Scalable Learned Geometric Feasibility for Cooperative Grasp and Motion Planning
This letter proposes a novel learned feasibility estimator that considers multi-modal grasp poses for grasp and motion planning. Grasp poses inherently have multi-modal structures, that is, continuous and discrete parameters. Mixed-integer programming (MIP) is one method that solves these multi-moda...
Gespeichert in:
Veröffentlicht in: | IEEE robotics and automation letters 2022-10, Vol.7 (4), p.11545-11552 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 11552 |
---|---|
container_issue | 4 |
container_start_page | 11545 |
container_title | IEEE robotics and automation letters |
container_volume | 7 |
creator | Park, Suhan Kim, Hyoung Cheol Baek, Jiyeong Park, Jaeheung |
description | This letter proposes a novel learned feasibility estimator that considers multi-modal grasp poses for grasp and motion planning. Grasp poses inherently have multi-modal structures, that is, continuous and discrete parameters. Mixed-integer programming (MIP) is one method that solves these multi-modal problems. However, searching for all the discrete parameters costs considerable time. Therefore, by learning the feasibility of each mode from the geometric variables, the problem can be solved efficiently within a given time limit. The feasibility of grasp poses is related to the pose of the object and nearby obstacles. Utilizing this information, we introduce learned geometric feasibility (LGF), which prioritizes the integer search of MIP. LGF is scalable to multiple robots and environments because it learns the feasibility using object-oriented information. It has been demonstrated to improve the number of solved MIP problems within the time limit and to be applicable to various environmental settings. |
doi_str_mv | 10.1109/LRA.2022.3202633 |
format | Article |
fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_9869726</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9869726</ieee_id><sourcerecordid>2711052060</sourcerecordid><originalsourceid>FETCH-LOGICAL-c221t-2155d03f2009270cf1c15f4da9b1611755f665011ee9cce3469b6365337f2c6e3</originalsourceid><addsrcrecordid>eNpNkE1LAzEQhoMoWGrvgpeA5635aBJzLMW2worFj3PIZieSst2syVbov3dLi3iZGZjnnYEHoVtKppQS_VC-zaeMMDblQ5WcX6AR40oVXEl5-W--RpOct4QQKpjiWozQ5t3ZxlYN4BJsaqHGK4g76FNweAk2hyo0oT9gHxNexNhBsn34AbxKNnfYtjV-iX2ILd40tm1D-3WDrrxtMkzOfYw-l08fi3VRvq6eF_OycIzRvmBUiJpwzwjRTBHnqaPCz2qrKyopVUJ4KQWhFEA7B3wmdSW5FJwrz5wEPkb3p7tdit97yL3Zxn1qh5eGqUGKYESSgSInyqWYcwJvuhR2Nh0MJeaozgzqzFGdOasbInenSACAP1w_Sq2G_S9FuGgo</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2711052060</pqid></control><display><type>article</type><title>Scalable Learned Geometric Feasibility for Cooperative Grasp and Motion Planning</title><source>IEEE Electronic Library (IEL)</source><creator>Park, Suhan ; Kim, Hyoung Cheol ; Baek, Jiyeong ; Park, Jaeheung</creator><creatorcontrib>Park, Suhan ; Kim, Hyoung Cheol ; Baek, Jiyeong ; Park, Jaeheung</creatorcontrib><description>This letter proposes a novel learned feasibility estimator that considers multi-modal grasp poses for grasp and motion planning. Grasp poses inherently have multi-modal structures, that is, continuous and discrete parameters. Mixed-integer programming (MIP) is one method that solves these multi-modal problems. However, searching for all the discrete parameters costs considerable time. Therefore, by learning the feasibility of each mode from the geometric variables, the problem can be solved efficiently within a given time limit. The feasibility of grasp poses is related to the pose of the object and nearby obstacles. Utilizing this information, we introduce learned geometric feasibility (LGF), which prioritizes the integer search of MIP. LGF is scalable to multiple robots and environments because it learns the feasibility using object-oriented information. It has been demonstrated to improve the number of solved MIP problems within the time limit and to be applicable to various environmental settings.