{"id":"https://openalex.org/W2897007254","doi":"https://doi.org/10.1109/ivs.2018.8500630","title":"Human-like Autonomous Vehicle Speed Control by Deep Reinforcement Learning with Double Q-Learning","display_name":"Human-like Autonomous Vehicle Speed Control by Deep Reinforcement Learning with Double Q-Learning","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2897007254","doi":"https://doi.org/10.1109/ivs.2018.8500630","mag":"2897007254"},"language":"en","primary_location":{"id":"doi:10.1109/ivs.2018.8500630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ivs.2018.8500630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5112447318","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0003-2423-2175"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["college of Software Engineering, Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"college of Software Engineering, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614097","display_name":"Ping Sun","orcid":"https://orcid.org/0000-0003-4607-0592"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Sun","raw_affiliation_strings":["college of Software Engineering, Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"college of Software Engineering, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112468900","display_name":"Yuhan Yin","orcid":"https://orcid.org/0000-0002-2094-5277"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Yin","raw_affiliation_strings":["college of Software Engineering, Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"college of Software Engineering, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342038","display_name":"Lin Lin","orcid":"https://orcid.org/0000-0002-1554-8883"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Lin","raw_affiliation_strings":["college of Software Engineering, Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"college of Software Engineering, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100336649","display_name":"Xuesong Wang","orcid":"https://orcid.org/0000-0002-4728-8924"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Wang","raw_affiliation_strings":["Key Laboratory of Road and Traffic Engineering, Ministry of Education, National Engineering Laboratory for Integrated Optimization of Road Traffic and Safety Analysis Technologies, Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Road and Traffic Engineering, Ministry of Education, National Engineering Laboratory for Integrated Optimization of Road Traffic and Safety Analysis Technologies, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":125,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1251","last_page":"1256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9991999864578247,"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"}},"topics":[{"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":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8987998962402344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7247709631919861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6153691411018372},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6080384850502014},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5779094696044922},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5561137795448303},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5526280999183655},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5278126001358032},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4547823965549469},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3393305540084839},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0745401382446289}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8987998962402344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247709631919861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6153691411018372},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6080384850502014},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5779094696044922},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5561137795448303},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5526280999183655},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5278126001358032},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4547823965549469},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3393305540084839},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0745401382446289},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ivs.2018.8500630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ivs.2018.8500630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1585377561","https://openalex.org/W1757796397","https://openalex.org/W1908020446","https://openalex.org/W2002427601","https://openalex.org/W2032621648","https://openalex.org/W2038794597","https://openalex.org/W2069940231","https://openalex.org/W2088241806","https://openalex.org/W2103325711","https://openalex.org/W2115579991","https://openalex.org/W2119112357","https://openalex.org/W2124817418","https://openalex.org/W2136891917","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155968351","https://openalex.org/W2165776394","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2182198985","https://openalex.org/W2201581102","https://openalex.org/W2342840547","https://openalex.org/W2460157116","https://openalex.org/W2483920485","https://openalex.org/W2512944926","https://openalex.org/W2513731013","https://openalex.org/W2559767995","https://openalex.org/W2562499480","https://openalex.org/W2746553466","https://openalex.org/W2951799221","https://openalex.org/W2962850098","https://openalex.org/W2963477884","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W3103780890","https://openalex.org/W4297666078","https://openalex.org/W4298857966","https://openalex.org/W6635292102","https://openalex.org/W6637967152","https://openalex.org/W6660064284","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6704559304"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2952356279"],"abstract_inverted_index":{"Autonomous":[0],"driving":[1,75],"has":[2,138],"become":[3],"a":[4,14,54,65,88],"popular":[5,38],"research":[6],"project.":[7],"How":[8],"to":[9,31,63,95],"control":[10,32,64],"vehicle":[11,34],"speed":[12,67],"is":[13,41,61,104,152],"core":[15],"problem":[16],"in":[17,43,46,141],"autonomous":[18],"driving.":[19],"Automatic":[20],"decision-making":[21],"approaches,":[22],"such":[23],"as":[24],"reinforcement":[25,55],"learning":[26,56],"(RL),":[27],"have":[28],"been":[29],"applied":[30],"the":[33,37,47,70,79,82,97,102,116,120,126],"speed.":[35],"However,":[36],"Q-learning":[39,60,133,137],"algorithm":[40],"unstable":[42],"some":[44],"games":[45],"Atari":[48],"2600":[49],"domain.":[50],"In":[51],"this":[52],"paper,":[53],"approach":[57,94],"called":[58,91],"Double":[59],"used":[62],"vehicle's":[66],"based":[68],"on":[69,78],"environment":[71],"constructed":[72],"by":[73],"naturalistic":[74],"data.":[76],"Depending":[77],"concept":[80],"of":[81,101,107,143,156],"direct":[83],"perception":[84,93],"approach,":[85],"we":[86],"propose":[87],"new":[89],"method":[90],"integrated":[92],"construct":[96],"environment.":[98],"The":[99],"input":[100],"model":[103],"made":[105],"up":[106],"high":[108],"dimensional":[109,122],"data":[110,118,123],"including":[111],"road":[112],"information":[113],"processed":[114,124],"from":[115,125],"video":[117],"and":[119,146],"low":[121],"sensors.":[127],"During":[128],"experiment,":[129],"compared":[130],"with":[131],"deep":[132,136,157],"algorithm,":[134],"double":[135],"improvements":[139],"both":[140],"terms":[142],"value":[144],"accuracy":[145],"policy":[147],"quality.":[148],"Our":[149],"model's":[150],"score":[151],"271.73%":[153],"times":[154],"that":[155],"Q-learning.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":9}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}