes dress from basket. Find washing machine. Walk to washing machine. Put clothes in washing machine. Put soap in washing machine. Switch on washing machine., "actions": ['[WALK] <bathroom>', '[WALK] <basket_for_clothes>', '[FIND] <basket_for_clothes>', '[FIND] <clothes_dress>', '[GRAB] <clothes_dress>', '[FIND] <washing_machine>', '[WALK] <washing_machine>', '[OPEN] <washing_machine>', '[PUTBACK] <clothes_dress> <washing_machine>', '[FIND] <soap>', '[GRAB] <soap>', '[PUTBACK] <soap> <washing_machine>', '[CLOSE] <washing_machine>', '[SWITCHON] <washing_machine>'] }

Scene_Objects:['spectacles', 'pot', 'filing_cabinet', 'crayon', 'toilet', 'ground_coffee', 'drawing', 'bills', 'cpuscreen', 'clothes_underwear', 'orchid', 'floor', 'phone', 'ceiling', 'bookshelf', 'mat', 'shower', 'foundation', 'homework', 'dining_room', 'wall', 'tape', 'cutting_board', 'photoframe', 'newspaper', 'food_food', 'toothbrush_holder', 'curtain', 'kitchen_counter', 'soap'] Task:Put clothes away response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'cd_player', 'walllamp', 'trashcan', 'food_carrot', 'drawing', 'needle', 'bathroom_counter', 'dvd_player', 'bedroom', 'bookshelf', 'alcohol', 'piano_bench', 'bookmark', 'laptop', 'stereo', 'couch', 'pillow', 'broom', 'bench', 'basket_for_clothes', 'mouse', 'shoes', 'headset', 'food_steak', 'sink', 'hairdryer', 'instrument_guitar', 'door', 'bag'] Task:Listen to music response: { "thoughts": Find the playback device you want to listen to. turn on. press play. enjoyu music., "actions": ['[WALK] <bedroom>', '[WALK] <cd_player>', '[FIND] <cd_player>', '[SWITCHON] <cd_player>'] }

Scene_Objects:['food_bread', 'food_salt', 'beer', 'walllamp', 'drawing', 'orchid', 'knifeblock', 'clothes_underwear', 'floor', 'folder', 'man', 'computer', 'toaster', 'ceilinglamp', 'stereo', 'window', 'homework', 'mousepad', 'couch', 'microphone', 'pillow', 'wall', 'nightstand', 'keys', 'food_food', 'wooden_spoon', 'curtain', 'doorjamb', 'hair', 'table'] Task:Have conversation with boyfriend response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'toilet', 'chair', 'freezer', 'detergent', 'orchid', 'food_egg', 'bathroom_counter', 'floor', 'ceiling', 'character', 'bedroom', 'purse', 'toaster', 'mat', 'faucet', 'iron', 'mousepad', 'wall', 'powersocket', 'cup', 'coffe_maker', 'water', 'shaving_cream', 'kitchen_counter', 'cupboard', 'food_steak', 'sink', 'clothes_scarf', 'colander'] Task:Drink response: { "thoughts": I go in the kitchen and get the glass near the sink. I open the faucet, then I pour water in it, turn off the faucet and drink it., "actions": ['[WALK] <dining_room>', '[WALK] <sink>', '[FIND] <cup>', '[GRAB] <cup>', '[FIND] <faucet>', '[SWITCHON] <faucet>', '[FIND] <water>', '[PUTBACK] <cup> <sink>', '[GRAB] <cup>', '[SWITCHOFF] <faucet>', '[DRINK] <cup>'] }

Scene_Objects:['microwave', 'chair', 'freezer', 'walllamp', 'bathroom', 'orchid', 'cpuscreen', 'clothes_underwear', 'bathroom_counter', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'mat', 'shower', 'mousepad', 'pillow', 'dining_room', 'wall', 'wall_clock', 'nightstand', 'tape', 'bed', 'console', 'mouse', 'clothes_scarf', 'light', 'soap', 'teeth'] Task:Check email response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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:['filing_cabinet', 'crayon', 'walllamp', 'woman', 'knifeblock', 'hanger', 'ceiling', 'folder', 'character', 'man', 'mop_bucket', 'bookmark', 'shower', 'window', 'electric_shaver', 'pillow', 'dining_room', 'wall_clock', 'cutting_board', 'bed', 'television', 'wine', 'curtain', 'mouse', 'pencil', 'sink', 'home_office', 'light', 'dirt', 'shoe_rack'] Task:Greet people response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'tablelamp', 'beer', 'toilet', 'freezer', 'walllamp', 'drawing', 'knifeblock', 'kitchen_cabinet', 'floor', 'ceiling', 'food_chicken', 'stovefan', 'mat', 'toaster', 'shower', 'nightstand', 'wall', 'powersocket', 'oven', 'photoframe', 'food_food', 'food_donut', 'tray', 'doorjamb', 'kitchen_counter', 'cupboard', 'door', 'light', 'dishwasher'] Task:Cook some food response: { "thoughts": Walk into the kitchen. Open the fridge. Take out the chicken. Open the kitchen cabinet. Take out the frying pan. Put the chicken in the frying pan. Put the frying pan on the stove. Turn on the stove. Cook the chicken., "actions": ['[WALK] <dining_room>', '[WALK] <freezer>', '[OPEN] <freezer>', '[FIND] <food_chicken>', '[GRAB] <food_chicken>', '[CLOSE] <freezer>', '[FIND] <kitchen_cabinet>', '[OPEN] <kitchen_cabinet>', '[FIND] <pot>', '[GRAB] <pot>', '[CLOSE] <kitchen_cabinet>', '[WALK] <oven>', '[PUTBACK] <pot> <oven>', '[PUTBACK] <food_chicken> <oven>', '[SWITCHON] <oven>'] }

