{"id":"https://openalex.org/W7124477070","doi":"https://doi.org/10.1109/tsmc.2025.3650055","title":"Fuzzy Reinforcement Learning-Based Safe Cooperative Control for Nonlinear Multiagent Systems","display_name":"Fuzzy Reinforcement Learning-Based Safe Cooperative Control for Nonlinear Multiagent Systems","publication_year":2026,"publication_date":"2026-01-16","ids":{"openalex":"https://openalex.org/W7124477070","doi":"https://doi.org/10.1109/tsmc.2025.3650055"},"language":null,"primary_location":{"id":"doi:10.1109/tsmc.2025.3650055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3650055","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040271608","display_name":"Jinshan Bian","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinshan Bian","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123244794","display_name":"Chaoxu Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoxu Mu","raw_affiliation_strings":["Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education, Anhui Provincial Key Laboratory of Security Artificial Intelligence, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1055-9513","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education, Anhui Provincial Key Laboratory of Security Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035460432","display_name":"Hongbing Xia","orcid":"https://orcid.org/0000-0002-3360-3110"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbing Xia","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3360-3110","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020096491","display_name":"Chenyi Si","orcid":"https://orcid.org/0000-0002-0006-8967"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyi Si","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-0006-8967","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.0136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95464385,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"56","issue":"4","first_page":"2240","last_page":"2252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0017999999690800905,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/backstepping","display_name":"Backstepping","score":0.6902999877929688},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.586899995803833},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5806999802589417},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5618000030517578},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.47749999165534973},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.46299999952316284},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46160000562667847},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.42559999227523804},{"id":"https://openalex.org/keywords/lyapunov-stability","display_name":"Lyapunov stability","score":0.4185999929904938},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4138000011444092}],"concepts":[{"id":"https://openalex.org/C72218879","wikidata":"https://www.wikidata.org/wiki/Q4839759","display_name":"Backstepping","level":4,"score":0.6902999877929688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5873000025749207},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.586899995803833},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5806999802589417},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5618000030517578},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.42559999227523804},{"id":"https://openalex.org/C2776829284","wikidata":"https://www.wikidata.org/wiki/Q1341651","display_name":"Lyapunov stability","level":3,"score":0.4185999929904938},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C195975749","wikidata":"https://www.wikidata.org/wiki/Q1475705","display_name":"Fuzzy control system","level":3,"score":0.35420000553131104},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32989999651908875},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C129537906","wikidata":"https://www.wikidata.org/wiki/Q7603913","display_name":"State variable","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C3031470","wikidata":"https://www.wikidata.org/wiki/Q818544","display_name":"State observer","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C2779664074","wikidata":"https://www.wikidata.org/wiki/Q3518405","display_name":"Terminal (telecommunication)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C167964875","wikidata":"https://www.wikidata.org/wiki/Q17011487","display_name":"Exponential stability","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.2540999948978424},{"id":"https://openalex.org/C91581856","wikidata":"https://www.wikidata.org/wiki/Q2707001","display_name":"Nonlinear