{"id":"https://openalex.org/W4388819818","doi":"https://doi.org/10.1109/tits.2023.3331723","title":"Multi-Agent Constrained Policy Optimization for Conflict-Free Management of Connected Autonomous Vehicles at Unsignalized Intersections","display_name":"Multi-Agent Constrained Policy Optimization for Conflict-Free Management of Connected Autonomous Vehicles at Unsignalized Intersections","publication_year":2023,"publication_date":"2023-11-20","ids":{"openalex":"https://openalex.org/W4388819818","doi":"https://doi.org/10.1109/tits.2023.3331723"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2023.3331723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2023.3331723","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation 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/A5024414161","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0003-1597-1961"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["College of Automotive Engineering, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0003-1597-1961","affiliations":[{"raw_affiliation_string":"College of Automotive Engineering, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071303232","display_name":"Yun Li","orcid":"https://orcid.org/0009-0002-7824-7751"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yun Li","raw_affiliation_strings":["Graduate School of Information and Science Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0002-7824-7751","affiliations":[{"raw_affiliation_string":"Graduate School of Information and Science Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101688555","display_name":"Fei Gao","orcid":"https://orcid.org/0000-0001-9020-6720"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4392738231","display_name":"State Key Laboratory of Automotive Simulation and Control","ror":"https://ror.org/00b67z867","country_code":null,"type":"facility","lineage":["https://openalex.org/I194450716","https://openalex.org/I4392738231"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Gao","raw_affiliation_strings":["State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0001-9020-6720","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4392738231"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022668758","display_name":"Zhenhai Gao","orcid":"https://orcid.org/0000-0002-4623-3956"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4392738231","display_name":"State Key Laboratory of Automotive Simulation and Control","ror":"https://ror.org/00b67z867","country_code":null,"type":"facility","lineage":["https://openalex.org/I194450716","https://openalex.org/I4392738231"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhai Gao","raw_affiliation_strings":["State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0002-4623-3956","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4392738231"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108143707","display_name":"Tianyao Zhang","orcid":"https://orcid.org/0000-0003-0012-2190"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4392738231","display_name":"State Key Laboratory of Automotive Simulation and Control","ror":"https://ror.org/00b67z867","country_code":null,"type":"facility","lineage":["https://openalex.org/I194450716","https://openalex.org/I4392738231"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyao Zhang","raw_affiliation_strings":["State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4392738231"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1144,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.96118687,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"25","issue":"6","first_page":"5374","last_page":"5388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9994000196456909,"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/T10524","display_name":"Traffic control and management","score":0.9994000196456909,"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/T10370","display_name":"Traffic and Road Safety","score":0.9955000281333923,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9830999970436096,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8621711730957031},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.6817503571510315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6361685991287231},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5255124568939209},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5162620544433594},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.42118000984191895},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4138687551021576},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.37076854705810547},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3202013373374939},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.26252636313438416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.221635639667511},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.1777392327785492},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12021529674530029},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11633068323135376}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8621711730957031},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.6817503571510315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6361685991287231},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5255124568939209},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5162620544433594},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.42118000984191895},