{"id":"https://openalex.org/W4417506996","doi":"https://doi.org/10.1016/j.robot.2025.105293","title":"Passive Reinforcement Learning with Optimal Control for Safe Convergence in Cyber\u2013physical Systems","display_name":"Passive Reinforcement Learning with Optimal Control for Safe Convergence in Cyber\u2013physical Systems","publication_year":2025,"publication_date":"2025-12-19","ids":{"openalex":"https://openalex.org/W4417506996","doi":"https://doi.org/10.1016/j.robot.2025.105293"},"language":"en","primary_location":{"id":"doi:10.1016/j.robot.2025.105293","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.robot.2025.105293","pdf_url":null,"source":{"id":"https://openalex.org/S133768115","display_name":"Robotics and Autonomous Systems","issn_l":"0921-8890","issn":["0921-8890","1872-793X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Autonomous Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.robot.2025.105293","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055157174","display_name":"Nicola Piccinelli","orcid":null},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Nicola Piccinelli","raw_affiliation_strings":["Department of Engineering for Innovation Medicine, University of Verona, strada Le Grazie 15, Verona, 37135, Italy"],"raw_orcid":"https://orcid.org/0000-0002-8195-1531","affiliations":[{"raw_affiliation_string":"Department of Engineering for Innovation Medicine, University of Verona, strada Le Grazie 15, Verona, 37135, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082596393","display_name":"Daniele Meli","orcid":"https://orcid.org/0000-0002-3162-388X"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Daniele Meli","raw_affiliation_strings":["Department of Computer Science, University of Verona, strada Le Grazie 15, Verona, 37135, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Verona, strada Le Grazie 15, Verona, 37135, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120860323","display_name":"Enrico Bonoldi","orcid":null},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Enrico Bonoldi","raw_affiliation_strings":["Department of Engineering for Innovation Medicine, University of Verona, strada Le Grazie 15, Verona, 37135, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering for Innovation Medicine, University of Verona, strada Le Grazie 15, Verona, 37135, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001597507","display_name":"Riccardo Muradore","orcid":null},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Riccardo Muradore","raw_affiliation_strings":["Department of Engineering for Innovation Medicine, University of Verona, strada Le Grazie 15, Verona, 37135, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering for Innovation Medicine, University of Verona, strada Le Grazie 15, Verona, 37135, Italy","institution_ids":["https://openalex.org/I119439378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055157174"],"corresponding_institution_ids":["https://openalex.org/I119439378"],"apc_list":{"value":3020,"currency":"USD","value_usd":3020},"apc_paid":{"value":3020,"currency":"USD","value_usd":3020},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38608031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"197","issue":null,"first_page":"105293","last_page":"105293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.6636999845504761,"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":0.6636999845504761,"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":0.18479999899864197,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.04809999838471413,"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":0.7656999826431274},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5813999772071838},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5288000106811523},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5253000259399414},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5152999758720398},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.4625999927520752},{"id":"https://openalex.org/keywords/passivity","display_name":"Passivity","score":0.4620000123977661},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.429500013589859},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4016999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8041999936103821},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7656999826431274},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5813999772071838},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5288000106811523},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5253000259399414},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.4625999927520752},{"id":"https://openalex.org/C2778809601","wikidata":"https://www.wikidata.org/wiki/Q1045736","display_name":"Passivity","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.429500013589859},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38370001316070557},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C167964875","wikidata":"https://www.wikidata.org/wiki/Q17011487","display_name":"Exponential stability","level":3,"score":0.3416999876499176},{"id":"https://openalex.org/C2776829284","wikidata":"https://www.wikidata.org/wiki/Q1341651","display_name":"Lyapunov