{"id":"https://openalex.org/W4400042228","doi":"https://doi.org/10.3390/s24134140","title":"Towards Robust Decision-Making for Autonomous Highway Driving Based on Safe Reinforcement Learning","display_name":"Towards Robust Decision-Making for Autonomous Highway Driving Based on Safe Reinforcement Learning","publication_year":2024,"publication_date":"2024-06-26","ids":{"openalex":"https://openalex.org/W4400042228","doi":"https://doi.org/10.3390/s24134140","pmid":"https://pubmed.ncbi.nlm.nih.gov/39000919"},"language":"en","primary_location":{"id":"doi:10.3390/s24134140","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24134140","pdf_url":"https://www.mdpi.com/1424-8220/24/13/4140/pdf?version=1719390865","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/24/13/4140/pdf?version=1719390865","any_repository_has_fulltext":true},"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 130025, China"],"raw_orcid":"https://orcid.org/0000-0003-1597-1961","affiliations":[{"raw_affiliation_string":"College of Automotive Engineering, Jilin University, Changchun 130025, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziguo Chen","orcid":null},"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":"Ziguo Chen","raw_affiliation_strings":["College of Automotive Engineering, Jilin University, Changchun 130025, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automotive Engineering, Jilin University, Changchun 130025, 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 130025, China"],"raw_orcid":"https://orcid.org/0009-0003-8309-7396","affiliations":[{"raw_affiliation_string":"College of Automotive Engineering, Jilin University, Changchun 130025, 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 113-8654, 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 113-8654, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042542957","display_name":"Fei Gao","orcid":"https://orcid.org/0000-0003-4195-5033"},"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":true,"raw_author_name":"Fei Gao","raw_affiliation_strings":["State Key Laboratory of Automotive Simulation and Control, Jilin University, Changhun 130025, China"],"raw_orcid":"https://orcid.org/0000-0003-4195-5033","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Simulation and Control, Jilin University, Changhun 130025, China","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4392738231"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042542957"],"corresponding_institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4392738231"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":1.2143,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77458104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"24","issue":"13","first_page":"4140","last_page":"4140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.9894999861717224,"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":0.819715142250061},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6523913145065308},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.584614634513855},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5578069686889648},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.450241357088089},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42413246631622314},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2981308698654175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25834792852401733},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.13914385437965393}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.819715142250061},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6523913145065308},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.584614634513855},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5578069686889648},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.450241357088089},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42413246631622314},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2981308698654175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25834792852401733},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13914385437965393},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/s24134140","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24134140","pdf_url":"https://www.mdpi.com/1424-8220/24/13/4140/pdf?version=1719390865","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:39000919","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39000919","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11243946","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11243946","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:b15c0ac40bf94324b343b69e9b0406ce","is_oa":true,"landing_page_url":"https://doaj.org/article/b15c0ac40bf94324b343b69e9b0406ce","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":"Sensors, Vol 24, Iss 13, p 4140 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/s24134140","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24134140","pdf_url":"https://www.mdpi.com/1424-8220/24/13/4140/pdf?version=1719390865","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400042228.