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4138687551021576},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37076854705810547},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3202013373374939},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26252636313438416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.221635639667511},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.1777392327785492},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12021529674530029},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11633068323135376},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2023.3331723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2023.3331723","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7194057990","display_name":null,"funder_award_id":"52202495","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7872204055","display_name":null,"funder_award_id":"52202494","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1997082481","https://openalex.org/W2061052237","https://openalex.org/W2080782477","https://openalex.org/W2087065496","https://openalex.org/W2136398072","https://openalex.org/W2170788932","https://openalex.org/W2201235138","https://openalex.org/W2276329747","https://openalex.org/W2344243544","https://openalex.org/W2413232101","https://openalex.org/W2592818502","https://openalex.org/W2791054528","https://openalex.org/W2793780249","https://openalex.org/W2890536008","https://openalex.org/W2890598945","https://openalex.org/W2913512536","https://openalex.org/W2915779054","https://openalex.org/W2921392100","https://openalex.org/W2922677095","https://openalex.org/W2939973228","https://openalex.org/W2940821858","https://openalex.org/W2976036462","https://openalex.org/W2976133733","https://openalex.org/W2996623681","https://openalex.org/W2999203646","https://openalex.org/W3086302379","https://openalex.org/W3088218629","https://openalex.org/W3124755563","https://openalex.org/W3150493802","https://openalex.org/W3152695221","https://openalex.org/W3153130015","https://openalex.org/W3178423299","https://openalex.org/W4226071977","https://openalex.org/W4313534875","https://openalex.org/W4322730985","https://openalex.org/W6638018090","https://openalex.org/W6737893269"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"Autonomous":[0],"Intersection":[1],"Management":[2],"(AIM)":[3],"systems":[4],"present":[5],"a":[6,81,93,242],"new":[7],"paradigm":[8],"for":[9,61,246],"conflict-free":[10,58],"cooperation":[11],"of":[12,22,39,258],"connected":[13],"autonomous":[14],"vehicles":[15],"(CAVs)":[16],"at":[17,63],"road":[18],"intersections,":[19,65],"the":[20,30,37,76,89,107,117,127,132,157,197,201,234,247,256],"aim":[21],"which":[23],"is":[24],"to":[25,115,155,196,233],"eliminate":[26],"collisions":[27],"and":[28,33,49,86,101,167,176,191,203,215,219,227],"improve":[29],"traffic":[31,174,222],"efficiency":[32,48,211,223],"ride":[34,172,253],"comfort.":[35],"Given":[36],"challenges":[38],"current":[40],"centralized":[41],"coordination":[42],"methods":[43],"in":[44],"balancing":[45],"high":[46],"computational":[47,210],"robust":[50],"safety":[51,122,177],"assurance,":[52],"this":[53],"paper":[54],"proposes":[55],"an":[56,164],"innovative":[57],"management":[59,179],"scheme":[60],"CAVs":[62],"unsignalized":[64],"leveraging":[66],"safe":[67,77],"multi-agent":[68],"deep":[69],"reinforcement":[70,137,193],"learning":[71,138],"(MADRL).":[72],"Firstly,":[73],"we":[74,105,162],"formulate":[75],"MADRL":[78],"problem":[79,91],"as":[80],"constrained":[82],"Markov":[83],"game":[84],"(CMG)":[85],"then":[87],"transform":[88],"AIM":[90,159,165],"into":[92],"CMG":[94,118],"by":[95,131,212,224],"carefully":[96],"designing":[97],"state,":[98],"action,":[99],"reward,":[100],"cost":[102],"functions.":[103],"Subsequently,":[104],"propose":[106],"Multi-Agent":[108],"Constrained":[109],"Policy":[110],"Optimization":[111],"(MACPO),":[112],"specifically":[113],"tailored":[114],"solve":[116],"problem.":[119],"MACPO":[120],"incorporates":[121],"constraints":[123],"that":[124,141],"further":[125],"restrict":[126],"trust":[128],"region":[129],"formed":[130],"Kullback-Leibler":[133],"(KL)":[134],"divergence,":[135],"facilitating":[136],"policy":[139,166],"updates":[140],"maximize":[142],"performance":[143],"while":[144,250],"keeping":[145],"constraint":[146],"costs":[147],"within":[148],"their":[149],"limit":[150],"bounds.":[151],"This":[152],"leads":[153],"us":[154],"introduce":[156],"MACPO-based":[158],"Algorithm.":[160],"Finally,":[161],"train":[163],"compare":[168],"its":[169],"computation":[170],"time,":[171,249],"comfort,":[173,254],"efficiency,":[175],"with":[178,200],"schemes":[180],"based":[181],"on":[182],"Model":[183],"Predictive":[184],"Control":[185],"(MPC),":[186],"Mixed":[187],"Integer":[188],"Programming":[189],"(MIP),":[190],"non-safety-aware":[192],"learning.":[194],"According":[195],"results,":[198],"compared":[199],"MPC":[202],"MIP":[204],"methods,":[205,238],"our":[206,239],"method":[207,240],"has":[208,220],"increased":[209],"65.22":[213],"times":[214,217,226,229],"731.52":[216],"respectively,":[218],"improved":[221],"2.41":[225],"1.80":[228],"respectively.":[230],"In":[231],"contrast":[232],"non-safety":[235],"awareness":[236],"RL":[237],"achieves":[241],"zero":[243],"collision":[244],"rate":[245],"first":[248],"also":[251],"enhancing":[252],"highlighting":[255],"advantages":[257],"using":[259],"MACPO.":[260]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}