{"id":"https://openalex.org/W4298946154","doi":"https://doi.org/10.1109/jiot.2022.3196639","title":"A Behavior Decision Method Based on Reinforcement Learning for Autonomous Driving","display_name":"A Behavior Decision Method Based on Reinforcement Learning for Autonomous Driving","publication_year":2022,"publication_date":"2022-08-05","ids":{"openalex":"https://openalex.org/W4298946154","doi":"https://doi.org/10.1109/jiot.2022.3196639"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2022.3196639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2022.3196639","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","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/A5100412656","display_name":"Kan Zheng","orcid":"https://orcid.org/0000-0002-8531-6762"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kan Zheng","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, Ningbo University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-8531-6762","affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, Ningbo University, Ningbo, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067295504","display_name":"Haojun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Haojun Yang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Western University, London, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0001-7404-5007","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Western University, London, ON, Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037643664","display_name":"Shiwen Liu","orcid":"https://orcid.org/0000-0003-4324-1851"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwen Liu","raw_affiliation_strings":["Intelligent Computing and Communications Lab, Wireless Signal Processing and Networks Lab, Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Computing and Communications Lab, Wireless Signal Processing and Networks Lab, Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100736887","display_name":"Kuan Zhang","orcid":"https://orcid.org/0000-0002-4262-153X"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuan Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Nebraska–Lincoln, Omaha, NE, USA"],"raw_orcid":"https://orcid.org/0000-0002-4262-153X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Nebraska–Lincoln, Omaha, NE, USA","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381361","display_name":"Lei Lei","orcid":"https://orcid.org/0000-0002-7828-0415"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lei Lei","raw_affiliation_strings":["School of Engineering, University of Guelph, Guelph, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7828-0415","affiliations":[{"raw_affiliation_string":"School of Engineering, University of Guelph, Guelph, ON, Canada","institution_ids":["https://openalex.org/I79817857"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100412656"],"corresponding_institution_ids":["https://openalex.org/I109935558"],"apc_list":null,"apc_paid":null,"fwci":1.4884,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.80888834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"9","issue":"24","first_page":"25386","last_page":"25394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9993000030517578,"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":0.9939000010490417,"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":0.8937830924987793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8166791200637817},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7110544443130493},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5228291153907776},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4804258346557617},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.44963523745536804},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44440770149230957},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4413788318634033},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4076932966709137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36477184295654297},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.3636884093284607},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.32066091895103455},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10165289044380188}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8937830924987793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166791200637817},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7110544443130493},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5228291153907776},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4804258346557617},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.44963523745536804},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44440770149230957},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4413788318634033},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4076932966709137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36477184295654297},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.3636884093284607},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.32066091895103455},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10165289044380188},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/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/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/jiot.2022.3196639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2022.3196639","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1764420153","display_name":null,"funder_award_id":"61731004","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2006425395","https://openalex.org/W2060135607","https://openalex.org/W2083651391","https://openalex.org/W2149822156","https://openalex.org/W2200032133","https://openalex.org/W2576845151","https://openalex.org/W2605270919","https://openalex.org/W2905334533","https://openalex.org/W3001132159","https://openalex.org/W3002044607","https://openalex.org/W3020459854","https://openalex.org/W3020774883","https://openalex.org/W3046960330","https://openalex.org/W3086911381","https://openalex.org/W3107164117","https://openalex.org/W3108765643","https://openalex.org/W3109227260","https://openalex.org/W3120878013","https://openalex.org/W3147987103","https://openalex.org/W3160223607","https://openalex.org/W3186976204","https://openalex.org/W3207822236","https://openalex.org/W4226249143","https://openalex.org/W6795589745"],"related_works":["https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W4400868993"],"abstract_inverted_index":{"Autonomous":[0],"driving":[1,18,22,47,95],"vehicles":[2,105],"can":[3,132,173],"reduce":[4,175],"congestion":[5],"and":[6,25,44,98,140],"improve":[7],"safety":[8],"while":[9],"increasing":[10],"traffic":[11,42,148],"efficiency.":[12],"To":[13],"reflect":[14],"the":[15,21,71,92,103,111,115,127,146,155,159,162,176],"quality":[16],"of":[17,94,102,114,161],"more":[19],"comprehensively,":[20],"safety,":[23,96],"efficiency,":[24,97],"occupant":[26],"comfort":[27],"should":[28],"be":[29],"jointly":[30],"optimized":[31],"for":[32,56,157,179],"autonomous":[33,57,180],"vehicles.":[34,58,181],"Furthermore,":[35],"in":[36,74],"order":[37],"to":[38,68,109,152],"cope":[39],"with":[40,86],"complicated":[41],"environments":[43],"achieve":[45],"satisfactory":[46],"performance,":[48],"a":[49,64,87,121,136,141],"powerful":[50],"behavior":[51,72,112,122],"decision-making":[52],"module":[53],"is":[54,83,106],"indispensable":[55],"Toward":[59],"this":[60,75],"end,":[61],"we":[62],"study":[63],"reinforcement-learning":[65],"(RL)-based":[66],"method":[67,164,172],"intelligently":[69],"make":[70],"decision":[73,79,123],"article.":[76],"A":[77],"Markov":[78],"process":[80],"(MDP)":[81],"model":[82],"first":[84],"formulated":[85],"comprehensive":[88],"reward":[89],"function,":[90],"including":[91],"effects":[93],"comfort.":[99],"The":[100],"knowledge":[101],"surrounding":[104],"also":[107],"leveraged":[108],"exploit":[110],"prediction":[113],"target":[116],"vehicle.":[117],"We":[118],"then":[119],"propose":[120],"strategy":[124],"based":[125],"on":[126],"actor\u2013critic":[128],"(AC)":[129],"mechanism,":[130],"which":[131],"efficiently":[133],"learn":[134],"both":[135],"Gaussian":[137],"policy":[138],"function":[139],"linear":[142],"value":[143],"function.":[144],"Finally,":[145],"real":[147],"data":[149],"are":[150],"used":[151],"build":[153],"up":[154],"simulations":[156],"evaluating":[158],"performances":[160],"proposed":[163,171],"thoroughly.":[165],"Simulation":[166],"results":[167],"show":[168],"that":[169],"our":[170],"significantly":[174],"collision":[177],"rate":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}