Text-driven object affordance for guiding grasp-type recognition in multimodal robot teaching

This study investigates how text-driven object affordance, which provides prior knowledge about grasp types for each object, affects image-based grasp-type recognition in robot teaching. The researchers created labeled datasets of first-person hand images to examine the impact of object affordance o...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-05
Hauptverfasser: Wake, Naoki, Saito, Daichi, Sasabuchi, Kazuhiro, Koike, Hideki, Ikeuchi, Katsushi
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Wake, Naoki
Saito, Daichi
Sasabuchi, Kazuhiro
Koike, Hideki
Ikeuchi, Katsushi
description This study investigates how text-driven object affordance, which provides prior knowledge about grasp types for each object, affects image-based grasp-type recognition in robot teaching. The researchers created labeled datasets of first-person hand images to examine the impact of object affordance on recognition performance. They evaluated scenarios with real and illusory objects, considering mixed reality teaching conditions where visual object information may be limited. The results demonstrate that object affordance improves image-based recognition by filtering out unlikely grasp types and emphasizing likely ones. The effectiveness of object affordance was more pronounced when there was a stronger bias towards specific grasp types for each object. These findings highlight the significance of object affordance in multimodal robot teaching, regardless of whether real objects are present in the images. Sample code is available on https://github.com/microsoft/arr-grasp-type-recognition.
doi_str_mv 10.48550/arxiv.2103.00268
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2103_00268</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2495189876</sourcerecordid><originalsourceid>FETCH-LOGICAL-a958-5a440a362ec53a05ca74008c20038aaa0175142b42df35e4048d4968d65518033</originalsourceid><addsrcrecordid>eNotkEtrwzAQhEWh0JDmB_RUQc9213rY8rGEviDQS67FbCTZVUgkV5ZD8u_rJD3tsnwz7AwhDwXkQkkJzxiP7pCzAngOwEp1Q2aM8yJTgrE7shiGLZzvFZOSz8j32h5TZqI7WE_DZmt1oti2IRr02tJpod3ojPMd7SIOfZZOvaXR6tB5l1zw1Hm6H3fJ7YPBHY1hExJNFvXPpLknty3uBrv4n3OyfntdLz-y1df75_JllWEtVSZRCEBeMqslR5AaKwGgNAPgChGhqGQh2EYw03JpBQhlRF0qU0pZKOB8Th6vtpfsTR_dHuOpOXfQXDqYiKcr0cfwO9ohNdswRj_91DBRTy61qkr-BwC3XsI</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2495189876</pqid></control><display><type>article</type><title>Text-driven object affordance for guiding grasp-type recognition in multimodal robot teaching</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Wake, Naoki ; Saito, Daichi ; Sasabuchi, Kazuhiro ; Koike, Hideki ; Ikeuchi, Katsushi</creator><creatorcontrib>Wake, Naoki ; Saito, Daichi ; Sasabuchi, Kazuhiro ; Koike, Hideki ; Ikeuchi, Katsushi</creatorcontrib><description>This study investigates how text-driven object affordance, which provides prior knowledge about grasp types for each object, affects image-based grasp-type recognition in robot teaching. The researchers created labeled datasets of first-person hand images to examine the impact of object affordance on recognition performance. They evaluated scenarios with real and illusory objects, considering mixed reality teaching conditions where visual object information may be limited. The results demonstrate that object affordance improves image-based recognition by filtering out unlikely grasp types and emphasizing likely ones. The effectiveness of object affordance was more pronounced when there was a stronger bias towards specific grasp types for each object. These findings highlight the significance of object affordance in multimodal robot teaching, regardless of whether real objects are present in the images. Sample code is available on https://github.com/microsoft/arr-grasp-type-recognition.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2103.00268</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Human-Computer Interaction ; Computer Science - Robotics ; Grasping (robotics) ; Heterogeneity ; Mixed reality ; Object recognition ; Robots</subject><ispartof>arXiv.org, 2023-05</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27925</link.rule.ids><backlink>$$Uhttps://doi.org/10.1007/s00138-023-01408-z$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.2103.00268$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Wake, Naoki</creatorcontrib><creatorcontrib>Saito, Daichi</creatorcontrib><creatorcontrib>Sasabuchi, Kazuhiro</creatorcontrib><creatorcontrib>Koike, Hideki</creatorcontrib><creatorcontrib>Ikeuchi, Katsushi</creatorcontrib><title>Text-driven object affordance for guiding grasp-type recognition in multimodal robot teaching</title><title>arXiv.org</title><description>This study investigates how text-driven object affordance, which provides prior knowledge about grasp types for each object, affects image-based grasp-type recognition in robot teaching. The researchers created labeled datasets of first-person hand images to examine the impact of object affordance on recognition performance. They evaluated scenarios with real and illusory objects, considering mixed reality teaching conditions where visual object information may be limited. The results demonstrate that object affordance improves image-based recognition by filtering out unlikely grasp types and emphasizing likely ones. The effectiveness of object affordance was more pronounced when there was a stronger bias towards specific grasp types for each object. These findings highlight the significance of object affordance in multimodal robot teaching, regardless of whether real objects are present in the images. Sample code is available on https://github.com/microsoft/arr-grasp-type-recognition.