{"id":"https://openalex.org/W2905334533","doi":"https://doi.org/10.1109/tsmc.2018.2870983","title":"A Reinforcement Learning Approach to Autonomous Decision Making of Intelligent Vehicles on Highways","display_name":"A Reinforcement Learning Approach to Autonomous Decision Making of Intelligent Vehicles on Highways","publication_year":2018,"publication_date":"2018-12-11","ids":{"openalex":"https://openalex.org/W2905334533","doi":"https://doi.org/10.1109/tsmc.2018.2870983","mag":"2905334533"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2018.2870983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2018.2870983","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: 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/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Xu","raw_affiliation_strings":["Institute of Unmanned Systems, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Institute of Unmanned Systems, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057599028","display_name":"Lei Zuo","orcid":"https://orcid.org/0000-0002-9938-7449"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zuo","raw_affiliation_strings":["Institute of Unmanned Systems, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Institute of Unmanned Systems, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353915","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-6352-2725"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Institute of Unmanned Systems, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Institute of Unmanned Systems, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065246382","display_name":"Lilin Qian","orcid":"https://orcid.org/0000-0002-6227-9970"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lilin Qian","raw_affiliation_strings":["Institute of Unmanned Systems, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Institute of Unmanned Systems, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073231890","display_name":"Junkai Ren","orcid":"https://orcid.org/0000-0002-6199-7452"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junkai Ren","raw_affiliation_strings":["Institute of Unmanned Systems, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Institute of Unmanned Systems, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044447816","display_name":"Zhenping Sun","orcid":"https://orcid.org/0009-0009-1491-5280"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenping Sun","raw_affiliation_strings":["Institute of Unmanned Systems, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Institute of Unmanned Systems, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053112608"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":7.4964,"has_fulltext":false,"cited_by_count":168,"citation_normalized_percentile":{"value":0.97688246,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9995999932289124,"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":0.9995999932289124,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9991999864578247,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8240464925765991},{"id":"https://openalex.org/keywords/overtaking","display_name":"Overtaking","score":0.7431071996688843},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7264639139175415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7078458666801453},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6519718170166016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.500007152557373},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4577158987522125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45758405327796936},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4144435524940491},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.29284587502479553},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.271295428276062},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1700003445148468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09288513660430908}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8240464925765991},{"id":"https://openalex.org/C2778448659","wikidata":"https://www.wikidata.org/wiki/Q1931051","display_name":"Overtaking","level":2,"score":0.7431071996688843},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7264639139175415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7078458666801453},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6519718170166016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.500007152557373},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4577158987522125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45758405327796936},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4144435524940491},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.29284587502479553},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.271295428276062},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1700003445148468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09288513660430908},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