Stochastic Optimal Control for Robot Manipulation Skill Learning Under Time-Varying Uncertain Environment
In this article, a novel stochastic optimal control method is developed for robot manipulator interacting with a time-varying uncertain environment. The unknown environment model is described as a nonlinear system with time-varying parameters as well as stochastic information, which is learned via t...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on cybernetics 2024-04, Vol.54 (4), p.2015-2025 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2025 |
|---|---|
| container_issue | 4 |
| container_start_page | 2015 |
| container_title | IEEE transactions on cybernetics |
| container_volume | 54 |
| creator | Liu, Xing Liu, Zhengxiong Huang, Panfeng |
| description | In this article, a novel stochastic optimal control method is developed for robot manipulator interacting with a time-varying uncertain environment. The unknown environment model is described as a nonlinear system with time-varying parameters as well as stochastic information, which is learned via the Gaussian process regression (GPR) method as the external dynamics. Integrating the learned external dynamics as well as the stochastic uncertainties, the complete interaction system dynamics are obtained. Then the iterative linear quadratic Gaussian with learned external dynamics (ILQG-LEDs) method is presented to obtain the optimal manipulation control parameters, namely, the feedforward force, the reference trajectory, as well as the impedance parameters, subject to time-varying environment dynamics. The comparative simulation studies verify the advantages of the presented method, and the experimental studies of the peg-hole-insertion task prove that this method can deal with complex manipulation tasks. |
| doi_str_mv | 10.1109/TCYB.2022.3211440 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_9923577</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9923577</ieee_id><sourcerecordid>2969041334</sourcerecordid><originalsourceid>FETCH-LOGICAL-c349t-29c61d1101b6b3b9b2b56a63b3f7e9951c3b576b196932e860e334142af3d5da3</originalsourceid><addsrcrecordid>eNpdkV9LHDEUxYO0qFg_gAgl4EtfZps_M5nJoy5bFVaEuhZ8CsnMHRudSdYkU_Dbm2XXfWheEk5-93DvPQidUTKjlMifq_nT1YwRxmacUVqW5AAdMyqagrG6-rJ_i_oIncb4QvJpsiSbQ3TEBatETatjZB-Sb__qmGyL79fJjnrAc-9S8APufcC_vfEJ32ln19Ogk_UOP7zaYcBL0MFZ94wfXQcBr-wIxR8d3rdSCyFp6_DC_bPBuxFc-oa-9nqIcLq7T9Djr8VqflMs769v55fLouWlTAWTraBdnpAaYbiRhplKaMEN72uQsqItN1UtDJVCcgaNIMB5SUume95VneYn6MfWdx382wQxqdHGFoZBO_BTVKxmoiRNUzYZvfgPffFTcLk7xbI9KWm2zhTdUm3wMQbo1TrkPYV3RYnaRKE2UahNFGoXRa75vnOezAjdvuJz8Rk43wIWAPbfUjJe1TX_AFUHjF8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2969041334</pqid></control><display><type>article</type><title>Stochastic Optimal Control for Robot Manipulation Skill Learning Under Time-Varying Uncertain Environment</title><source>IEEE Electronic Library (IEL)</source><creator>Liu, Xing ; Liu, Zhengxiong ; Huang, Panfeng</creator><creatorcontrib>Liu, Xing ; Liu, Zhengxiong ; Huang, Panfeng</creatorcontrib><description>In this article, a novel stochastic optimal control method is developed for robot manipulator interacting with a time-varying uncertain environment. The unknown environment model is described as a nonlinear system with time-varying parameters as well as stochastic information, which is learned via the Gaussian process regression (GPR) method as the external dynamics. Integrating the learned external dynamics as well as the stochastic uncertainties, the complete interaction system dynamics are obtained. Then the iterative linear quadratic Gaussian with learned external dynamics (ILQG-LEDs) method is presented to obtain the optimal manipulation control parameters, namely, the feedforward force, the reference trajectory, as well as the impedance parameters, subject to time-varying environment dynamics. The comparative simulation studies verify the advantages of the presented method, and the experimental studies of the peg-hole-insertion task prove that this method can deal with complex manipulation tasks.</description><identifier>ISSN: 2168-2267</identifier><identifier>EISSN: 2168-2275</identifier><identifier>DOI: 10.1109/TCYB.2022.3211440</identifier><identifier>PMID: 36256715</identifier><identifier>CODEN: ITCEB8</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Control methods ; Environment models ; Feedforward control ; Gaussian process ; Gaussian processes ; Impedance ; iterative linear quadratic Gaussian with learned external dynamic (ILQG-LED) method ; Iterative methods ; Manipulator dynamics ; model-based reinforcement learning ; Nonlinear systems ; Optimal control ; Parameters ; Robot arms ; Robot control ; robot manipulation skill ; robot-environment interaction ; Robots ; stochastic optimal manipulation