{"id":"https://openalex.org/W3201271190","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533979","title":"Safe Reinforcement Learning for CPSs via Formal Modeling and Verification","display_name":"Safe Reinforcement Learning for CPSs via Formal Modeling and Verification","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3201271190","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533979","mag":"3201271190"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5064193335","display_name":"Chenchen Yang","orcid":"https://orcid.org/0000-0001-9627-7407"},"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":"Chenchen Yang","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":null,"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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375018","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0002-5347-8281"},"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":"Jing Liu","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":null,"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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107749145","display_name":"Haiying Sun","orcid":"https://orcid.org/0009-0006-9365-9518"},"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":"Haiying Sun","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai, China"],"raw_orcid":null,"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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009658384","display_name":"Junfeng Sun","orcid":"https://orcid.org/0000-0002-7614-7127"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junfeng Sun","raw_affiliation_strings":["R&D Institute, CASCO Signal Ltd., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"R&D Institute, CASCO Signal Ltd., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441901","display_name":"Xiang Chen","orcid":"https://orcid.org/0000-0001-8259-4815"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Chen","raw_affiliation_strings":["R&D Institute, CASCO Signal Ltd., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"R&D Institute, CASCO Signal Ltd., Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115589477","display_name":"Lipeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lipeng Zhang","raw_affiliation_strings":["R&D Institute, CASCO Signal Ltd., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"R&D Institute, CASCO Signal Ltd., Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9995999932289124,"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/T10142","display_name":"Formal Methods in Verification","score":0.9995999932289124,"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/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9801999926567078,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8569889068603516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7653218507766724},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6732239723205566},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.6026265025138855},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5703801512718201},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5631344318389893},{"id":"https://openalex.org/keywords/probabilistic-ctl","display_name":"Probabilistic CTL","score":0.5415608286857605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5244249105453491},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5235457420349121},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.49809718132019043},{"id":"https://openalex.org/keywords/probabilistic-automaton","display_name":"Probabilistic automaton","score":0.4923759698867798},{"id":"https://openalex.org/keywords/learning-automata","display_name":"Learning automata","score":0.4892718493938446},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.47643786668777466},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4392589330673218},{"id":"https://openalex.org/keywords/formal-methods","display_name":"Formal methods","score":0.43055087327957153},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.42976540327072144},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4118771553039551},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.18403172492980957},{"id":"https://openalex.org/keywords/probabilistic-analysis-of-algorithms","display_name":"Probabilistic analysis of algorithms","score":0.16048046946525574},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15513655543327332},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11708086729049683},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.10230961441993713},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10126784443855286}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8569889068603516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7653218507766724},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6732239723205566},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.6026265025138855},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5703801512718201},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5631344318389893},{"id":"https://openalex.org/C52063229","wikidata":"https://www.wikidata.org/wiki/Q7246845","display_name":"Probabilistic