{"id":"https://openalex.org/W4413392944","doi":"https://doi.org/10.23919/acc63710.2025.11108023","title":"Safe Reinforcement Learning Tracking Control based on Tunable Input-to-State Safe Control Barrier Function","display_name":"Safe Reinforcement Learning Tracking Control based on Tunable Input-to-State Safe Control Barrier Function","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413392944","doi":"https://doi.org/10.23919/acc63710.2025.11108023"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11108023","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11108023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-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/A5016000776","display_name":"Soha Kanso","orcid":"https://orcid.org/0009-0003-0921-1939"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210110792","display_name":"Centre de Recherche en Automatique de Nancy","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Soha Kanso","raw_affiliation_strings":["Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000"],"affiliations":[{"raw_affiliation_string":"Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590","https://openalex.org/I4210110792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003606353","display_name":"Mayank Jha","orcid":"https://orcid.org/0000-0002-6926-1386"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210110792","display_name":"Centre de Recherche en Automatique de Nancy","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mayank Shekhar Jha","raw_affiliation_strings":["Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000"],"affiliations":[{"raw_affiliation_string":"Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590","https://openalex.org/I4210110792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106184374","display_name":"Didier Theilliol","orcid":"https://orcid.org/0000-0002-1942-0094"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210110792","display_name":"Centre de Recherche en Automatique de Nancy","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Didier Theilliol","raw_affiliation_strings":["Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000"],"affiliations":[{"raw_affiliation_string":"Universite de Lorraine, CNRS, CRAN,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590","https://openalex.org/I4210110792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016000776"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210110792","https://openalex.org/I90183372"],"apc_list":null,"apc_paid":null,"fwci":1.3185,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83451896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3103","last_page":"3108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14225","display_name":"Advanced Sensor and Control Systems","score":0.8912000060081482,"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/T14225","display_name":"Advanced Sensor and Control Systems","score":0.8912000060081482,"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/T14474","display_name":"Industrial Technology and Control Systems","score":0.8812000155448914,"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/T14011","display_name":"Elevator Systems and Control","score":0.8797000050544739,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8128815293312073},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.603326678276062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6018502116203308},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5150389671325684},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5088034272193909},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.46897682547569275},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3599039912223816},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.32094889879226685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25048625469207764},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.23353031277656555},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.05812877416610718},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.05097252130508423}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8128815293312073},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.603326678276062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6018502116203308},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5150389671325684},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5088034272193909},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.46897682547569275},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3599039912223816},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.32094889879226685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25048625469207764},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23353031277656555},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.05812877416610718},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.05097252130508423},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/acc63710.2025.11108023","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11108023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05435810v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05435810","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025 American Control Conference (ACC), Jul 2025, Denver, France. pp.3103-3108, &#x27E8;10.23919/ACC63710.2025.11108023&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1968908471","https://openalex.org/W1969959431","https://openalex.org/W2165726932","https://openalex.org/W2291649624","https://openalex.org/W2560504659","https://openalex.org/W2587478215","https://openalex.org/W2789826932","https://openalex.org/W2966735560","https://openalex.org/W2968945909","https://openalex.org/W2971473345","https://openalex.org/W3154507809","https://openalex.org/W3166543246","https://openalex.org/W4313478129","https://openalex.org/W4388852236","https://openalex.org/W4391021039","https://openalex.org/W4391021228"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"a":[3,69,98,144],"novel":[4],"off-policy":[5],"safe":[6,77],"Reinforcement":[7],"Learning":[8],"(RL)":[9],"approach":[10,140],"for":[11],"optimal":[12,30,36],"tracking":[13,37],"of":[14,28,55,90,138],"continuous-time":[15],"nonlinear":[16],"systems":[17],"affine":[18],"in":[19,25,52],"control.":[20],"The":[21],"main":[22],"contribution":[23],"consists":[24],"the":[26,48,53,84,91,105,126,128,131,136,139],"synthesis":[27],"an":[29,110],"tracker":[31],"under":[32],"safety":[33,42,46,85,114],"guarantees":[34],"enabling":[35],"while":[38],"satisfying":[39],"state":[40],"based":[41],"constraints.":[43],"To":[44],"ensure":[45],"during":[47,86],"exploration":[49],"phase,":[50],"even":[51],"presence":[54],"model":[56],"uncertainty,":[57],"control":[58,78,100],"inputs":[59],"are":[60,122],"dynamically":[61],"adjusted.":[62],"These":[63],"adjustments,":[64],"determined":[65],"as":[66],"solutions":[67],"to":[68,109,124],"quadratic":[70],"programming":[71],"(QP)":[72],"problem,":[73],"incorporate":[74],"tunable":[75],"input-to-state":[76],"barrier":[79,101],"function":[80,102],"(TISSf-CBF)":[81],"conditions.":[82],"Additionally,":[83],"exploitation":[87],"(operational":[88],"phase)":[89],"learned":[92],"policy":[93],"is":[94,141],"guaranteed":[95],"by":[96],"integrating":[97],"reciprocal":[99],"(RCBF)":[103],"into":[104],"cost":[106],"function,":[107],"leading":[108],"effective":[111],"trade-off":[112],"between":[113],"and":[115,130],"system":[116],"performance.":[117],"Novel":[118],"mathematically":[119],"rigorous":[120],"proofs":[121],"developed":[123],"guarantee":[125],"safety,":[127],"stability":[129],"convergence":[132],"towards":[133],"optimality.":[134],"Finally,":[135],"effectiveness":[137],"assessed":[142],"using":[143],"simulation":[145],"example.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}