2018.2870983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2018.2870983","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5320757814","display_name":null,"funder_award_id":"U1564214","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7457541925","display_name":null,"funder_award_id":"61751311","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8136749885","display_name":null,"funder_award_id":"61611540348","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320310234","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W565786554","https://openalex.org/W1584101032","https://openalex.org/W1626155273","https://openalex.org/W1968004977","https://openalex.org/W1987725948","https://openalex.org/W1988707322","https://openalex.org/W1989499286","https://openalex.org/W1989962452","https://openalex.org/W1997112725","https://openalex.org/W2001856902","https://openalex.org/W2003993399","https://openalex.org/W2012612381","https://openalex.org/W2017570421","https://openalex.org/W2023122515","https://openalex.org/W2028145673","https://openalex.org/W2032378315","https://openalex.org/W2041225042","https://openalex.org/W2048989213","https://openalex.org/W2054469884","https://openalex.org/W2060135607","https://openalex.org/W2064823886","https://openalex.org/W2072931156","https://openalex.org/W2082972783","https://openalex.org/W2107664660","https://openalex.org/W2107668352","https://openalex.org/W2108511252","https://openalex.org/W2118556122","https://openalex.org/W2120581524","https://openalex.org/W2121806728","https://openalex.org/W2121863487","https://openalex.org/W2157472761","https://openalex.org/W2159312714","https://openalex.org/W2161795906","https://openalex.org/W2164617893","https://openalex.org/W2165726932","https://openalex.org/W2171974638","https://openalex.org/W2188644438","https://openalex.org/W2242368318","https://openalex.org/W2406067508","https://openalex.org/W2438413413","https://openalex.org/W2476930474","https://openalex.org/W2504001346","https://openalex.org/W2586680856","https://openalex.org/W2623234904","https://openalex.org/W2758704203","https://openalex.org/W3027095131","https://openalex.org/W4214717370","https://openalex.org/W4236439427","https://openalex.org/W4285719527","https://openalex.org/W6683841269","https://openalex.org/W6738690632"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2386410636","https://openalex.org/W3038962357"],"abstract_inverted_index":{"Autonomous":[0],"decision":[1,34,47,60,193,203],"making":[2,35,48],"is":[3,30,55,86],"a":[4,19,58,79,97,148,196],"critical":[5],"and":[6,27,53,132,160,204],"difficult":[7],"task":[8],"for":[9,32,50,76,90,130,168],"intelligent":[10,37,169],"vehicles":[11,38,170],"in":[12,96],"dynamic":[13],"transportation":[14],"environments.":[15],"In":[16,41,70],"this":[17],"paper,":[18],"reinforcement":[20],"learning":[21,29,138],"approach":[22,125],"with":[23,62,115],"value":[24,91,131],"function":[25,92],"approximation":[26,93,134],"feature":[28,128],"proposed":[31,43,180,220],"autonomous":[33,77,198],"of":[36,164,178,218],"on":[39,111,171,195,209],"highways.":[40,172,210],"the":[42,45,123,162,176,179,191,216,219],"approach,":[44],"sequential":[46],"problem":[49],"lane":[51],"changing":[52],"overtaking":[54,202],"modeled":[56],"as":[57,120],"Markov":[59],"process":[61],"multiple":[63],"goals,":[64],"including":[65],"safety,":[66],"speediness,":[67],"smoothness,":[68],"etc.":[69],"order":[71],"to":[72,156,200],"learn":[73],"optimized":[74],"policies":[75],"decision-making,":[78],"multiobjective":[80,121],"approximate":[81],"policy":[82,133,194],"iteration":[83],"(MO-API)":[84],"algorithm":[85],"presented.":[87],"The":[88,173,211],"features":[89,103,106],"are":[94],"learned":[95,192],"data-driven":[98,127],"way,":[99],"where":[100],"sparse":[101],"kernel-based":[102],"or":[104],"manifold-based":[105],"can":[107,140],"be":[108,141],"constructed":[109],"based":[110],"data":[112,159],"samples.":[113],"Compared":[114],"previous":[116],"RL":[117],"algorithms":[118],"such":[119],"Q-learning,":[122],"MO-API":[124,181],"uses":[126],"representation":[129],"so":[135],"that":[136],"better":[137],"efficiency":[139],"achieved.":[142],"A":[143],"highway":[144],"simulation":[145],"environment":[146],"using":[147],"14":[149],"degree-of-freedom":[150],"vehicle":[151,199],"dynamics":[152],"model":[153],"was":[154],"established":[155],"generate":[157],"training":[158],"test":[161],"performance":[163],"different":[165,184],"decision-making":[166],"methods":[167],"results":[174,213],"illustrate":[175],"advantages":[177],"method":[182],"under":[183,206],"traffic":[185,208],"conditions.":[186],"Furthermore,":[187],"we":[188],"also":[189,214],"tested":[190],"real":[197],"implement":[201],"control":[205],"normal":[207],"experimental":[212],"demonstrate":[215],"effectiveness":[217],"method.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":36},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":4}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2025-10-10T00:00:00"}