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W198912494","https://openalex.org/W1965455100","https://openalex.org/W2003708116","https://openalex.org/W2101075098","https://openalex.org/W2154844948","https://openalex.org/W2343568200","https://openalex.org/W2406067508","https://openalex.org/W2487175822","https://openalex.org/W2741222326","https://openalex.org/W2787908307","https://openalex.org/W2795064979","https://openalex.org/W2806163172","https://openalex.org/W2990318036","https://openalex.org/W3008218687","https://openalex.org/W3016931720","https://openalex.org/W3041202696","https://openalex.org/W3102777717","https://openalex.org/W3109227260","https://openalex.org/W3115615603","https://openalex.org/W3115648115","https://openalex.org/W3117877147","https://openalex.org/W3119987494","https://openalex.org/W3129969543","https://openalex.org/W3141426068","https://openalex.org/W3145799606","https://openalex.org/W3185083385","https://openalex.org/W3200064570","https://openalex.org/W3204336908","https://openalex.org/W4214496626","https://openalex.org/W4225679458","https://openalex.org/W4285181401","https://openalex.org/W4286285538","https://openalex.org/W4287878580","https://openalex.org/W4366957357","https://openalex.org/W4387618290","https://openalex.org/W4388430441","https://openalex.org/W4391769168","https://openalex.org/W6745935785"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"methods":[3],"are":[4,18],"regarded":[5],"as":[6],"effective":[7],"for":[8,51,115,146,193],"designing":[9],"autonomous":[10,53,130,222],"driving":[11,54,131,150],"policies.":[12,151],"However,":[13],"even":[14],"when":[15],"RL":[16,37,75],"policies":[17,84,114],"trained":[19],"to":[20,77,95],"convergence,":[21],"ensuring":[22,81],"their":[23],"robust":[24],"safety":[25,59,88],"remains":[26],"a":[27,49,101,135,217],"challenge,":[28],"particularly":[29],"in":[30,43,100,157,166,220],"long-tail":[31],"data.":[32],"Therefore,":[33],"decision-making":[34,214],"based":[35,176],"on":[36,177],"must":[38],"adequately":[39],"consider":[40],"potential":[41,122],"variations":[42],"data":[44,99,111],"distribution.":[45],"This":[46],"paper":[47],"presents":[48],"framework":[50,73,206],"highway":[52,129,149,168,221],"decisions":[55],"that":[56,82,204],"prioritizes":[57],"both":[58],"and":[60,97,141,162,183,190,213],"robustness.":[61],"Utilizing":[62],"the":[63,83,108,128,158,191],"proposed":[64,144],"Replay":[65,102],"Buffer":[66],"Constrained":[67,136],"Policy":[68,180],"Optimization":[69],"(RECPO)":[70],"method,":[71],"this":[72],"updates":[74],"strategies":[76,175],"maximize":[78],"rewards":[79],"while":[80],"always":[85],"remain":[86],"within":[87],"constraints.":[89],"We":[90],"incorporate":[91],"importance":[92],"sampling":[93],"techniques":[94],"collect":[96],"store":[98],"buffer":[103],"during":[104],"agent":[105],"operation,":[106],"allowing":[107],"reutilization":[109],"of":[110],"from":[112],"old":[113],"training":[116],"new":[117],"policy":[118],"models,":[119],"thus":[120],"mitigating":[121],"catastrophic":[123],"forgetting.":[124],"Additionally,":[125],"we":[126,153],"transform":[127],"decision":[132],"problem":[133],"into":[134],"Markov":[137],"Decision":[138],"Process":[139],"(CMDP)":[140],"apply":[142],"our":[143,155,205],"RECPO":[145],"training,":[147],"optimizing":[148],"Finally,":[152],"deploy":[154],"method":[156],"CARLA":[159],"simulation":[160],"environment":[161],"compare":[163],"its":[164],"performance":[165],"typical":[167],"scenarios":[169],"against":[170],"traditional":[171],"CPO,":[172],"current":[173],"advanced":[174],"Deep":[178],"Deterministic":[179],"Gradient":[181],"(DDPG),":[182],"IDM":[184],"+":[185],"MOBIL":[186],"(Intelligent":[187],"Driver":[188],"Model":[189],"model":[192,209],"minimizing":[194],"overall":[195],"braking":[196],"induced":[197],"by":[198],"lane":[199],"changes).":[200],"The":[201],"results":[202],"show":[203],"significantly":[207],"enhances":[208],"convergence":[210],"speed,":[211],"safety,":[212],"stability,":[215],"achieving":[216],"zero-collision":[218],"rate":[219],"driving.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-25T08:15:23.626066","created_date":"2025-10-10T00:00:00"}