Constrained online optimal control for continuous-time nonlinear systems using neuro-dynamic programming

This paper develops an online adaptive optimal control scheme to solve the infinite-horizon optimal control problem of continuous-time nonlinear systems with control constraints. A novel architecture is presented to approximate the Hamilton-Jacobi-Bellman equation. That is, only a critic neural netw...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang Xiong, Liu Derong, Wang Ding, Ma Hongwen
Format: Conference Proceeding
Language:English
Subjects:
Actuators
Artificial neural networks
Constrained input
Equations
Neuro-dynamic programming
Nonlinear systems
Online control
Optimal control
Programming
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 8722
container_issue
container_start_page 8717
container_title
container_volume
creator Yang Xiong
Liu Derong
Wang Ding
Ma Hongwen
description This paper develops an online adaptive optimal control scheme to solve the infinite-horizon optimal control problem of continuous-time nonlinear systems with control constraints. A novel architecture is presented to approximate the Hamilton-Jacobi-Bellman equation. That is, only a critic neural network is used to derive the optimal control instead of typical action-critic dual networks employed in neuro-dynamic programming methods. Meanwhile, unlike existing tuning laws for the critic, the newly developed critic update rule not only ensures convergence of the critic to the optimal control but also guarantees the closed-loop system to be uniformly ultimately bounded. In addition, no initial stabilizing control is required. Finally, an example is provided to verify the effectiveness of the present approach.
doi_str_mv 10.1109/ChiCC.2014.6896465
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_6896465</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6896465</ieee_id><sourcerecordid>6896465</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-e01ff0b697c217704efd82f08c1b33a6c610df6aa5e586ed4e0ed92544c84d9c3</originalsourceid><addsrcrecordid>eNotkM1KAzEcxKMgWGtfQC95ga352nwcZVErFLzouaTJP21kNynJ7qFv72J7-g3MMDCD0BMla0qJeemOsevWjFCxltpIIdsbtDJKG61pK7lW_BYtGJW0YYape_RQ6y8hkhjKF-jY5VTHYmMCj3PqZ-J8GuNge-xyGkvuccjlX8c05ak2swk4XbK24HquIwwVTzWmA04wldz4c7JDdPhU8qHYYZidR3QXbF9hdeUS_by_fXebZvv18dm9bptIVTs2QGgIZC-NcowqRQQEr1kg2tE951Y6SYkP0toWWi3BCyDgDWuFcFp44_gSPV96IwDsTmVeUs676zH8D65gWyo</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Constrained online optimal control for continuous-time nonlinear systems using neuro-dynamic programming</title><source>IEEE Xplore All Conference Series</source><creator>Yang Xiong ; Liu Derong ; Wang Ding ; Ma Hongwen</creator><creatorcontrib>Yang Xiong ; Liu Derong ; Wang Ding ; Ma Hongwen</creatorcontrib><description>This paper develops an online adaptive optimal control scheme to solve the infinite-horizon optimal control problem of continuous-time nonlinear systems with control constraints. A novel architecture is presented to approximate the Hamilton-Jacobi-Bellman equation. That is, only a critic neural network is used to derive the optimal control instead of typical action-critic dual networks employed in neuro-dynamic programming methods. Meanwhile, unlike existing tuning laws for the critic, the newly developed critic update rule not only ensures convergence of the critic to the optimal control but also guarantees the closed-loop system to be uniformly ultimately bounded. In addition, no initial stabilizing control is required. Finally, an example is provided to verify the effectiveness of the present approach.</description><identifier>EISSN: 2161-2927</identifier><identifier>EISBN: 9789881563873</identifier><identifier>EISBN: 9881563879</identifier><identifier>DOI: 10.1109/ChiCC.2014.6896465</identifier><language>eng</language><publisher>TCCT, CAA</publisher><subject>Actuators ; Artificial neural networks ; Constrained input ; Equations ; Neuro-dynamic programming ; Nonlinear systems ; Online control ; Optimal control ; Programming</subject><ispartof>Proceedings of the 33rd Chinese Control Conference, 2014, p.8717-8722</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6896465$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27924,54554,54931</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6896465$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Yang Xiong</creatorcontrib><creatorcontrib>Liu Derong</creatorcontrib><creatorcontrib>Wang Ding</creatorcontrib><creatorcontrib>Ma Hongwen</creatorcontrib><title>Constrained online optimal control for continuous-time nonlinear systems using neuro-dynamic programming</title><title>Proceedings of the 33rd Chinese Control Conference</title><addtitle>ChiCC</addtitle><description>This paper develops an online adaptive optimal control scheme to solve the infinite-horizon optimal control problem of continuous-time nonlinear systems with control constraints. A novel architecture is presented to approximate the Hamilton-Jacobi-Bellman equation. That is, only a critic neural network is used to derive the optimal control instead of typical action-critic dual networks employed in neuro-dynamic programming methods. Meanwhile, unlike existing tuning laws for the critic, the newly developed critic update rule not only ensures convergence of the critic to the optimal control but also guarantees the closed-loop system to be uniformly ultimately bounded. In addition, no initial stabilizing control is required. Finally, an example is provided to verify the effectiveness of the present approach.</description><subject>Actuators</subject><subject>Artificial neural networks</subject><subject>Constrained input</subject><subject>Equations</subject><subject>Neuro-dynamic programming</subject><subject>Nonlinear systems</subject><subject>Online control</subject><subject>Optimal control</subject><subject>Programming</subject><issn>2161-2927</issn><isbn>9789881563873</isbn><isbn>9881563879</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2014</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotkM1KAzEcxKMgWGtfQC95ga352nwcZVErFLzouaTJP21kNynJ7qFv72J7-g3MMDCD0BMla0qJeemOsevWjFCxltpIIdsbtDJKG61pK7lW_BYtGJW0YYape_RQ6y8hkhjKF-jY5VTHYmMCj3PqZ-J8GuNge-xyGkvuccjlX8c05ak2swk4XbK24HquIwwVTzWmA04wldz4c7JDdPhU8qHYYZidR3QXbF9hdeUS_by_fXebZvv18dm9bptIVTs2QGgIZC-NcowqRQQEr1kg2tE951Y6SYkP0toWWi3BCyDgDWuFcFp44_gSPV96IwDsTmVeUs676zH8D65gWyo</recordid><startdate>201407</startdate><enddate>201407</enddate><creator>Yang Xiong</creator><creator>Liu Derong</creator><creator>Wang Ding</creator><creator>Ma Hongwen</creator><general>TCCT, CAA</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201407</creationdate><title>Constrained online optimal control for continuous-time nonlinear systems using neuro-dynamic programming</title><author>Yang Xiong ; Liu Derong ; Wang Ding ; Ma Hongwen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-e01ff0b697c217704efd82f08c1b33a6c610df6aa5e586ed4e0ed92544c84d9c3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Actuators</topic><topic>Artificial neural networks</topic><topic>Constrained input</topic><topic>Equations</topic><topic>Neuro-dynamic programming</topic><topic>Nonlinear systems</topic><topic>Online control</topic><topic>Optimal control</topic><topic>Programming</topic><toplevel>online_resources</toplevel><creatorcontrib>Yang Xiong</creatorcontrib><creatorcontrib>Liu Derong</creatorcontrib><creatorcontrib>Wang Ding</creatorcontrib><creatorcontrib>Ma Hongwen</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yang Xiong</au><au>Liu Derong</au><au>Wang Ding</au><au>Ma Hongwen</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Constrained online optimal control for continuous-time nonlinear systems using neuro-dynamic programming</atitle><btitle>Proceedings of the 33rd Chinese Control Conference</btitle><stitle>ChiCC</stitle><date>2014-07</date><risdate>2014</risdate><spage>8717</spage><epage>8722</epage><pages>8717-8722</pages><eissn>2161-2927</eissn><eisbn>9789881563873</eisbn><eisbn>9881563879</eisbn><abstract>This paper develops an online adaptive optimal control scheme to solve the infinite-horizon optimal control problem of continuous-time nonlinear systems with control constraints. A novel architecture is presented to approximate the Hamilton-Jacobi-Bellman equation. That is, only a critic neural network is used to derive the optimal control instead of typical action-critic dual networks employed in neuro-dynamic programming methods. Meanwhile, unlike existing tuning laws for the critic, the newly developed critic update rule not only ensures convergence of the critic to the optimal control but also guarantees the closed-loop system to be uniformly ultimately bounded. In addition, no initial stabilizing control is required. Finally, an example is provided to verify the effectiveness of the present approach.</abstract><pub>TCCT, CAA</pub><doi>10.1109/ChiCC.2014.6896465</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2161-2927
ispartof Proceedings of the 33rd Chinese Control Conference, 2014, p.8717-8722
issn 2161-2927
language eng
recordid cdi_ieee_primary_6896465
source IEEE Xplore All Conference Series
subjects Actuators
Artificial neural networks
Constrained input
Equations
Neuro-dynamic programming
Nonlinear systems
Online control
Optimal control
Programming
title Constrained online optimal control for continuous-time nonlinear systems using neuro-dynamic programming
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T13%3A17%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Constrained%20online%20optimal%20control%20for%20continuous-time%20nonlinear%20systems%20using%20neuro-dynamic%20programming&rft.btitle=Proceedings%20of%20the%2033rd%20Chinese%20Control%20Conference&rft.au=Yang%20Xiong&rft.date=2014-07&rft.spage=8717&rft.epage=8722&rft.pages=8717-8722&rft.eissn=2161-2927&rft_id=info:doi/10.1109/ChiCC.2014.6896465&rft.eisbn=9789881563873&rft.eisbn_list=9881563879&rft_dat=%3Cieee_CHZPO%3E6896465%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-e01ff0b697c217704efd82f08c1b33a6c610df6aa5e586ed4e0ed92544c84d9c3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6896465&rfr_iscdi=true