{"id":"https://openalex.org/W3135239772","doi":"https://doi.org/10.1109/iros51168.2021.9636468","title":"Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function","display_name":"Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3135239772","doi":"https://doi.org/10.1109/iros51168.2021.9636468","mag":"3135239772"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636468","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5004124678","display_name":"Haitong Ma","orcid":"https://orcid.org/0000-0002-9943-0638"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haitong Ma","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611365","display_name":"Jianyu Chen","orcid":"https://orcid.org/0000-0002-1835-6115"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyu Chen","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences, Tsinghua University","Shanghai Qizhi Institute"],"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shanghai Qizhi Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098652003","display_name":"Shengbo Eben","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037283185","display_name":"Ziyu Lin","orcid":"https://orcid.org/0000-0003-0532-0030"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Lin","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082794136","display_name":"Yang Guan","orcid":"https://orcid.org/0000-0003-0689-0510"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Guan","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007325049","display_name":"Yangang Ren","orcid":"https://orcid.org/0000-0002-1173-7230"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangang Ren","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036282981","display_name":"Sifa Zheng","orcid":"https://orcid.org/0000-0001-5160-1365"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifa Zheng","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004124678"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.6954,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.95943074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4552","last_page":"4559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955000281333923,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955000281333923,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10524","display_name":"Traffic control and management","score":0.9775999784469604,"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":0.8463692665100098},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.7689801454544067},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.67332923412323},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5987257957458496},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.5712577104568481},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5709292888641357},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5401611924171448},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47644785046577454},{"id":"https://openalex.org/keywords/time-constraint","display_name":"Time constraint","score":0.41018280386924744},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.40607166290283203},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.3967413306236267},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3820500373840332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3211757242679596},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1854545772075653},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15515920519828796}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8463692665100098},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.7689801454544067},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.67332923412323},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5987257957458496},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.5712577104568481},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5709292888641357},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5401611924171448},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47644785046577454},{"id":"https://openalex.org/C2775907273","wikidata":"https://www.wikidata.org/wiki/Q7805281","display_name":"Time constraint","level":2,"score":0.41018280386924744},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40607166290283203},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.3967413306236267},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3820500373840332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3211757242679596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1854545772075653},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15515920519828796},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros51168.2021.9636468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636468","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1518931405","https://openalex.org/W1551275368","https://openalex.org/W1771410628","https://openalex.org/W1845972764","https://openalex.org/W2052446317","https://openalex.org/W2073265799","https://openalex.org/W2155511972","https://openalex.org/W2170973929","https://openalex.org/W2462906003","https://openalex.org/W2489231587","https://openalex.org/W2735010720","https://openalex.org/W2804791273","https://openalex.org/W2892521964","https://openalex.org/W2944582497","https://openalex.org/W2962803570","https://openalex.org/W2963082979","https://openalex.org/W2968945909","https://openalex.org/W2979211489","https://openalex.org/W2991604404","https://openalex.org/W3088218629","https://openalex.org/W3099108819","https://openalex.org/W3114647763","https://openalex.org/W3124407081","https://openalex.org/W3131282584","https://openalex.org/W3134135463","https://openalex.org/W3134476446","https://openalex.org/W3138915777","https://openalex.org/W3162902207","https://openalex.org/W3180711880","https://openalex.org/W4285071855","https://openalex.org/W4293545785","https://openalex.org/W6638018090","https://openalex.org/W6687063787","https://openalex.org/W6718836005","https://openalex.org/W6737893269","https://openalex.org/W6751725685","https://openalex.org/W6771188774","https://openalex.org/W6773895053","https://openalex.org/W6785250840","https://openalex.org/W6791851269"],"related_works":["https://openalex.org/W1819938260","https://openalex.org/W2340892746","https://openalex.org/W3163022373","https://openalex.org/W2742483371","https://openalex.org/W3005999311","https://openalex.org/W2064309607","https://openalex.org/W3200670168","https://openalex.org/W2090344631","https://openalex.org/W3125309996","https://openalex.org/W4313469555"],"abstract_inverted_index":{"Model":[0],"information":[1],"can":[2,79],"be":[3,80],"used":[4],"to":[5,14,69,134],"predict":[6],"future":[7],"trajectories,":[8],"so":[9],"it":[10],"has":[11],"huge":[12],"potential":[13],"avoid":[15],"dangerous":[16],"regions":[17],"when":[18],"applying":[19],"reinforcement":[20],"learning":[21],"(RL)":[22],"on":[23,66],"real-world":[24],"tasks,":[25],"like":[26],"autonomous":[27,124],"driving.":[28],"However,":[29],"existing":[30],"studies":[31],"mostly":[32],"use":[33],"model-free":[34],"constrained":[35,51,99,147],"RL,":[36,52],"which":[37,53],"causes":[38],"inevitable":[39],"constraint":[40,70,138],"violations.":[41],"This":[42],"paper":[43],"proposes":[44],"a":[45,122],"model-based":[46],"feasibility":[47,56],"enhancement":[48],"technique":[49],"of":[50,57],"enhances":[54],"the":[55,67,74,77,89,98,111],"policy":[58,78,100],"using":[59,73],"generalized":[60],"control":[61],"barrier":[62],"function":[63],"(GCBF)":[64],"defined":[65],"distance":[68],"boundary.":[71],"By":[72],"model":[75],"information,":[76],"optimized":[81],"safely":[82],"without":[83],"violating":[84],"actual":[85],"safety":[86],"constraints,":[87],"and":[88,117,140],"sample":[90],"efficiency":[91],"is":[92,102],"increased.":[93],"The":[94,129],"infeasibility":[95],"in":[96,114,121],"solving":[97],"gradient":[101],"handled":[103],"by":[104],"an":[105],"adaptive":[106],"coefficient":[107],"mechanism.":[108],"We":[109],"evaluate":[110],"proposed":[112,130],"method":[113,131],"both":[115],"simulations":[116],"real":[118],"vehicle":[119],"experiments":[120],"complex":[123],"driving":[125],"collision":[126],"avoidance":[127],"task.":[128],"achieves":[132],"up":[133],"four":[135],"times":[136,143],"fewer":[137],"violations":[139],"converges":[141],"3.36":[142],"faster":[144],"than":[145],"baseline":[146],"RL":[148],"approaches.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-30T08:08:38.191290","created_date":"2025-10-10T00:00:00"}