Lifelong learning‐based multilayer neural network control of nonlinear continuous‐time strict‐feedback systems
In this paper, we investigate lifelong learning (LL)‐based tracking control for partially uncertain strict feedback nonlinear systems with state constraints, employing a singular value decomposition (SVD) of the multilayer neural networks (MNNs) activation function based weight tuning scheme. The no...
Gespeichert in:
| Veröffentlicht in: | International journal of robust and nonlinear control 2024-01, Vol.34 (2), p.1397-1416 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1416 |
|---|---|
| container_issue | 2 |
| container_start_page | 1397 |
| container_title | International journal of robust and nonlinear control |
| container_volume | 34 |
| creator | Ganie, Irfan Ahmad Jagannathan, S. |
| description | In this paper, we investigate lifelong learning (LL)‐based tracking control for partially uncertain strict feedback nonlinear systems with state constraints, employing a singular value decomposition (SVD) of the multilayer neural networks (MNNs) activation function based weight tuning scheme. The novel SVD‐based approach extends the MNN weight tuning to n$$ n $$ layers. A unique online LL method, based on tracking error, is integrated into the MNN weight update laws to counteract catastrophic forgetting. To adeptly address constraints for safety assurances, taking into account the effects caused by disturbances, we utilize a time‐varying barrier Lyapunov function (TBLF) that ensures a uniformly ultimately bounded closed‐loop system. The effectiveness of the proposed safe LL MNN approach is demonstrated through a leader‐follower formation scenario involving unknown kinematics and dynamics. Supporting simulation results of mobile robot formation control are provided, confirming the theoretical findings. |
| doi_str_mv | 10.1002/rnc.7039 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2901395510</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2901395510</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3279-bde18f93de11a454a4e34f40f1ac221795b3a2bbd3f74d16e814ff99dd04fbf3</originalsourceid><addsrcrecordid>eNp1kMtKAzEUhoMoWKvgIwTcuJma2zjNUoo3KArS_ZCZOSlp06QmGcrsfASf0Scxbd26-s_lO_-BH6FrSiaUEHYXXDupCJcnaESJlAVlXJ7uayGLqWT8HF3EuCIk75gYoTQ3Gqx3S2xBBWfc8ufru1EROrzpbTJWDRCwgz4omyXtfFjj1rsUvMVeY-edNS6fHobG9b6P2SGZDeCYgmlT7jRA16h2jeMQE2ziJTrTyka4-tMxWjw9LmYvxfz9-XX2MC9azipZNB3QqZY8C1WiFEoAF1oQTVXLGK1k2XDFmqbjuhIdvYcpFVpL2XVE6EbzMbo52m6D_-whpnrl--Dyx5pJQrksS0oydXuk2uBjDKDrbTAbFYaaknofaZ0jrfeRZrQ4ojtjYfiXqz_eZgf-F96AfjM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2901395510</pqid></control><display><type>article</type><title>Lifelong learning‐based multilayer neural network control of nonlinear continuous‐time strict‐feedback systems</title><source>Wiley Journals</source><creator>Ganie, Irfan Ahmad ; Jagannathan, S.</creator><creatorcontrib>Ganie, Irfan Ahmad ; Jagannathan, S.</creatorcontrib><description>In this paper, we investigate lifelong learning (LL)‐based tracking control for partially uncertain strict feedback nonlinear systems with state constraints, employing a singular value decomposition (SVD) of the multilayer neural networks (MNNs) activation function based weight tuning scheme. The novel SVD‐based approach extends the MNN weight tuning to n$$ n $$ layers. A unique online LL method, based on tracking error, is integrated into the MNN weight update laws to counteract catastrophic forgetting. To adeptly address constraints for safety assurances, taking into account the effects caused by disturbances, we utilize a time‐varying barrier Lyapunov function (TBLF) that ensures a uniformly ultimately bounded closed‐loop system. The effectiveness of the proposed safe LL MNN approach is demonstrated through a leader‐follower formation scenario involving unknown kinematics and dynamics. Supporting simulation results of mobile robot formation control are provided, confirming the theoretical findings.</description><identifier>ISSN: 1049-8923</identifier><identifier>EISSN: 1099-1239</identifier><identifier>DOI: 10.1002/rnc.7039</identifier><language>eng</language><publisher>Bognor Regis: Wiley Subscription Services, Inc</publisher><subject>adaptive control ; Feedback ; formation control ; Kinematics ; Liapunov functions ; Lifelong learning ; multilayer neural networks ; Multilayers ; Network control ; Neural networks ; Nonlinear control ; Nonlinear systems ; Robot control ; Singular value decomposition ; Tracking control ; Tracking errors ; Tuning</subject><ispartof>International journal of robust and nonlinear control, 2024-01, Vol.34 (2), p.1397-1416</ispartof><rights>2023 John Wiley & Sons Ltd.</rights><rights>2024 John Wiley & Sons, Ltd.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3279-bde18f93de11a454a4e34f40f1ac221795b3a2bbd3f74d16e814ff99dd04fbf3</citedby><cites>FETCH-LOGICAL-c3279-bde18f93de11a454a4e34f40f1ac221795b3a2bbd3f74d16e814ff99dd04fbf3</cites><orcidid>0000-0002-0376-735X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1002%2Frnc.7039$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Frnc.7039$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,780,784,1417,27924,27925,45574,45575</link.rule.ids></links><search><creatorcontrib>Ganie, Irfan Ahmad</creatorcontrib><creatorcontrib>Jagannathan, S.</creatorcontrib><title>Lifelong learning‐based multilayer neural network control of nonlinear continuous‐time strict‐feedback systems</title><title>International journal of robust and nonlinear control</title><description>In this paper, we investigate lifelong learning (LL)‐based tracking control for partially uncertain strict feedback nonlinear systems with state constraints, employing a singular value decomposition (SVD) of the multilayer neural networks (MNNs) activation function based weight tuning scheme. The novel SVD‐based approach extends the MNN weight tuning to n$$ n $$ layers. A unique online LL method, based on tracking error, is integrated into the MNN weight update laws to counteract catastrophic forgetting. To adeptly address constraints for safety assurances, taking into account the effects caused by disturbances, we utilize a time‐varying barrier Lyapunov function (TBLF) that ensures a uniformly ultimately bounded closed‐loop system. The effectiveness of the proposed safe LL MNN approach is demonstrated through a leader‐follower formation scenario involving unknown kinematics and dynamics. Supporting simulation results of mobile robot formation control are provided, confirming the theoretical findings.</description><subject>adaptive control</subject><subject>Feedback</subject><subject>formation control</subject><subject>Kinematics</subject><subject>Liapunov functions</subject><subject>Lifelong learning</subject><subject>multilayer neural networks</subject><subject>Multilayers</subject><subject>Network control</subject><subject>Neural networks</subject><subject>Nonlinear control</subject><subject>Nonlinear systems</subject><subject>Robot control</subject><subject>Singular value decomposition</subject><subject>Tracking control</subject><subject>Tracking errors</subject><subject>Tuning</subject><issn>1049-8923</issn><issn>1099-1239</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp1kMtKAzEUhoMoWKvgIwTcuJma2zjNUoo3KArS_ZCZOSlp06QmGcrsfASf0Scxbd26-s_lO_-BH6FrSiaUEHYXXDupCJcnaESJlAVlXJ7uayGLqWT8HF3EuCIk75gYoTQ3Gqx3S2xBBWfc8ufru1EROrzpbTJWDRCwgz4omyXtfFjj1rsUvMVeY-edNS6fHobG9b6P2SGZDeCYgmlT7jRA16h2jeMQE2ziJTrTyka4-tMxWjw9LmYvxfz9-XX2MC9azipZNB3QqZY8C1WiFEoAF1oQTVXLGK1k2XDFmqbjuhIdvYcpFVpL2XVE6EbzMbo52m6D_-whpnrl--Dyx5pJQrksS0oydXuk2uBjDKDrbTAbFYaaknofaZ0jrfeRZrQ4ojtjYfiXqz_eZgf-F96AfjM</recordid><startdate>20240125</startdate><enddate>20240125</enddate><creator>Ganie, Irfan Ahmad</creator><creator>Jagannathan, S.