Scene_Objects:['walllamp', 'drawing', 'orchid', 'knifeblock', 'cpuscreen', 'bathroom_counter', 'floor', 'ceiling', 'remote_control', 'ceilinglamp', 'tvstand', 'mat', 'window', 'couch', 'pillow', 'wall', 'powersocket', 'basket_for_clothes', 'food_cheese', 'television', 'curtain', 'doorjamb', 'cd', 'conditioner', 'door', 'clothes_scarf', 'home_office', 'table', 'dishwasher', 'instrument_guitar'] Task:Watch TV response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'trashcan', 'orchid', 'drawing', 'floor', 'ceiling', 'bookshelf', 'computer', 'stovefan', 'ceilinglamp', 'mat', 'shower', 'window', 'food_noodles', 'couch', 'pillow', 'wall', 'photoframe', 'toothbrush_holder', 'curtain', 'doorjamb', 'chessboard', 'door', 'bathtub', 'bag', 'home_office', 'light', 'table', 'dishwasher', 'instrument_violin'] Task:Admire art response: { "thoughts": Looking at painting, art, "actions": ['[WALK] <home_office>', '[WALK] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>', '[FIND] <drawing>', '[TURNTO] <drawing>', '[LOOKAT] <drawing>'] }

Scene_Objects:['glue', 'pot', 'toilet', 'chair', 'freezer', 'band-aids', 'bathroom', 'food_carrot', 'drawing', 'floor', 'mat', 'window', 'couch', 'clothes_hat', 'form', 'pillow', 'bench', 'food_food', 'check', 'coffe_maker', 'toilet_paper', 'ice', 'centerpiece', 'doorjamb', 'cupboard', 'home_office', 'table', 'light', 'bathroom_cabinet', 'scrabble'] Task:Eat dinner response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. 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', 'tablelamp', 'food_salt', 'toilet', 'chair', 'bathroom', 'trashcan', 'drawing', 'floor', 'character', 'desk', 'purse', 'computer', 'table_cloth', 'stovefan', 'ceilinglamp', 'tvstand', 'shower', 'foundation', 'couch', 'pillow', 'nightstand', 'powersocket', 'novel', 'tray', 'mouse', 'bathroom_cabinet', 'soap', 'teeth'] Task:Pet cat response: { "thoughts": First I need to find the cat in the living room. Then I walk over to the cat and pet it gently., "actions": ['[WALK] <home_office>', '[WALK] <cat>', '[FIND] <cat>', '[WALK] <cat>', '[TOUCH] <cat>'] }

Scene_Objects:['chair', 'walllamp', 'cat', 'food_carrot', 'toothbrush', 'drawing', 'orchid', 'floor', 'mail', 'stovefan', 'ceilinglamp', 'window', 'mousepad', 'couch', 'food_jam', 'pillow', 'dining_room', 'wall', 'photoframe', 'mouthwash', 'tray', 'curtain', 'coffee_pot', 'pajamas', 'door', 'sink', 'bathroom_cabinet', 'table', 'light', 'tooth_paste'] Task:Relax response:

You serve as an AI task planner. 1. Your task is to create a plan to achieve a goal by converting it into a sequence of actions. Each action should follow the format "[verb] <target1> <target2>", where 'verb' represents the action, and 'target1' and 'target2' are optional arguments. 2. You must describe your plan in natural language at the beginning. After that, you should list all the actions together. Ensure that you response can be parsed by Python json.loads. Here is an example plan to achieve a goal for reference: Scene_Objects:['pot', 'food_salt', 'beer', 'chair', 'freezer', 'knifeblock', 'bathroom_counter', 'longboard', 'phone', 'keyboard', 'computer', 'food_bacon', 'tvstand', 'balanceball', 'stereo', 'mousepad', 'clothes_pants', 'nightstand', 'bench', 'bed', 'photoframe', 'novel', 'television', 'pencil', 'kitchen_counter', 'vacuum_cleaner', 'food_steak', 'sink', 'hairdryer', 'vase'] Task:Read book response: { "thoughts": Go to the book shelf, get a book, open the book and read the book., "actions": ['[WALK] <home_office>', '[WALK] <novel>', '[FIND] <novel>', '[GRAB] <novel>', '[READ] <novel>'] }

Scene_Objects:['dry_pasta', 'tea', 'chair', 'walllamp', 'bathroom', 'orchid', 'cpuscreen', 'hanger', 'floor', 'ceiling', 'desk', 'keyboard', 'computer', 'table_cloth', 'ceilinglamp', 'mat', 'mousepad', 'wall', 'pasta', 'powersocket', 'coffe_maker', 'doorjamb', 'mouse', 'pencil', 'kitchen_counter', 'cupboard', 'door', 'home_office', 'table', 'tooth_paste'] Task:Turn on computer response: