{"id":"https://openalex.org/W4414693524","doi":"https://doi.org/10.1109/tcad.2025.3616856","title":"Safe Reinforcement Learning for NN-Controlled Systems With Neural Barrier Certificate Guidance","display_name":"Safe Reinforcement Learning for NN-Controlled Systems With Neural Barrier Certificate Guidance","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W4414693524","doi":"https://doi.org/10.1109/tcad.2025.3616856"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2025.3616856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2025.3616856","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and 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/A5049103084","display_name":"Hanrui Zhao","orcid":"https://orcid.org/0000-0001-5246-0330"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanrui Zhao","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5246-0330","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109676901","display_name":"Mengxin Ren","orcid":"https://orcid.org/0009-0004-3772-8369"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxin Ren","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-3772-8369","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059888387","display_name":"Banglong Liu","orcid":"https://orcid.org/0009-0002-3584-1339"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Banglong Liu","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-3584-1339","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059554537","display_name":"Niuniu Qi","orcid":"https://orcid.org/0009-0003-5352-3681"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Niuniu Qi","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-5352-3681","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079927285","display_name":"Xia Zeng","orcid":"https://orcid.org/0000-0003-2575-7045"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xia Zeng","raw_affiliation_strings":["School of Computer and Information Science, Southwest University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0003-2575-7045","affiliations":[{"raw_affiliation_string":"School of Computer and Information Science, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058328411","display_name":"Zhenbing Zeng","orcid":"https://orcid.org/0000-0002-9728-1114"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenbing Zeng","raw_affiliation_strings":["Department of Mathematics, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9728-1114","affiliations":[{"raw_affiliation_string":"Department of Mathematics, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065028030","display_name":"Zhengfeng Yang","orcid":"https://orcid.org/0000-0003-1209-8191"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengfeng Yang","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1209-8191","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29737556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"5","first_page":"2460","last_page":"2473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.948199987411499,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.948199987411499,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9395999908447266,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8551999926567078},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6310999989509583},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5738000273704529},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5256999731063843},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43479999899864197},{"id":"https://openalex.org/keywords/certificate","display_name":"Certificate","score":0.4196000099182129},{"id":"https://openalex.org/keywords/iterative-learning-control","display_name":"Iterative learning control","score":0.3984000086784363}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8551999926567078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218999862670898},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6310999989509583},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5738000273704529},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5256999731063843},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4307999908924103},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.3984000086784363},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3246999979019165},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3000999987125397},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C155386361","wikidata":"https://www.wikidata.org/wiki/Q1649571","display_name":"Process control","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2025.3616856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2025.3616856","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1285319566","display_name":null,"funder_award_id":"12171159","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1690479065","display_name":null,"funder_award_id":"62472362","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6641716459","display_name":null,"funder_award_id":"62272397","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7294830272","display_name":null,"funder_award_id":"2023YFA1009402","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8447102269","display_name":null,"funder_award_id":"40500-20104-222609","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Safe":[0],"controller":[1,32,49,62,95,113],"synthesis":[2],"is":[3,114,125],"crucial":[4],"for":[5,20,142,167],"safety-critical":[6],"applications.":[7],"This":[8],"paper":[9],"presents":[10],"a":[11,42,59,87,118,168],"novel":[12],"reinforcement":[13,68],"learning":[14,33,69],"approach":[15],"to":[16,116,132,174],"synthesize":[17],"safe":[18,44],"controllers":[19],"NN-controlled":[21],"systems.":[22],"The":[23,54],"core":[24],"idea":[25],"leverages":[26],"an":[27,64,128,147],"iterative":[28,140],"scheme":[29],"that":[30,91],"combines":[31],"with":[34,50,171],"neural":[35,46,102],"barrier":[36],"certificate":[37],"(BC)":[38],"verification,":[39],"ultimately":[40],"producing":[41],"provably":[43],"deep":[45,67],"network":[47],"(DNN)":[48],"formal":[51,88],"safety":[52,75],"guarantees.":[53],"process":[55],"begins":[56],"by":[57,100],"pre-training":[58],"well-performing":[60],"DNN":[61,94],"as":[63,127],"\u201coracle\u201d":[65],"via":[66,104],"(DRL).":[70],"To":[71],"formally":[72],"verify":[73],"the":[74,78,82,93,111,121,134,139,155],"properties":[76],"of":[77,157,162],"closed-loop":[79],"system":[80,170],"under":[81],"base":[83,112],"controller,":[84],"we":[85],"devise":[86],"verification":[89],"procedure":[90],"approximates":[92],"using":[96],"polynomial":[97],"inclusion,":[98],"followed":[99],"synthesizing":[101],"BCs":[103],"sum-of-squares":[105],"(SOS)":[106],"relaxation.":[107],"In":[108],"cases":[109],"where":[110],"insufficient":[115],"yield":[117],"real":[119],"BC,":[120],"current":[122],"spurious":[123],"BC":[124],"incorporated":[126],"additional":[129],"penalty":[130],"term":[131],"reshape":[133],"RL":[135],"reward":[136],"function,":[137],"guiding":[138],"refinement":[141],"new":[143],"controllers.":[144],"We":[145],"implement":[146],"automated":[148],"tool,":[149],"NBCRL,":[150],"and":[151,164],"experimental":[152],"results":[153],"demonstrate":[154],"benefits":[156],"our":[158],"method":[159],"in":[160],"terms":[161],"efficiency":[163],"scalability":[165],"even":[166],"nonlinear":[169],"dimension":[172],"up":[173],"12.":[175]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