</description><identifier>ISSN: 2377-3766</identifier><identifier>EISSN: 2377-3766</identifier><identifier>DOI: 10.1109/LRA.2022.3202633</identifier><identifier>CODEN: IRALC6</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Costs ; Deep learning in grasping and manipulation ; Feasibility ; Grasping ; Grippers ; Integer programming ; Linear programming ; manipulation planning ; Mixed integer ; Motion planning ; Multiple robots ; Object oriented modeling ; Parameters ; Planning ; Robots ; Task analysis</subject><ispartof>IEEE robotics and automation letters, 2022-10, Vol.7 (4), p.11545-11552</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c221t-2155d03f2009270cf1c15f4da9b1611755f665011ee9cce3469b6365337f2c6e3</citedby><cites>FETCH-LOGICAL-c221t-2155d03f2009270cf1c15f4da9b1611755f665011ee9cce3469b6365337f2c6e3</cites><orcidid>0000-0002-9338-5813 ; 0000-0002-5062-8264 ; 0000-0001-6094-0908 ; 0000-0002-9609-4616</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9869726$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27903,27904,54736</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9869726$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Park, Suhan</creatorcontrib><creatorcontrib>Kim, Hyoung Cheol</creatorcontrib><creatorcontrib>Baek, Jiyeong</creatorcontrib><creatorcontrib>Park, Jaeheung</creatorcontrib><title>Scalable Learned Geometric Feasibility for Cooperative Grasp and Motion Planning</title><title>IEEE robotics and automation letters</title><addtitle>LRA</addtitle><description>This letter proposes a novel learned feasibility estimator that considers multi-modal grasp poses for grasp and motion planning. Grasp poses inherently have multi-modal structures, that is, continuous and discrete parameters. Mixed-integer programming (MIP) is one method that solves these multi-modal problems. However, searching for all the discrete parameters costs considerable time. Therefore, by learning the feasibility of each mode from the geometric variables, the problem can be solved efficiently within a given time limit. The feasibility of grasp poses is related to the pose of the object and nearby obstacles. Utilizing this information, we introduce learned geometric feasibility (LGF), which prioritizes the integer search of MIP. LGF is scalable to multiple robots and environments because it learns the feasibility using object-oriented information. It has been demonstrated to improve the number of solved MIP problems within the time limit and to be applicable to various environmental settings.</description><subject>Costs</subject><subject>Deep learning in grasping and manipulation</subject><subject>Feasibility</subject><subject>Grasping</subject><subject>Grippers</subject><subject>Integer programming</subject><subject>Linear programming</subject><subject>manipulation planning</subject><subject>Mixed integer</subject><subject>Motion planning</subject><subject>Multiple robots</subject><subject>Object oriented modeling</subject><subject>Parameters</subject><subject>Planning</subject><subject>Robots</subject><subject>Task analysis</subject><issn>2377-3766</issn><issn>2377-3766</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkE1LAzEQhoMoWGrvgpeA5635aBJzLMW2worFj3PIZieSst2syVbov3dLi3iZGZjnnYEHoVtKppQS_VC-zaeMMDblQ5WcX6AR40oVXEl5-W--RpOct4QQKpjiWozQ5t3ZxlYN4BJsaqHGK4g76FNweAk2hyo0oT9gHxNexNhBsn34AbxKNnfYtjV-iX2ILd40tm1D-3WDrrxtMkzOfYw-l08fi3VRvq6eF_OycIzRvmBUiJpwzwjRTBHnqaPCz2qrKyopVUJ4KQWhFEA7B3wmdSW5FJwrz5wEPkb3p7tdit97yL3Zxn1qh5eGqUGKYESSgSInyqWYcwJvuhR2Nh0MJeaozgzqzFGdOasbInenSACAP1w_Sq2G_S9FuGgo</recordid><startdate>20221001</startdate><enddate>20221001</enddate><creator>Park, Suhan</creator><creator>Kim, Hyoung Cheol</creator><creator>Baek, Jiyeong</creator><creator>Park, Jaeheung</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-9338-5813</orcidid><orcidid>https://orcid.org/0000-0002-5062-8264</orcidid><orcidid>https://orcid.org/0000-0001-6094-0908</orcidid><orcidid>https://orcid.org/0000-0002-9609-4616</orcidid></search><sort><creationdate>20221001</creationdate><title>Scalable Learned Geometric Feasibility for Cooperative Grasp and Motion Planning</title><author>Park, Suhan ; Kim, Hyoung Cheol ; Baek, Jiyeong ; Park, Jaeheung</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c221t-2155d03f2009270cf1c15f4da9b1611755f665011ee9cce3469b6365337f2c6e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Costs</topic><topic>Deep learning in grasping and manipulation</topic><topic>Feasibility</topic><topic>Grasping</topic><topic>Grippers</topic><topic>Integer programming</topic><topic>Linear programming</topic><topic>manipulation planning</topic><topic>Mixed integer</topic><topic>Motion planning</topic><topic>Multiple robots</topic><topic>Object oriented modeling</topic><topic>Parameters</topic><topic>Planning</topic><topic>Robots</topic><topic>Task analysis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Park, Suhan</creatorcontrib><creatorcontrib>Kim, Hyoung Cheol</creatorcontrib><creatorcontrib>Baek, Jiyeong</creatorcontrib><creatorcontrib>Park, Jaeheung</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE robotics and automation letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Park, Suhan</au><au>Kim, Hyoung Cheol</au><au>Baek, Jiyeong</au><au>Park, Jaeheung</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Scalable Learned Geometric Feasibility for Cooperative Grasp and Motion Planning</atitle><jtitle>IEEE robotics and automation letters</jtitle><stitle>LRA</stitle><date>2022-10-01</date><risdate>2022</risdate><volume>7</volume><issue>4</issue><spage>11545</spage><epage>11552</epage><pages>11545-11552</pages><issn>2377-3766</issn><eissn>2377-3766</eissn><coden>IRALC6</coden><abstract>This letter proposes a novel learned feasibility estimator that considers multi-modal grasp poses for grasp and motion planning. Grasp poses inherently have multi-modal structures, that is, continuous and discrete parameters. Mixed-integer programming (MIP) is one method that solves these multi-modal problems. However, searching for all the discrete parameters costs considerable time. Therefore, by learning the feasibility of each mode from the geometric variables, the problem can be solved efficiently within a given time limit. The feasibility of grasp poses is related to the pose of the object and nearby obstacles. Utilizing this information, we introduce learned geometric feasibility (LGF), which prioritizes the integer search of MIP. LGF is scalable to multiple robots and environments because it learns the feasibility using object-oriented information. It has been demonstrated to improve the number of solved MIP problems within the time limit and to be applicable to various environmental settings.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/LRA.2022.3202633</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0002-9338-5813</orcidid><orcidid>https://orcid.org/0000-0002-5062-8264</orcidid><orcidid>https://orcid.org/0000-0001-6094-0908</orcidid><orcidid>https://orcid.org/0000-0002-9609-4616</orcidid></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 2377-3766 |
ispartof | IEEE robotics and automation letters, 2022-10, Vol.7 (4), p.11545-11552 |
issn | 2377-3766 2377-3766 |
language | eng |
recordid | cdi_ieee_primary_9869726 |
source | IEEE Electronic Library (IEL) |
subjects | Costs Deep learning in grasping and manipulation Feasibility Grasping Grippers Integer programming Linear programming manipulation planning Mixed integer Motion planning Multiple robots Object oriented modeling Parameters Planning Robots Task analysis |
title | Scalable Learned Geometric Feasibility for Cooperative Grasp and Motion Planning |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-26T23%3A22%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Scalable%20Learned%20Geometric%20Feasibility%20for%20Cooperative%20Grasp%20and%20Motion%20Planning&rft.jtitle=IEEE%20robotics%20and%20automation%20letters&rft.au=Park,%20Suhan&rft.date=2022-10-01&rft.volume=7&rft.issue=4&rft.spage=11545&rft.epage=11552&rft.pages=11545-11552&rft.issn=2377-3766&rft.eissn=2377-3766&rft.coden=IRALC6&rft_id=info:doi/10.1109/LRA.2022.3202633&rft_dat=%3Cproquest_RIE%3E2711052060%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2711052060&rft_id=info:pmid/&rft_ieee_id=9869726&rfr_iscdi=true |