{"id":"https://openalex.org/W4403863433","doi":"https://doi.org/10.1109/jiot.2024.3487854","title":"Constrained Reinforcement-Learning-Enabled Policies With Augmented Lagrangian for Cooperative Intersection Management","display_name":"Constrained Reinforcement-Learning-Enabled Policies With Augmented Lagrangian for Cooperative Intersection Management","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4403863433","doi":"https://doi.org/10.1109/jiot.2024.3487854"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2024.3487854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2024.3487854","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","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/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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhai Gao","raw_affiliation_strings":["College of Automotive Engineering and the National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0002-4623-3956","affiliations":[{"raw_affiliation_string":"College of Automotive Engineering and the National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114443835","display_name":"Hesheng Hao","orcid":"https://orcid.org/0009-0005-9029-9249"},"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":"Hesheng Hao","raw_affiliation_strings":["College of Automotive Engineering, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0009-0005-9029-9249","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/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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Gao","raw_affiliation_strings":["College of Automotive Engineering and the National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0001-9020-6720","affiliations":[{"raw_affiliation_string":"College of Automotive Engineering and the National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I194450716"],"apc_list":null,"apc_paid":null,"fwci":1.7046,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84841204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"12","issue":"5","first_page":"5396","last_page":"5411"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.996399998664856,"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":0.996399998664856,"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/T12782","display_name":"Assembly Line Balancing Optimization","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.973800003528595,"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":0.7414334416389465},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.679286539554596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6739721298217773},{"id":"https://openalex.org/keywords/augmented-lagrangian-method","display_name":"Augmented Lagrangian method","score":0.5173370242118835},{"id":"https://openalex.org/keywords/lagrangian","display_name":"Lagrangian","score":0.47716063261032104},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.376158207654953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27708524465560913},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.1650708019733429},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14502844214439392},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.13558846712112427},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.127090185880661},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11243346333503723}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7414334416389465},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.679286539554596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6739721298217773},{"id":"https://openalex.org/C150452318","wikidata":"https://www.wikidata.org/wiki/Q4820432","display_name":"Augmented Lagrangian method","level":2,"score":0.5173370242118835},{"id":"https://openalex.org/C53469067","wikidata":"https://www.wikidata.org/wiki/Q505735","display_name":"Lagrangian","level":2,"score":0.47716063261032104},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.376158207654953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27708524465560913},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.1650708019733429},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14502844214439392},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.13558846712112427},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.127090185880661},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11243346333503723}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2024.3487854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2024.3487854","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1050522061","display_name":null,"funder_award_id":"52394261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