{"id":"https://openalex.org/W4402216364","doi":"https://doi.org/10.1109/access.2024.3454249","title":"Constraints Driven Safe Reinforcement Learning for Autonomous Driving Decision-Making","display_name":"Constraints Driven Safe Reinforcement Learning for Autonomous Driving Decision-Making","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402216364","doi":"https://doi.org/10.1109/access.2024.3454249"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3454249","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3454249","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3454249","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0001-9020-6720","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/A5115695468","display_name":"Xiaodong Wang","orcid":"https://orcid.org/0000-0001-8949-5967"},"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":"Xiaodong Wang","raw_affiliation_strings":["College of Automotive Engineering, Jilin University, Changchun, China"],"raw_orcid":null,"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/A5067527835","display_name":"Yuze Fan","orcid":"https://orcid.org/0009-0003-8309-7396"},"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":"Yuze Fan","raw_affiliation_strings":["College of Automotive Engineering, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0009-0003-8309-7396","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/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, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0002-4623-3956","affiliations":[{"raw_affiliation_string":"College of Automotive Engineering, 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":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.7315,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8373284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"12","issue":null,"first_page":"128007","last_page":"128023"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9998999834060669,"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":0.9973999857902527,"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":0.9861000180244446,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8397343158721924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6922428607940674},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.4529997706413269},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35857439041137695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35244250297546387}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8397343158721924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6922428607940674},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.4529997706413269},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35857439041137695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35244250297546387}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3454249","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3454249","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:aff75aee17c5417db7d942a49b49d4db","is_oa":true,"landing_page_url":"https://doaj.org/article/aff75aee17c5417db7d942a49b49d4db","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 128007-128023 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3454249","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3454249","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.699999988079071,"display_name":"Peace, Justice and strong institutions"}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1538903703","https://openalex.org/W1833552892","https://openalex.org/W2032924574","https://openalex.org/W2086124410","https://openalex.org/W2321166790","https://openalex.org/W2404189583","https://openalex.org/W2406067508","https://openalex.org/W2746553466","https://openalex.org/W2758107681","https://openalex.org/W2965888130","https://openalex.org/W3089582082","https://openalex.org/W3116665706","https://openalex.org/W3128115655","https://openalex.org/W3182751084","https://openalex.org/W3196020871","https://openalex.org/W3210590548","https://openalex.org/W4285279465","https://openalex.org/W4312974600","https://openalex.org/W4381733133","https://openalex.org/W4385329466","https://openalex.org/W4386219277","https://openalex.org/W4388340369","https://openalex.org/W4390933704","https://openalex.org/W4392397363","https://openalex.org/W4392406006","https://openalex.org/W4392966039","https://openalex.org/W6685444567","https://openalex.org/W6696324988","https://openalex.org/W6751285671"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W1966803121","https://openalex.org/W2391666574","https://openalex.org/W2786230833","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1544514152","https://openalex.org/W1493952344"],"abstract_inverted_index":{"Although":[0],"reinforcement":[1,150,207],"learning":[2,151,208],"(RL)":[3],"methodologies":[4],"exhibit":[5],"potential":[6,231],"in":[7,13,29,45,73,244],"addressing":[8],"decision-making":[9,69,99],"and":[10,53,70,159,164,238],"planning":[11,71],"problems":[12],"autonomous":[14,97,166],"driving,":[15],"ensuring":[16,216],"the":[17,20,84,93,96,109,136,141,146,160,184,188,206,224,229,236,242],"safety":[18,64,87,110,129,214],"of":[19,86,174,241],"vehicle":[21],"under":[22],"all":[23],"circumstances":[24],"remains":[25],"a":[26,62,102,116,124,199,220],"formidable":[27],"challenge":[28],"practical":[30],"applications.":[31,246],"Current":[32],"RL":[33,65,111],"methods":[34],"are":[35],"predominantly":[36],"driven":[37],"by":[38,178],"singular":[39],"reward":[40],"mechanisms,":[41],"frequently":[42],"encountering":[43],"difficulties":[44],"balancing":[46],"multiple":[47],"sub-rewards":[48],"such":[49],"as":[50,101],"safety,":[51],"comfort,":[52],"efficiency.":[54],"To":[55],"address":[56,128],"these":[57],"limitations,":[58],"this":[59],"paper":[60],"introduces":[61,115],"constraint-driven":[63],"method,":[66,122,187],"applied":[67],"to":[68,127,183,234],"policy":[72],"highway":[74],"scenarios.":[75],"This":[76],"method":[77,143,209,243],"ensures":[78],"decisions":[79],"maximize":[80],"performance":[81],"rewards":[82],"within":[83,108,135],"bounds":[85],"constraints,":[88],"exhibiting":[89],"exceptional":[90],"robustness.":[91],"Initially,":[92],"framework":[94],"reformulates":[95],"driving":[98,167,195,201,217],"problem":[100],"Constrained":[103],"Markov":[104],"Decision":[105],"Process":[106],"(CMDP)":[107],"framework.":[112],"It":[113],"then":[114],"Multi-Level":[117],"Safety-Constrained":[118],"Policy":[119,154],"Optimization":[120,155],"(MLSCPO)":[121],"incorporating":[123],"cost":[125],"function":[126],"constraints.":[130],"Ultimately,":[131],"simulated":[132],"tests":[133],"conducted":[134],"CARLA":[137],"environment":[138],"demonstrate":[139],"that":[140],"proposed":[142,189],"MLSCPO":[144],"outperforms":[145],"current":[147],"advanced":[148],"safe":[149],"policy,":[152],"Proximal":[153],"with":[156,172,205],"Lagrangian":[157],"(PPO-Lag)":[158],"traditional":[161],"stable":[162],"longitudinal":[163],"lateral":[165],"model,":[168],"Intelligent":[169],"Driver":[170],"Model":[171],"Minimization":[173],"Overall":[175],"Braking":[176],"Induced":[177],"Lane":[179],"Changes":[180],"(IDM+MOBIL).":[181],"Compared":[182],"classic":[185],"IDM+MOBIL":[186],"approach":[190],"not":[191],"only":[192],"achieves":[193],"efficient":[194],"but":[196],"also":[197],"offers":[198],"better":[200],"experience.":[202],"In":[203,223],"comparison":[204],"PPO-Lag,":[210],"it":[211],"significantly":[212],"enhances":[213],"while":[215],"efficiency,":[218],"achieving":[219],"zero-collision":[221],"rate.":[222],"future,":[225],"we":[226],"will":[227],"integrate":[228],"aforementioned":[230],"expansion":[232],"plans":[233],"enhance":[235],"usability":[237],"generalization":[239],"capabilities":[240],"real-world":[245]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}