Housekeep: Tidying Virtual Households using Commonsense Reasoning

We introduce Housekeep, a benchmark to evaluate commonsense reasoning in the home for embodied AI. In Housekeep, an embodied agent must tidy a house by rearranging misplaced objects without explicit instructions specifying which objects need to be rearranged. Instead, the agent must learn from and i...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kant, Yash, Ramachandran, Arun, Yenamandra, Sriram, Gilitschenski, Igor, Batra, Dhruv, Szot, Andrew, Agrawal, Harsh
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Kant, Yash
Ramachandran, Arun
Yenamandra, Sriram
Gilitschenski, Igor
Batra, Dhruv
Szot, Andrew
Agrawal, Harsh
description We introduce Housekeep, a benchmark to evaluate commonsense reasoning in the home for embodied AI. In Housekeep, an embodied agent must tidy a house by rearranging misplaced objects without explicit instructions specifying which objects need to be rearranged. Instead, the agent must learn from and is evaluated against human preferences of which objects belong where in a tidy house. Specifically, we collect a dataset of where humans typically place objects in tidy and untidy houses constituting 1799 objects, 268 object categories, 585 placements, and 105 rooms. Next, we propose a modular baseline approach for Housekeep that integrates planning, exploration, and navigation. It leverages a fine-tuned large language model (LLM) trained on an internet text corpus for effective planning. We show that our baseline agent generalizes to rearranging unseen objects in unknown environments. See our webpage for more details: https://yashkant.github.io/housekeep/
doi_str_mv 10.48550/arxiv.2205.10712
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2205_10712</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2205_10712</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-fcebc2e481008fea23ed86a7fe5a2fcfe3070c996a046ddde318cf958cce43f43</originalsourceid><addsrcrecordid>eNotj81Kw0AUhWfThbQ-gCvnBZLObzJxV0K1QqEgwW24ztxpB5NMyRixb28bhQMHzgcHPkIeOMuV0ZqtYfwJ37kQTOeclVzckc0uTgk_Ec9PtAnuEoYjfQ_j1wQdndEpdi7RKd1AHfs-DgmvoW8IKQ7XdUUWHrqE9_-9JM3ztql32f7w8lpv9hkUpci8xQ8rUBnOmPEIQqIzBZQeNQhvPUpWMltVBTBVOOdQcmN9pY21qKRXckke_25nh_Y8hh7GS3tzaWcX-QsNQkXd</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Housekeep: Tidying Virtual Households using Commonsense Reasoning</title><source>arXiv.org</source><creator>Kant, Yash ; Ramachandran, Arun ; Yenamandra, Sriram ; Gilitschenski, Igor ; Batra, Dhruv ; Szot, Andrew ; Agrawal, Harsh</creator><creatorcontrib>Kant, Yash ; Ramachandran, Arun ; Yenamandra, Sriram ; Gilitschenski, Igor ; Batra, Dhruv ; Szot, Andrew ; Agrawal, Harsh</creatorcontrib><description>We introduce Housekeep, a benchmark to evaluate commonsense reasoning in the home for embodied AI. In Housekeep, an embodied agent must tidy a house by rearranging misplaced objects without explicit instructions specifying which objects need to be rearranged. Instead, the agent must learn from and is evaluated against human preferences of which objects belong where in a tidy house. Specifically, we collect a dataset of where humans typically place objects in tidy and untidy houses constituting 1799 objects, 268 object categories, 585 placements, and 105 rooms. Next, we propose a modular baseline approach for Housekeep that integrates planning, exploration, and navigation. It leverages a fine-tuned large language model (LLM) trained on an internet text corpus for effective planning. We show that our baseline agent generalizes to rearranging unseen objects in unknown environments. See our webpage for more details: https://yashkant.github.io/housekeep/</description><identifier>DOI: 10.48550/arxiv.2205.10712</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2022-05</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2205.10712$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2205.10712$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Kant, Yash</creatorcontrib><creatorcontrib>Ramachandran, Arun</creatorcontrib><creatorcontrib>Yenamandra, Sriram</creatorcontrib><creatorcontrib>Gilitschenski, Igor</creatorcontrib><creatorcontrib>Batra, Dhruv</creatorcontrib><creatorcontrib>Szot, Andrew</creatorcontrib><creatorcontrib>Agrawal, Harsh</creatorcontrib><title>Housekeep: Tidying Virtual Households using Commonsense