</description><subject>Artificial neural networks</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Human-Computer Interaction</subject><subject>Computer Science - Robotics</subject><subject>Grasping (robotics)</subject><subject>Heterogeneity</subject><subject>Mixed reality</subject><subject>Object recognition</subject><subject>Robots</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotkEtrwzAQhEWh0JDmB_RUQc9213rY8rGEviDQS67FbCTZVUgkV5ZD8u_rJD3tsnwz7AwhDwXkQkkJzxiP7pCzAngOwEp1Q2aM8yJTgrE7shiGLZzvFZOSz8j32h5TZqI7WE_DZmt1oti2IRr02tJpod3ojPMd7SIOfZZOvaXR6tB5l1zw1Hm6H3fJ7YPBHY1hExJNFvXPpLknty3uBrv4n3OyfntdLz-y1df75_JllWEtVSZRCEBeMqslR5AaKwGgNAPgChGhqGQh2EYw03JpBQhlRF0qU0pZKOB8Th6vtpfsTR_dHuOpOXfQXDqYiKcr0cfwO9ohNdswRj_91DBRTy61qkr-BwC3XsI</recordid><startdate>20230512</startdate><enddate>20230512</enddate><creator>Wake, Naoki</creator><creator>Saito, Daichi</creator><creator>Sasabuchi, Kazuhiro</creator><creator>Koike, Hideki</creator><creator>Ikeuchi, Katsushi</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230512</creationdate><title>Text-driven object affordance for guiding grasp-type recognition in multimodal robot teaching</title><author>Wake, Naoki ; Saito, Daichi ; Sasabuchi, Kazuhiro ; Koike, Hideki ; Ikeuchi, Katsushi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a958-5a440a362ec53a05ca74008c20038aaa0175142b42df35e4048d4968d65518033</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial neural networks</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Human-Computer Interaction</topic><topic>Computer Science - Robotics</topic><topic>Grasping (robotics)</topic><topic>Heterogeneity</topic><topic>Mixed reality</topic><topic>Object recognition</topic><topic>Robots</topic><toplevel>online_resources</toplevel><creatorcontrib>Wake, Naoki</creatorcontrib><creatorcontrib>Saito, Daichi</creatorcontrib><creatorcontrib>Sasabuchi, Kazuhiro</creatorcontrib><creatorcontrib>Koike, Hideki</creatorcontrib><creatorcontrib>Ikeuchi, Katsushi</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wake, Naoki</au><au>Saito, Daichi</au><au>Sasabuchi, Kazuhiro</au><au>Koike, Hideki</au><au>Ikeuchi, Katsushi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Text-driven object affordance for guiding grasp-type recognition in multimodal robot teaching</atitle><jtitle>arXiv.org</jtitle><date>2023-05-12</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>This study investigates how text-driven object affordance, which provides prior knowledge about grasp types for each object, affects image-based grasp-type recognition in robot teaching. The researchers created labeled datasets of first-person hand images to examine the impact of object affordance on recognition performance. They evaluated scenarios with real and illusory objects, considering mixed reality teaching conditions where visual object information may be limited. The results demonstrate that object affordance improves image-based recognition by filtering out unlikely grasp types and emphasizing likely ones. The effectiveness of object affordance was more pronounced when there was a stronger bias towards specific grasp types for each object. These findings highlight the significance of object affordance in multimodal robot teaching, regardless of whether real objects are present in the images. Sample code is available on https://github.com/microsoft/arr-grasp-type-recognition.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2103.00268</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-05
issn 2331-8422
language eng
recordid cdi_arxiv_primary_2103_00268
source arXiv.org; Free E- Journals
subjects Artificial neural networks
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Human-Computer Interaction
Computer Science - Robotics
Grasping (robotics)
Heterogeneity
Mixed reality
Object recognition
Robots
title Text-driven object affordance for guiding grasp-type recognition in multimodal robot teaching
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T04%3A08%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Text-driven%20object%20affordance%20for%20guiding%20grasp-type%20recognition%20in%20multimodal%20robot%20teaching&rft.jtitle=arXiv.org&rft.au=Wake,%20Naoki&rft.date=2023-05-12&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2103.00268&rft_dat=%3Cproquest_arxiv%3E2495189876%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2495189876&rft_id=info:pmid/&rfr_iscdi=true