CTL","level":4,"score":0.5415608286857605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5244249105453491},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5235457420349121},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.49809718132019043},{"id":"https://openalex.org/C174784677","wikidata":"https://www.wikidata.org/wiki/Q176567","display_name":"Probabilistic automaton","level":3,"score":0.4923759698867798},{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.4892718493938446},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.47643786668777466},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4392589330673218},{"id":"https://openalex.org/C75606506","wikidata":"https://www.wikidata.org/wiki/Q1049183","display_name":"Formal methods","level":2,"score":0.43055087327957153},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.42976540327072144},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4118771553039551},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.18403172492980957},{"id":"https://openalex.org/C24404364","wikidata":"https://www.wikidata.org/wiki/Q7246846","display_name":"Probabilistic analysis of algorithms","level":3,"score":0.16048046946525574},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15513655543327332},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11708086729049683},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.10230961441993713},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10126784443855286},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8399999737739563}],"awards":[{"id":"https://openalex.org/G4844286744","display_name":"\u4fe1\u606f\u7269\u7406\u7cfb\u7edf\u65f6\u7a7a\u5efa\u6a21\u4e0e\u9a8c\u8bc1\u5173\u952e\u95ee\u9898\u7814\u7a76","funder_award_id":"61972150","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8181698950","display_name":null,"funder_award_id":"2017YFB1001800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"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}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W296769721","https://openalex.org/W1534052968","https://openalex.org/W1996625075","https://openalex.org/W2048355938","https://openalex.org/W2121863487","https://openalex.org/W2166423024","https://openalex.org/W2169239645","https://openalex.org/W2217538972","https://openalex.org/W2222789563","https://openalex.org/W2288565641","https://openalex.org/W2537758980","https://openalex.org/W2573731904","https://openalex.org/W2751422670","https://openalex.org/W2787908307","https://openalex.org/W2963575966","https://openalex.org/W2973186106","https://openalex.org/W3013550173","https://openalex.org/W3090425956","https://openalex.org/W3114224083","https://openalex.org/W3127561923","https://openalex.org/W4214717370","https://openalex.org/W4300116138","https://openalex.org/W6748381881","https://openalex.org/W6773319185","https://openalex.org/W6775354534"],"related_works":["https://openalex.org/W2401977081","https://openalex.org/W2065292090","https://openalex.org/W1545451257","https://openalex.org/W249340682","https://openalex.org/W2803580888","https://openalex.org/W4313207396","https://openalex.org/W2038056353","https://openalex.org/W1817234734","https://openalex.org/W4244879671","https://openalex.org/W3105078582"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,10,134],"(RL)":[2],"can":[3],"be":[4],"defined":[5],"as":[6],"the":[7,14,17,57,85,119,133,139,143],"process":[8],"of":[9,16,36,38,84,93,158],"policies":[11],"that":[12,117],"maximize":[13],"expectation":[15],"rewards.":[18],"It":[19],"has":[20],"shown":[21],"success":[22],"in":[23,41],"solving":[24],"complex":[25],"decision-making":[26],"tasks.":[27],"However,":[28],"reinforcement":[29],"learning-based":[30],"controllers":[31],"do":[32],"not":[33],"provide":[34],"guarantees":[35],"safety":[37],"physical":[39],"models":[40],"Cyber-physical":[42],"systems":[43],"(CPSs).":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,74,101],"propose":[49,75],"a":[50,114],"framework,":[51],"which":[52],"allows":[53],"implementing":[54],"RL":[55],"to":[56,65,81],"safe":[58,99,147],"control":[59,160],"system":[60],"by":[61,122],"transforming":[62],"formal":[63],"analysis":[64],"learned":[66],"policy.":[67],"For":[68,98],"satisfaction":[69],"verification":[70],"and":[71,87,148],"quantitative":[72],"analysis,":[73],"an":[76,103],"uncertainty":[77],"modeling":[78],"language":[79],"CSML":[80,89],"describe":[82],"behaviors":[83],"system,":[86,140],"transform":[88],"design":[90],"into":[91],"networks":[92],"probabilistic":[94,123],"timed":[95],"automata":[96],"(NPTA).":[97],"learning,":[100],"present":[102],"algorithm":[104],"called":[105],"Safe":[106],"Control":[107],"with":[108],"Formal":[109],"Methods":[110],"(SCFM).":[111],"SCFM":[112],"constructs":[113],"state":[115,130],"set":[116],"obeys":[118],"constraint":[120],"described":[121],"computation":[124],"tree":[125],"logic":[126],"(PCTL)":[127],"via":[128],"exploring":[129],"space":[131],"before":[132],"process.":[135],"The":[136],"monitor":[137],"monitors":[138],"determines":[141],"whether":[142],"chosen":[144],"action":[145],"is":[146],"corrects":[149],"unsafe":[150],"decisions.":[151],"We":[152],"validate":[153],"our":[154],"method":[155],"through":[156],"experiments":[157],"lane-change":[159],"for":[161],"autonomous":[162],"cars.":[163]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}