control ; Stochastic processes ; System dynamics ; Task complexity ; Time-varying systems ; time-varying uncertain environment ; Trajectory ; Unknown environments</subject><ispartof>IEEE transactions on cybernetics, 2024-04, Vol.54 (4), p.2015-2025</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c349t-29c61d1101b6b3b9b2b56a63b3f7e9951c3b576b196932e860e334142af3d5da3</citedby><cites>FETCH-LOGICAL-c349t-29c61d1101b6b3b9b2b56a63b3f7e9951c3b576b196932e860e334142af3d5da3</cites><orcidid>0000-0002-5327-4908 ; 0000-0002-9427-4066 ; 0000-0002-5132-9602</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9923577$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27922,27923,54756</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9923577$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/36256715$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Liu, Xing</creatorcontrib><creatorcontrib>Liu, Zhengxiong</creatorcontrib><creatorcontrib>Huang, Panfeng</creatorcontrib><title>Stochastic Optimal Control for Robot Manipulation Skill Learning Under Time-Varying Uncertain Environment</title><title>IEEE transactions on cybernetics</title><addtitle>TCYB</addtitle><addtitle>IEEE Trans Cybern</addtitle><description>In this article, a novel stochastic optimal control method is developed for robot manipulator interacting with a time-varying uncertain environment. The unknown environment model is described as a nonlinear system with time-varying parameters as well as stochastic information, which is learned via the Gaussian process regression (GPR) method as the external dynamics. Integrating the learned external dynamics as well as the stochastic uncertainties, the complete interaction system dynamics are obtained. Then the iterative linear quadratic Gaussian with learned external dynamics (ILQG-LEDs) method is presented to obtain the optimal manipulation control parameters, namely, the feedforward force, the reference trajectory, as well as the impedance parameters, subject to time-varying environment dynamics. The comparative simulation studies verify the advantages of the presented method, and the experimental studies of the peg-hole-insertion task prove that this method can deal with complex manipulation tasks.</description><subject>Control methods</subject><subject>Environment models</subject><subject>Feedforward control</subject><subject>Gaussian process</subject><subject>Gaussian processes</subject><subject>Impedance</subject><subject>iterative linear quadratic Gaussian with learned external dynamic (ILQG-LED) method</subject><subject>Iterative methods</subject><subject>Manipulator dynamics</subject><subject>model-based reinforcement learning</subject><subject>Nonlinear systems</subject><subject>Optimal control</subject><subject>Parameters</subject><subject>Robot arms</subject><subject>Robot control</subject><subject>robot manipulation skill</subject><subject>robot-environment interaction</subject><subject>Robots</subject><subject>stochastic optimal manipulation control</subject><subject>Stochastic processes</subject><subject>System dynamics</subject><subject>Task complexity</subject><subject>Time-varying systems</subject><subject>time-varying uncertain environment</subject><subject>Trajectory</subject><subject>Unknown environments</subject><issn>2168-2267</issn><issn>2168-2275</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkV9LHDEUxYO0qFg_gAgl4EtfZps_M5nJoy5bFVaEuhZ8CsnMHRudSdYkU_Dbm2XXfWheEk5-93DvPQidUTKjlMifq_nT1YwRxmacUVqW5AAdMyqagrG6-rJ_i_oIncb4QvJpsiSbQ3TEBatETatjZB-Sb__qmGyL79fJjnrAc-9S8APufcC_vfEJ32ln19Ogk_UOP7zaYcBL0MFZ94wfXQcBr-wIxR8d3rdSCyFp6_DC_bPBuxFc-oa-9nqIcLq7T9Djr8VqflMs769v55fLouWlTAWTraBdnpAaYbiRhplKaMEN72uQsqItN1UtDJVCcgaNIMB5SUume95VneYn6MfWdx382wQxqdHGFoZBO_BTVKxmoiRNUzYZvfgPffFTcLk7xbI9KWm2zhTdUm3wMQbo1TrkPYV3RYnaRKE2UahNFGoXRa75vnOezAjdvuJz8Rk43wIWAPbfUjJe1TX_AFUHjF8</recordid><startdate>20240401</startdate><enddate>20240401</enddate><creator>Liu, Xing</creator><creator>Liu, Zhengxiong</creator><creator>Huang, Panfeng</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>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>H8D</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-5327-4908</orcidid><orcidid>https://orcid.org/0000-0002-9427-4066</orcidid><orcidid>https://orcid.org/0000-0002-5132-9602</orcidid></search><sort><creationdate>20240401</creationdate><title>Stochastic Optimal Control for Robot Manipulation Skill Learning Under Time-Varying Uncertain Environment</title><author>Liu, Xing ; Liu, Zhengxiong ; Huang, Panfeng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c349t-29c61d1101b6b3b9b2b56a63b3f7e9951c3b576b196932e860e334142af3d5da3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Control methods</topic><topic>Environment models</topic><topic>Feedforward