stability","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.25270000100135803},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.robot.2025.105293","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.robot.2025.105293","pdf_url":null,"source":{"id":"https://openalex.org/S133768115","display_name":"Robotics and Autonomous Systems","issn_l":"0921-8890","issn":["0921-8890","1872-793X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Autonomous Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.robot.2025.105293","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.robot.2025.105293","pdf_url":null,"source":{"id":"https://openalex.org/S133768115","display_name":"Robotics and Autonomous Systems","issn_l":"0921-8890","issn":["0921-8890","1872-793X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Autonomous Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2001579955","https://openalex.org/W2046376809","https://openalex.org/W2086975818","https://openalex.org/W2169130436","https://openalex.org/W2296039882","https://openalex.org/W2438255111","https://openalex.org/W3118584630","https://openalex.org/W3128013500","https://openalex.org/W3150718622","https://openalex.org/W3179588321","https://openalex.org/W4206696957","https://openalex.org/W4206831758","https://openalex.org/W4285204099","https://openalex.org/W4287266177","https://openalex.org/W4391260208","https://openalex.org/W4392351923","https://openalex.org/W4408780387"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"can":[3],"compute":[4],"optimal":[5],"strategies":[6],"for":[7,66,90,108,119,295,301,312],"accomplishing":[8],"difficult":[9],"tasks":[10],"in":[11,133,181,233,255,266,271,283],"complex":[12],"scenarios.":[13],"However,":[14],"most":[15],"RL":[16,35,87,102,128,169,214,298,307],"algorithms":[17],"do":[18],"not":[19],"provide":[20],"safety":[21,64,282],"and":[22,51,95,111,212,215,235,268,281,299,319,336],"performance":[23],"guarantees":[24,98],"during":[25],"the":[26,46,123,130,134,139,152,157,164,168,174,185,189,243,272,284,323],"deployment":[27],"phase.":[28],"This":[29,81,100],"is":[30,36,48,69,136,171,198],"a":[31,55,78,84,146,195,209,220,228,237,252,332,338],"critical":[32],"drawback":[33],"when":[34],"applied":[37,218],"to":[38,49,54,122,144,160,183,200,219],"cyber\u2013physical":[39],"systems":[40,68],"such":[41],"as":[42,77],"robotic":[43,67,91,230,341],"manipulators,":[44],"where":[45,194],"goal":[47,57],"always":[50],"safely":[52],"converge":[53],"desired":[56,124],"or":[58],"equilibrium":[59,125,302],"state.":[60],"Specifically,":[61],"one":[62],"fundamental":[63],"requirement":[65],"closed-loop":[70],"L":[71],"2":[72],"-stability,":[73],"which":[74],"has":[75],"passivity":[76,94,280],"sufficient":[79],"condition.":[80],"paper":[82],"proposes":[83],"novel":[85],"switched":[86,292],"control":[88,293],"scheme":[89],"systems,":[92],"with":[93,114,178,208,248],"asymptotic":[96,120,202],"stability":[97],".":[99],"combines":[101],"over":[103],"constrained":[104,306],"Markov":[105],"decision":[106],"processes,":[107],"passive":[109],"training":[110,267],"inference":[112],",":[113],"Linear":[115],"Quadratic":[116],"Regulation":[117],"(LQR)":[118],"convergence":[121],"point.":[126],"During":[127,150],"training,":[129],"energy":[131,141,154,310],"stored":[132],"system":[135,186,294,335],"monitored":[137],"via":[138],"virtual":[140,153,309],"tank":[142,155,311],"approach":[143],"train":[145],"cost":[147],"critic":[148],"function.":[149,328],"inference,":[151,269],"modulates":[156],"command":[158],"input":[159],"guarantee":[161,201],"passivity.":[162],"Finally,":[163],"reward":[165,317],"design":[166],"of":[167,192,227,245,274,286],"agent":[170],"based":[172],"on":[173,236,251,331,337],"Lyapunov":[175,327],"function":[176,318],"associated":[177],"LQR":[179,190,300,326],"control,":[180],"order":[182],"steer":[184],"state":[187],"towards":[188],"basin":[191],"attraction,":[193],"switching":[196,320],"mechanism":[197],"triggered":[199],"convergence.":[203,303],"We":[204,240],"compare":[205],"our":[206,246,262],"methodology":[207,263],"model-based":[210,216],"controller":[211],"other":[213],"architectures":[217],"paradigmatic":[221],"under-actuated":[222],"cart\u2013pole":[223,334],"system,":[224],"an":[225,249],"instance":[226],"2-DOF":[229],"manipulator,":[231],"both":[232],"simulation":[234],"real":[238,333],"setup.":[239],"also":[241],"test":[242],"generality":[244],"approach,":[247],"experiment":[250],"6-DOF":[253,340],"manipulator":[254],"simulation.":[256],"The":[257],"experimental":[258],"validation":[259],"shows":[260],"that":[261],"performs":[264],"better":[265],"even":[270],"presence":[273,285],"plant":[275],"modelling":[276],"errors,":[277],"while":[278],"guaranteeing":[279],"large":[287],"disruptive":[288],"disturbances.":[289],"\u2022":[290,304,315,329],"A":[291,305,316],"robotics":[296],"using":[297,308,322],"passivity-based":[313],"control.":[314],"criterion":[321],"closed":[324],"loop":[325],"Validation":[330],"simulated":[339],"manipulator.":[342]},"counts_by_year":[],"updated_date":"2026-02-03T00:53:05.648605","created_date":"2025-12-19T00:00:00"}