W134193224","https://openalex.org/W1191599655","https://openalex.org/W1977565586","https://openalex.org/W1985609359","https://openalex.org/W2010725166","https://openalex.org/W2080782477","https://openalex.org/W2114195376","https://openalex.org/W2137514195","https://openalex.org/W2516923985","https://openalex.org/W2736601468","https://openalex.org/W2765693755","https://openalex.org/W2913512536","https://openalex.org/W2939973228","https://openalex.org/W2964749398","https://openalex.org/W2976036462","https://openalex.org/W2996623681","https://openalex.org/W3088218629","https://openalex.org/W3091885432","https://openalex.org/W3189576409","https://openalex.org/W4214717370","https://openalex.org/W4285189474","https://openalex.org/W4295813962","https://openalex.org/W4312332697","https://openalex.org/W4313534875","https://openalex.org/W4321483908","https://openalex.org/W4382618547","https://openalex.org/W4391021053","https://openalex.org/W4399728414","https://openalex.org/W6605512291","https://openalex.org/W6627932998","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6843754643","https://openalex.org/W6853778389"],"related_works":["https://openalex.org/W2015060724","https://openalex.org/W2919324478","https://openalex.org/W4400665899","https://openalex.org/W2130120519","https://openalex.org/W2012871340","https://openalex.org/W2315802443","https://openalex.org/W2767923834","https://openalex.org/W2376104286","https://openalex.org/W1635517180","https://openalex.org/W2082353735"],"abstract_inverted_index":{"Traffic":[0],"control":[1],"at":[2],"signal-free":[3],"intersections":[4],"is":[5,91],"extensively":[6],"studied":[7],"to":[8,37,80,93,102,148,165],"facilitate":[9],"cooperative":[10,26],"traffic":[11,162,228],"for":[12,25,171],"connected":[13],"and":[14,106,112,139,141,151,194,216,232,243],"autonomous":[15],"vehicles":[16],"(CAVs).":[17],"Reinforcement":[18],"learning":[19],"(RL)":[20],"techniques":[21],"have":[22],"proven":[23],"effective":[24],"intersection":[27],"management":[28],"(CIM)":[29],"challenges,":[30],"but":[31],"often":[32],"involves":[33],"unsafe":[34],"states":[35],"due":[36],"the":[38,46,72,115,145,172,206,210],"arbitrary":[39],"exploration":[40],"of":[41],"trial-and-error":[42],"mechanism.":[43],"To":[44],"tackle":[45],"safety":[47,163,177,190,200],"challenges":[48],"associated":[49,175],"with":[50,76,176],"current":[51],"RL-based":[52],"CIM":[53,60,207,218],"methods,":[54],"this":[55,199],"article":[56],"proposes":[57],"a":[58,66,82,186,214],"safety-augmented":[59],"(SACIM)":[61],"method.":[62,219],"Initially,":[63],"we":[64,135],"introduce":[65],"constrained":[67,83],"RL":[68],"framework":[69],"that":[70,223],"integrates":[71,185],"augmented":[73],"Lagrangian":[74],"method":[75,116,184,225],"proximal":[77],"policy":[78,89,104,153,196],"optimization":[79,120],"address":[81],"Markov":[84],"decision":[85],"process":[86],"(CMDP).":[87],"A":[88],"network":[90],"designed":[92],"optimize":[94],"performance,":[95],"while":[96,167],"multiple":[97],"value":[98],"networks":[99],"are":[100],"employed":[101],"evaluate":[103],"performance":[105],"safety.":[107],"By":[108],"incorporating":[109],"Lagrange":[110],"multipliers":[111],"quadratic":[113],"penalties,":[114],"effectively":[117,204],"transforms":[118],"constraints":[119],"problems":[121],"into":[122,144],"unconstrained":[123],"primal-dual":[124],"problems,":[125],"achieving":[126],"an":[127],"optimal":[128,241],"solution":[129],"without":[130],"requiring":[131],"strong":[132],"convexity.":[133],"Simultaneously,":[134],"incorporate":[136],"communication":[137],"delays":[138],"long-":[140],"short-term":[142,168],"costs":[143],"CMDP":[146,211],"formulation":[147],"enhance":[149],"safe":[150,215],"efficient":[152],"exploration,":[154],"closely":[155],"mirroring":[156],"real-world":[157],"scenarios.":[158],"Long-term":[159],"cost":[160,169],"reflects":[161],"related":[164],"collisions,":[166],"accounts":[170],"driving":[173],"risks":[174],"violations":[178],"during":[179],"vehicle":[180],"interactions.":[181],"Furthermore,":[182],"our":[183,224],"motion":[187],"prediction-based,":[188],"in-the-loop":[189],"layer,":[191],"facilitating":[192],"rapid":[193],"robust":[195],"learning.":[197],"Through":[198],"enhancement":[201],"design,":[202],"SACIM":[203],"resolves":[205],"issue":[208],"within":[209],"framework,":[212],"training":[213],"reliable":[217],"Simulation":[220],"results":[221],"demonstrate":[222],"significantly":[226],"improves":[227],"safety,":[229],"efficiency,":[230],"comfort,":[231],"inference":[233],"time,":[234],"outperforming":[235],"various":[236],"methods":[237],"based":[238],"on":[239],"rules,":[240],"control,":[242],"RL.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}