control</topic><topic>Gaussian process</topic><topic>Gaussian processes</topic><topic>Impedance</topic><topic>iterative linear quadratic Gaussian with learned external dynamic (ILQG-LED) method</topic><topic>Iterative methods</topic><topic>Manipulator dynamics</topic><topic>model-based reinforcement learning</topic><topic>Nonlinear systems</topic><topic>Optimal control</topic><topic>Parameters</topic><topic>Robot arms</topic><topic>Robot control</topic><topic>robot manipulation skill</topic><topic>robot-environment interaction</topic><topic>Robots</topic><topic>stochastic optimal manipulation control</topic><topic>Stochastic processes</topic><topic>System dynamics</topic><topic>Task complexity</topic><topic>Time-varying systems</topic><topic>time-varying uncertain environment</topic><topic>Trajectory</topic><topic>Unknown environments</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Liu, Xing</creatorcontrib><creatorcontrib>Liu, Zhengxiong</creatorcontrib><creatorcontrib>Huang, Panfeng</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>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Aerospace 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>MEDLINE - Academic</collection><jtitle>IEEE transactions on cybernetics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Liu, Xing</au><au>Liu, Zhengxiong</au><au>Huang, Panfeng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Stochastic Optimal Control for Robot Manipulation Skill Learning Under Time-Varying Uncertain Environment</atitle><jtitle>IEEE transactions on cybernetics</jtitle><stitle>TCYB</stitle><addtitle>IEEE Trans Cybern</addtitle><date>2024-04-01</date><risdate>2024</risdate><volume>54</volume><issue>4</issue><spage>2015</spage><epage>2025</epage><pages>2015-2025</pages><issn>2168-2267</issn><eissn>2168-2275</eissn><coden>ITCEB8</coden><abstract>In this article, a novel stochastic optimal control method is developed for robot manipulator interacting with a time-varying uncertain environment. The unknown environment model is described as a nonlinear system with time-varying parameters as well as stochastic information, which is learned via the Gaussian process regression (GPR) method as the external dynamics. Integrating the learned external dynamics as well as the stochastic uncertainties, the complete interaction system dynamics are obtained. Then the iterative linear quadratic Gaussian with learned external dynamics (ILQG-LEDs) method is presented to obtain the optimal manipulation control parameters, namely, the feedforward force, the reference trajectory, as well as the impedance parameters, subject to time-varying environment dynamics. The comparative simulation studies verify the advantages of the presented method, and the experimental studies of the peg-hole-insertion task prove that this method can deal with complex manipulation tasks.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>36256715</pmid><doi>10.1109/TCYB.2022.3211440</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0002-5327-4908</orcidid><orcidid>https://orcid.org/0000-0002-9427-4066</orcidid><orcidid>https://orcid.org/0000-0002-5132-9602</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2168-2267 |
| ispartof | IEEE transactions on cybernetics, 2024-04, Vol.54 (4), p.2015-2025 |
| issn | 2168-2267 2168-2275 |
| language | eng |
| recordid | cdi_ieee_primary_9923577 |
| source | IEEE Electronic Library (IEL) |
| subjects | Control methods Environment models Feedforward control Gaussian process Gaussian processes Impedance iterative linear quadratic Gaussian with learned external dynamic (ILQG-LED) method Iterative methods Manipulator dynamics model-based reinforcement learning Nonlinear systems Optimal control Parameters Robot arms Robot control robot manipulation skill robot-environment interaction Robots stochastic optimal manipulation control Stochastic processes System dynamics Task complexity Time-varying systems time-varying uncertain environment Trajectory Unknown environments |
| title | Stochastic Optimal Control for Robot Manipulation Skill Learning Under Time-Varying Uncertain Environment |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T04%3A00%3A27IST&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=Stochastic%20Optimal%20Control%20for%20Robot%20Manipulation%20Skill%20Learning%20Under%20Time-Varying%20Uncertain%20Environment&rft.jtitle=IEEE%20transactions%20on%20cybernetics&rft.au=Liu,%20Xing&rft.date=2024-04-01&rft.volume=54&rft.issue=4&rft.spage=2015&rft.epage=2025&rft.pages=2015-2025&rft.issn=2168-2267&rft.eissn=2168-2275&rft.coden=ITCEB8&rft_id=info:doi/10.1109/TCYB.2022.3211440&rft_dat=%3Cproquest_RIE%3E2969041334%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=2969041334&rft_id=info:pmid/36256715&rft_ieee_id=9923577&rfr_iscdi=true |