control","level":3,"score":0.25290000438690186},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2025.3650055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3650055","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2597819638","display_name":null,"funder_award_id":"62503007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G751832858","display_name":null,"funder_award_id":"62333016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2975408797","https://openalex.org/W2995409103","https://openalex.org/W3205825802","https://openalex.org/W4221019190","https://openalex.org/W4226264323","https://openalex.org/W4285292987","https://openalex.org/W4289822158","https://openalex.org/W4292851023","https://openalex.org/W4293064926","https://openalex.org/W4298234305","https://openalex.org/W4308634128","https://openalex.org/W4312971606","https://openalex.org/W4321484057","https://openalex.org/W4362681493","https://openalex.org/W4379533021","https://openalex.org/W4382119159","https://openalex.org/W4384304062","https://openalex.org/W4386432276","https://openalex.org/W4388109846","https://openalex.org/W4388430413","https://openalex.org/W4389105013","https://openalex.org/W4389459105","https://openalex.org/W4389916450","https://openalex.org/W4391407057","https://openalex.org/W4393404787","https://openalex.org/W4395069650","https://openalex.org/W4396598617","https://openalex.org/W4399039179","https://openalex.org/W4399039339","https://openalex.org/W4399989878","https://openalex.org/W4400314853","https://openalex.org/W4401717619","https://openalex.org/W4401747288","https://openalex.org/W4401806704","https://openalex.org/W4402216058","https://openalex.org/W4402624667","https://openalex.org/W4403918167","https://openalex.org/W4404132947","https://openalex.org/W4405487939","https://openalex.org/W4405933903","https://openalex.org/W4411485138","https://openalex.org/W7076053091"],"related_works":[],"abstract_inverted_index":{"This":[0,60],"article":[1],"investigates":[2],"safe":[3],"cooperative":[4],"control":[5,189],"problem":[6],"for":[7,149],"nonlinear":[8],"multiagent":[9],"systems":[10],"(MASs)":[11],"with":[12,158,176],"composite":[13,20],"constraints":[14,21,26,88],"and":[15,27,36,70,80,115,169],"multiactuator":[16],"faults.":[17],"Specifically,":[18],"the":[19,32,63,71,90,93,110,137,140,147,170,177,185],"primarily":[22],"consist":[23],"of":[24,73,92,139,187],"state":[25,53,58],"terminal":[28,86],"time":[29,87],"constraints.":[30],"For":[31],"former,":[33],"state-mapping":[34],"functions":[35,39],"universal":[37],"barrier":[38],"are":[40,49,106,167,181],"introduced":[41],"to":[42,55,96,108,183],"address":[43],"asymmetric":[44],"dynamic":[45,174],"delayed":[46],"constraints,":[47],"which":[48],"further":[50],"enhanced":[51],"through":[52],"transformation":[54],"create":[56],"new":[57],"variables.":[59],"approach":[61],"eliminates":[62],"limitations":[64],"imposed":[65],"by":[66,153],"initial":[67],"system":[68,99,116],"conditions":[69],"influence":[72],"unknown":[74],"terms,":[75],"while":[76],"accommodating":[77],"both":[78],"unconstrained":[79],"constrained":[81],"scenarios.":[82],"The":[83],"latter":[84],"introduces":[85],"on":[89,123],"basis":[91],"former":[94],"framework":[95],"rapidly":[97],"satisfy":[98],"performance":[100],"requirements.":[101],"Furthermore,":[102],"neural":[103],"networks":[104],"(NNs)":[105],"employed":[107],"approximate":[109],"reconstructed":[111],"multiple":[112],"fault":[113],"information":[114],"uncertainties.":[117],"Then,":[118],"an":[119,131],"actor-critic-identifier":[120],"architecture":[121],"based":[122],"fuzzy":[124],"reinforcement":[125],"learning":[126],"(RL)":[127],"is":[128,162],"constructed":[129],"via":[130],"optimal":[132],"backstepping":[133],"(OB)":[134],"method,":[135],"enabling":[136],"solution":[138],"Hamilton\u2013Jacobi\u2013Bellman":[141],"equation":[142],"within":[143],"each":[144],"subsystem":[145],"without":[146],"need":[148],"persistent":[150],"excitation.":[151],"Finally,":[152],"integrating":[154],"Lyapunov":[155],"stability":[156],"theory":[157],"graph":[159],"theory,":[160],"it":[161],"proven":[163],"that":[164],"all":[165],"signals":[166],"bounded,":[168],"followers":[171],"ultimately":[172],"achieve":[173],"consensus":[175],"leader.":[178],"Simulation":[179],"results":[180],"provided":[182],"demonstrate":[184],"effectiveness":[186],"this":[188],"strategy.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-01-17T00:00:00"}