Reasoning</title><description>We introduce Housekeep, a benchmark to evaluate commonsense reasoning in the home for embodied AI. In Housekeep, an embodied agent must tidy a house by rearranging misplaced objects without explicit instructions specifying which objects need to be rearranged. Instead, the agent must learn from and is evaluated against human preferences of which objects belong where in a tidy house. Specifically, we collect a dataset of where humans typically place objects in tidy and untidy houses constituting 1799 objects, 268 object categories, 585 placements, and 105 rooms. Next, we propose a modular baseline approach for Housekeep that integrates planning, exploration, and navigation. It leverages a fine-tuned large language model (LLM) trained on an internet text corpus for effective planning. We show that our baseline agent generalizes to rearranging unseen objects in unknown environments. See our webpage for more details: https://yashkant.github.io/housekeep/</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81Kw0AUhWfThbQ-gCvnBZLObzJxV0K1QqEgwW24ztxpB5NMyRixb28bhQMHzgcHPkIeOMuV0ZqtYfwJ37kQTOeclVzckc0uTgk_Ec9PtAnuEoYjfQ_j1wQdndEpdi7RKd1AHfs-DgmvoW8IKQ7XdUUWHrqE9_-9JM3ztql32f7w8lpv9hkUpci8xQ8rUBnOmPEIQqIzBZQeNQhvPUpWMltVBTBVOOdQcmN9pY21qKRXckke_25nh_Y8hh7GS3tzaWcX-QsNQkXd</recordid><startdate>20220521</startdate><enddate>20220521</enddate><creator>Kant, Yash</creator><creator>Ramachandran, Arun</creator><creator>Yenamandra, Sriram</creator><creator>Gilitschenski, Igor</creator><creator>Batra, Dhruv</creator><creator>Szot, Andrew</creator><creator>Agrawal, Harsh</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220521</creationdate><title>Housekeep: Tidying Virtual Households using Commonsense Reasoning</title><author>Kant, Yash ; Ramachandran, Arun ; Yenamandra, Sriram ; Gilitschenski, Igor ; Batra, Dhruv ; Szot, Andrew ; Agrawal, Harsh</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-fcebc2e481008fea23ed86a7fe5a2fcfe3070c996a046ddde318cf958cce43f43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Kant, Yash</creatorcontrib><creatorcontrib>Ramachandran, Arun</creatorcontrib><creatorcontrib>Yenamandra, Sriram</creatorcontrib><creatorcontrib>Gilitschenski, Igor</creatorcontrib><creatorcontrib>Batra, Dhruv</creatorcontrib><creatorcontrib>Szot, Andrew</creatorcontrib><creatorcontrib>Agrawal, Harsh</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kant, Yash</au><au>Ramachandran, Arun</au><au>Yenamandra, Sriram</au><au>Gilitschenski, Igor</au><au>Batra, Dhruv</au><au>Szot, Andrew</au><au>Agrawal, Harsh</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Housekeep: Tidying Virtual Households using Commonsense Reasoning</atitle><date>2022-05-21</date><risdate>2022</risdate><abstract>We introduce Housekeep, a benchmark to evaluate commonsense reasoning in the home for embodied AI. In Housekeep, an embodied agent must tidy a house by rearranging misplaced objects without explicit instructions specifying which objects need to be rearranged. Instead, the agent must learn from and is evaluated against human preferences of which objects belong where in a tidy house. Specifically, we collect a dataset of where humans typically place objects in tidy and untidy houses constituting 1799 objects, 268 object categories, 585 placements, and 105 rooms. Next, we propose a modular baseline approach for Housekeep that integrates planning, exploration, and navigation. It leverages a fine-tuned large language model (LLM) trained on an internet text corpus for effective planning. We show that our baseline agent generalizes to rearranging unseen objects in unknown environments. See our webpage for more details: https://yashkant.github.io/housekeep/</abstract><doi>10.48550/arxiv.2205.10712</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2205.10712
ispartof
issn
language eng
recordid cdi_arxiv_primary_2205_10712
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Housekeep: Tidying Virtual Households using Commonsense Reasoning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T19%3A02%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Housekeep:%20Tidying%20Virtual%20Households%20using%20Commonsense%20Reasoning&rft.au=Kant,%20Yash&rft.date=2022-05-21&rft_id=info:doi/10.48550/arxiv.2205.10712&rft_dat=%3Carxiv_GOX%3E2205_10712%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true