{"id":"https://openalex.org/W4414432604","doi":"https://doi.org/10.1109/case58245.2025.11163999","title":"Safety-Guaranteed Policy Composition via Generalized Policy Improvement for Autonomous Vehicles","display_name":"Safety-Guaranteed Policy Composition via Generalized Policy Improvement for Autonomous Vehicles","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414432604","doi":"https://doi.org/10.1109/case58245.2025.11163999"},"language":"en","primary_location":{"id":"doi:10.1109/case58245.2025.11163999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","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/A5014299354","display_name":"Ni Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ni Mu","raw_affiliation_strings":["Tsinghua University,Center for Intelligent and Networked System (CFINS), Beijing Key Laboratory of Embodied Intelligence Systems,Department of Automation,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Intelligent and Networked System (CFINS), Beijing Key Laboratory of Embodied Intelligence Systems,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yao Luan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Luan","raw_affiliation_strings":["Tsinghua University,Center for Intelligent and Networked System (CFINS), Beijing Key Laboratory of Embodied Intelligence Systems,Department of Automation,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Intelligent and Networked System (CFINS), Beijing Key Laboratory of Embodied Intelligence Systems,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044965133","display_name":"Qing\u2010Shan Jia","orcid":"https://orcid.org/0000-0002-4683-7215"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Shan Jia","raw_affiliation_strings":["Tsinghua University,Center for Intelligent and Networked System (CFINS), Beijing Key Laboratory of Embodied Intelligence Systems,Department of Automation,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Intelligent and Networked System (CFINS), Beijing Key Laboratory of Embodied Intelligence Systems,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":0.9388,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76909718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2450","last_page":"2455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.8202000260353088,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.8202000260353088,"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/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.789900004863739,"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":0.757099986076355,"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":0.8496999740600586},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.7228999733924866},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.636900007724762},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.47450000047683716},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.4722999930381775},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.46320000290870667},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.38580000400543213}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8496999740600586},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.7228999733924866},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.636900007724762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5924000144004822},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.47450000047683716},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.42100000381469727},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3050000071525574},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.29600000381469727},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C2986542766","wikidata":"https://www.wikidata.org/wiki/Q2090494","display_name":"Vehicle safety","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C2777016798","wikidata":"https://www.wikidata.org/wiki/Q2001988","display_name":"Collision avoidance system","level":4,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case58245.2025.11163999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307804","display_name":"BP","ror":"https://ror.org/051659894"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1540821927","https://openalex.org/W1769611610","https://openalex.org/W1965455100","https://openalex.org/W2055202879","https://openalex.org/W2056877664","https://openalex.org/W2583993537","https://openalex.org/W2766447205","https://openalex.org/W2989958156","https://openalex.org/W4214717370","https://openalex.org/W4220902452","https://openalex.org/W4294993033","https://openalex.org/W4315778373","https://openalex.org/W4315781029","https://openalex.org/W4366957357","https://openalex.org/W4386219277","https://openalex.org/W4388230841","https://openalex.org/W4389002566","https://openalex.org/W4392941164","https://openalex.org/W4392942009","https://openalex.org/W4401025062","https://openalex.org/W4403676845","https://openalex.org/W4407466734","https://openalex.org/W4408142709","https://openalex.org/W4409494151"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"driving":[1,151],"has":[2,114],"the":[3,43,103,115,141,145],"potential":[4],"to":[5,27,41,57,67,117,126,140],"revolutionize":[6],"transportation":[7],"by":[8],"improving":[9,73],"safety,":[10],"efficiency,":[11,31],"and":[12,23,34,110,147],"accessibility.":[13],"However,":[14],"existing":[15],"methods,":[16],"such":[17],"as":[18,42],"reinforcement":[19,128],"learning":[20,129],"(RL)":[21],"approaches":[22],"rule-based":[24,108],"strategies,":[25],"struggle":[26],"achieve":[28],"high":[29],"sample":[30],"superior":[32],"performance,":[33],"safety":[35,74,146],"assurance,":[36],"a":[37,52,107,111,137],"challenge":[38],"we":[39,49],"refer":[40],"\"impossible":[44,142],"triangle\".":[45],"In":[46],"this":[47,59],"paper,":[48],"propose":[50],"Safe-GPI,":[51],"novel":[53],"decision-making":[54],"method":[55],"designed":[56],"address":[58],"issue.":[60],"Safe-GPI":[61,83,135],"employs":[62],"Generalized":[63],"Policy":[64],"Improvement":[65],"(GPI)":[66],"effectively":[68],"combine":[69],"multiple":[70],"policies,":[71],"thereby":[72],"without":[75],"compromising":[76],"performance.":[77],"Our":[78],"theoretical":[79],"analysis":[80],"demonstrates":[81],"that":[82,102,134],"maintains":[84],"formal":[85],"guarantees":[86],"for":[87],"collision":[88,120],"avoidance":[89],"under":[90],"specific":[91],"reward":[92],"structures,":[93],"while":[94,122],"also":[95],"providing":[96],"performance":[97,124],"assurances.":[98],"Experimental":[99],"results":[100],"demonstrate":[101],"simple":[104],"combination":[105],"of":[106,149],"model":[109],"planning-based":[112],"policy":[113],"ability":[116],"significantly":[118],"reduce":[119],"rates,":[121],"achieving":[123],"comparable":[125],"deep":[127],"methods.":[130],"These":[131],"findings":[132],"suggest":[133],"offers":[136],"feasible":[138],"solution":[139],"triangle\",":[143],"enhancing":[144],"reliability":[148],"autonomous":[150],"systems.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}