Triangle Inequality for Inverse Optimal Control
Inverse optimal control (IOC) is a problem of estimating a cost function based on the behaviors of an expert that behaves optimally with respect to the cost function. Although the Hamilton-Jacobi-Bellman (HJB) equation for the value function that evaluates the temporal integral of the cost function...
Gespeichert in:
Veröffentlicht in: | IEEE access 2023, Vol.11, p.119187-119199 |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 119199 |
---|---|
container_issue | |
container_start_page | 119187 |
container_title | IEEE access |
container_volume | 11 |
creator | Mitsuhashi, Sho Ishii, Shin |
description | Inverse optimal control (IOC) is a problem of estimating a cost function based on the behaviors of an expert that behaves optimally with respect to the cost function. Although the Hamilton-Jacobi-Bellman (HJB) equation for the value function that evaluates the temporal integral of the cost function provides a necessary condition for the optimality of expert behaviors, the use of the HJB equation alone is insufficient for solving the IOC problem. In this study, we propose a triangle inequality which is useful for estimating the better representation of the value function, along with a new IOC method incorporating the triangle inequality. Through several IOC problems and imitation learning problems of time-dependent control behaviors, we show that our IOC method performs substantially better than an existing IOC method. Showing our IOC method is also applicable to an imitation of expert control of a 2-link manipulator, we demonstrate applicability of our method to real-world problems. |
doi_str_mv | 10.1109/ACCESS.2023.3327426 |
format | Article |
fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_proquest_journals_2885652512</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10295444</ieee_id><doaj_id>oai_doaj_org_article_55529466b9d24673a102c4a5736d3441</doaj_id><sourcerecordid>2885652512</sourcerecordid><originalsourceid>FETCH-LOGICAL-c322t-a2a3b6cb807a8963e2af252a0b0774a61e7dd98fc3928f2c4cf625d54121d6ab3</originalsourceid><addsrcrecordid>eNpNUE1rwkAQXUoLFesvaA-BnqO7s1_ZowTbCoIH7XmZJBuJpK5uYsF_37WR0rnMzGPem8cj5JnRKWPUzOZ5vthspkCBTzkHLUDdkREwZVIuubr_Nz-SSdftaawsQlKPyGwbGjzsWpcsD-50xrbpL0ntQ1y_Xehcsj72zRe2Se4PffDtE3mose3c5NbH5PNtsc0_0tX6fZnPV2nJAfoUAXmhyiKjGjOjuAOsQQLSgmotUDGnq8pkdckNZDWUoqwVyEoKBqxSWPAxWQ66lce9PYboIVysx8b-Aj7sLIa-KVtnpZRghFKFqUAozZHRKIhSc1VxIVjUeh20jsGfzq7r7d6fwyHat5BlUkmQDOIVH67K4LsuuPrvK6P2GrQdgrbXoO0t6Mh6GViNc-4fA4wUQvAfK6l21w</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2885652512</pqid></control><display><type>article</type><title>Triangle Inequality for Inverse Optimal Control</title><source>IEEE Open Access Journals</source><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Mitsuhashi, Sho ; Ishii, Shin</creator><creatorcontrib>Mitsuhashi, Sho ; Ishii, Shin</creatorcontrib><description>Inverse optimal control (IOC) is a problem of estimating a cost function based on the behaviors of an expert that behaves optimally with respect to the cost function. Although the Hamilton-Jacobi-Bellman (HJB) equation for the value function that evaluates the temporal integral of the cost function provides a necessary condition for the optimality of expert behaviors, the use of the HJB equation alone is insufficient for solving the IOC problem. In this study, we propose a triangle inequality which is useful for estimating the better representation of the value function, along with a new IOC method incorporating the triangle inequality. Through several IOC problems and imitation learning problems of time-dependent control behaviors, we show that our IOC method performs substantially better than an existing IOC method. Showing our IOC method is also applicable to an imitation of expert control of a 2-link manipulator, we demonstrate applicability of our method to real-world problems.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2023.3327426</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Aerospace electronics ; Behavioral sciences ; Cost estimation ; Cost function ; Costs ; Estimation ; imitation learning ; Inequality ; inverse optimal control ; inverse reinforcement learning ; Optimal control ; Optimization ; Task analysis ; Trajectory</subject><ispartof>IEEE access, 2023, Vol.11, p.119187-119199</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c322t-a2a3b6cb807a8963e2af252a0b0774a61e7dd98fc3928f2c4cf625d54121d6ab3</cites><orcidid>0000-0001-9385-8230 ; 0000-0003-4217-6883</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10295444$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,864,2102,4024,27633,27923,27924,27925,54933</link.rule.ids></links><search><creatorcontrib>Mitsuhashi, Sho</creatorcontrib><creatorcontrib>Ishii, Shin</creatorcontrib><title>Triangle Inequality for Inverse Optimal Control</title><title>IEEE access</title><addtitle>Access</addtitle><description>Inverse optimal control (IOC) is a problem of estimating a cost function based on the behaviors of an expert that behaves optimally with respect to the cost function. Although the Hamilton-Jacobi-Bellman (HJB) equation for the value function that evaluates the temporal integral of the cost function provides a necessary condition for the optimality of expert behaviors, the use of the HJB equation alone is insufficient for solving the IOC problem. In this study, we propose a triangle inequality which is useful for estimating the better representation of the value function, along with a new IOC method incorporating the triangle inequality. Through several IOC problems and imitation learning problems of time-dependent control behaviors, we show that our IOC method performs substantially better than an existing IOC method. Showing our IOC method is also applicable to an imitation of expert control of a 2-link manipulator, we demonstrate applicability of our method to real-world problems.