</creator><general>Wiley Subscription Services, Inc</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-0376-735X</orcidid></search><sort><creationdate>20240125</creationdate><title>Lifelong learning‐based multilayer neural network control of nonlinear continuous‐time strict‐feedback systems</title><author>Ganie, Irfan Ahmad ; Jagannathan, S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3279-bde18f93de11a454a4e34f40f1ac221795b3a2bbd3f74d16e814ff99dd04fbf3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>adaptive control</topic><topic>Feedback</topic><topic>formation control</topic><topic>Kinematics</topic><topic>Liapunov functions</topic><topic>Lifelong learning</topic><topic>multilayer neural networks</topic><topic>Multilayers</topic><topic>Network control</topic><topic>Neural networks</topic><topic>Nonlinear control</topic><topic>Nonlinear systems</topic><topic>Robot control</topic><topic>Singular value decomposition</topic><topic>Tracking control</topic><topic>Tracking errors</topic><topic>Tuning</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ganie, Irfan Ahmad</creatorcontrib><creatorcontrib>Jagannathan, S.</creatorcontrib><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>Engineering 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>International journal of robust and nonlinear control</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ganie, Irfan Ahmad</au><au>Jagannathan, S.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Lifelong learning‐based multilayer neural network control of nonlinear continuous‐time strict‐feedback systems</atitle><jtitle>International journal of robust and nonlinear control</jtitle><date>2024-01-25</date><risdate>2024</risdate><volume>34</volume><issue>2</issue><spage>1397</spage><epage>1416</epage><pages>1397-1416</pages><issn>1049-8923</issn><eissn>1099-1239</eissn><abstract>In this paper, we investigate lifelong learning (LL)‐based tracking control for partially uncertain strict feedback nonlinear systems with state constraints, employing a singular value decomposition (SVD) of the multilayer neural networks (MNNs) activation function based weight tuning scheme. The novel SVD‐based approach extends the MNN weight tuning to n$$ n $$ layers. A unique online LL method, based on tracking error, is integrated into the MNN weight update laws to counteract catastrophic forgetting. To adeptly address constraints for safety assurances, taking into account the effects caused by disturbances, we utilize a time‐varying barrier Lyapunov function (TBLF) that ensures a uniformly ultimately bounded closed‐loop system. The effectiveness of the proposed safe LL MNN approach is demonstrated through a leader‐follower formation scenario involving unknown kinematics and dynamics. Supporting simulation results of mobile robot formation control are provided, confirming the theoretical findings.</abstract><cop>Bognor Regis</cop><pub>Wiley Subscription Services, Inc</pub><doi>10.1002/rnc.7039</doi><tpages>20</tpages><orcidid>https://orcid.org/0000-0002-0376-735X</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1049-8923 |
| ispartof | International journal of robust and nonlinear control, 2024-01, Vol.34 (2), p.1397-1416 |
| issn | 1049-8923 1099-1239 |
| language | eng |
| recordid | cdi_proquest_journals_2901395510 |
| source | Wiley Journals |
| subjects | adaptive control Feedback formation control Kinematics Liapunov functions Lifelong learning multilayer neural networks Multilayers Network control Neural networks Nonlinear control Nonlinear systems Robot control Singular value decomposition Tracking control Tracking errors Tuning |
| title | Lifelong learning‐based multilayer neural network control of nonlinear continuous‐time strict‐feedback systems |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T08%3A20%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Lifelong%20learning%E2%80%90based%20multilayer%20neural%20network%20control%20of%20nonlinear%20continuous%E2%80%90time%20strict%E2%80%90feedback%20systems&rft.jtitle=International%20journal%20of%20robust%20and%20nonlinear%20control&rft.au=Ganie,%20Irfan%20Ahmad&rft.date=2024-01-25&rft.volume=34&rft.issue=2&rft.spage=1397&rft.epage=1416&rft.pages=1397-1416&rft.issn=1049-8923&rft.eissn=1099-1239&rft_id=info:doi/10.1002/rnc.7039&rft_dat=%3Cproquest_cross%3E2901395510%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2901395510&rft_id=info:pmid/&rfr_iscdi=true |