</description><subject>Aerospace electronics</subject><subject>Behavioral sciences</subject><subject>Cost estimation</subject><subject>Cost function</subject><subject>Costs</subject><subject>Estimation</subject><subject>imitation learning</subject><subject>Inequality</subject><subject>inverse optimal control</subject><subject>inverse reinforcement learning</subject><subject>Optimal control</subject><subject>Optimization</subject><subject>Task analysis</subject><subject>Trajectory</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNUE1rwkAQXUoLFesvaA-BnqO7s1_ZowTbCoIH7XmZJBuJpK5uYsF_37WR0rnMzGPem8cj5JnRKWPUzOZ5vthspkCBTzkHLUDdkREwZVIuubr_Nz-SSdftaawsQlKPyGwbGjzsWpcsD-50xrbpL0ntQ1y_Xehcsj72zRe2Se4PffDtE3mose3c5NbH5PNtsc0_0tX6fZnPV2nJAfoUAXmhyiKjGjOjuAOsQQLSgmotUDGnq8pkdckNZDWUoqwVyEoKBqxSWPAxWQ66lce9PYboIVysx8b-Aj7sLIa-KVtnpZRghFKFqUAozZHRKIhSc1VxIVjUeh20jsGfzq7r7d6fwyHat5BlUkmQDOIVH67K4LsuuPrvK6P2GrQdgrbXoO0t6Mh6GViNc-4fA4wUQvAfK6l21w</recordid><startdate>2023</startdate><enddate>2023</enddate><creator>Mitsuhashi, Sho</creator><creator>Ishii, Shin</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0001-9385-8230</orcidid><orcidid>https://orcid.org/0000-0003-4217-6883</orcidid></search><sort><creationdate>2023</creationdate><title>Triangle Inequality for Inverse Optimal Control</title><author>Mitsuhashi, Sho ; Ishii, Shin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c322t-a2a3b6cb807a8963e2af252a0b0774a61e7dd98fc3928f2c4cf625d54121d6ab3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Aerospace electronics</topic><topic>Behavioral sciences</topic><topic>Cost estimation</topic><topic>Cost function</topic><topic>Costs</topic><topic>Estimation</topic><topic>imitation learning</topic><topic>Inequality</topic><topic>inverse optimal control</topic><topic>inverse reinforcement learning</topic><topic>Optimal control</topic><topic>Optimization</topic><topic>Task analysis</topic><topic>Trajectory</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Mitsuhashi, Sho</creatorcontrib><creatorcontrib>Ishii, Shin</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005–Present</collection><collection>IEEE Open Access Journals</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>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials 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><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mitsuhashi, Sho</au><au>Ishii, Shin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Triangle Inequality for Inverse Optimal Control</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2023</date><risdate>2023</risdate><volume>11</volume><spage>119187</spage><epage>119199</epage><pages>119187-119199</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>Inverse optimal control (IOC) is a problem of estimating a cost function based on the behaviors of an expert that behaves optimally with respect to the cost function. Although the Hamilton-Jacobi-Bellman (HJB) equation for the value function that evaluates the temporal integral of the cost function provides a necessary condition for the optimality of expert behaviors, the use of the HJB equation alone is insufficient for solving the IOC problem. In this study, we propose a triangle inequality which is useful for estimating the better representation of the value function, along with a new IOC method incorporating the triangle inequality. Through several IOC problems and imitation learning problems of time-dependent control behaviors, we show that our IOC method performs substantially better than an existing IOC method. Showing our IOC method is also applicable to an imitation of expert control of a 2-link manipulator, we demonstrate applicability of our method to real-world problems.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2023.3327426</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0001-9385-8230</orcidid><orcidid>https://orcid.org/0000-0003-4217-6883</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2169-3536 |
ispartof | IEEE access, 2023, Vol.11, p.119187-119199 |
issn | 2169-3536 2169-3536 |
language | eng |
recordid | cdi_proquest_journals_2885652512 |
source | IEEE Open Access Journals; DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals |
subjects | Aerospace electronics Behavioral sciences Cost estimation Cost function Costs Estimation imitation learning Inequality inverse optimal control inverse reinforcement learning Optimal control Optimization Task analysis Trajectory |
title | Triangle Inequality for Inverse Optimal Control |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T21%3A08%3A16IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Triangle%20Inequality%20for%20Inverse%20Optimal%20Control&rft.jtitle=IEEE%20access&rft.au=Mitsuhashi,%20Sho&rft.date=2023&rft.volume=11&rft.spage=119187&rft.epage=119199&rft.pages=119187-119199&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2023.3327426&rft_dat=%3Cproquest_ieee_%3E2885652512%3C/proquest_ieee_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2885652512&rft_id=info:pmid/&rft_ieee_id=10295444&rft_doaj_id=oai_doaj_org_article_55529466b9d24673a102c4a5736d3441&rfr_iscdi=true |