{"id":"https://openalex.org/W2023122515","doi":"https://doi.org/10.1109/icmlc.2013.6890495","title":"A decision-making method for autonomous vehicles based on simulation and reinforcement learning","display_name":"A decision-making method for autonomous vehicles based on simulation and reinforcement learning","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W2023122515","doi":"https://doi.org/10.1109/icmlc.2013.6890495","mag":"2023122515"},"language":"en","primary_location":{"id":"doi:10.1109/icmlc.2013.6890495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2013.6890495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 International Conference on Machine Learning and Cybernetics","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/A5069521068","display_name":"Rui Zheng","orcid":"https://orcid.org/0000-0002-0365-4494"},"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":"Rui Zheng","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, P. R. China","College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, P. R. China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100623407","display_name":"Chunming Liu","orcid":"https://orcid.org/0000-0002-5440-4938"},"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":"Chunming Liu","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, P. R. China","College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, P. R. China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101617329","display_name":"Qi Guo","orcid":"https://orcid.org/0000-0002-7055-7280"},"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":"Qi Guo","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, P. R. China","College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, P. R. China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National Univ. of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"362","last_page":"369"},"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":0.9984999895095825,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9799000024795532,"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":0.9074673652648926},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8261239528656006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7343636751174927},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5325865745544434},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5255621671676636},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5217745900154114},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4569634795188904},{"id":"https://openalex.org/keywords/decision-process","display_name":"Decision process","score":0.4262534976005554},{"id":"https://openalex.org/keywords/decision-problem","display_name":"Decision problem","score":0.42544299364089966},{"id":"https://openalex.org/keywords/dynamic-decision-making","display_name":"Dynamic decision-making","score":0.42296379804611206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3900052011013031},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.29754191637039185},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26616930961608887},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.22119492292404175},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1665985882282257},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.11585751175880432},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08382561802864075},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07852467894554138}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9074673652648926},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8261239528656006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343636751174927},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5325865745544434},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5255621671676636},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5217745900154114},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4569634795188904},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.4262534976005554},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.42544299364089966},{"id":"https://openalex.org/C174988536","wikidata":"https://www.wikidata.org/wiki/Q5318965","display_name":"Dynamic decision-making","level":2,"score":0.42296379804611206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3900052011013031},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.29754191637039185},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26616930961608887},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.22119492292404175},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1665985882282257},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.11585751175880432},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08382561802864075},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07852467894554138},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlc.2013.6890495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2013.6890495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 International Conference on Machine Learning and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W983526034","https://openalex.org/W1967825107","https://openalex.org/W1986042185","https://openalex.org/W1989810136","https://openalex.org/W2106165722","https://openalex.org/W2106655640","https://openalex.org/W2118556122","https://openalex.org/W2121863487","https://openalex.org/W2131076267","https://openalex.org/W2134882417","https://openalex.org/W2136929315","https://openalex.org/W2139204808","https://openalex.org/W2145129279","https://openalex.org/W2369547086","https://openalex.org/W3148361230","https://openalex.org/W4300995080","https://openalex.org/W6677916085","https://openalex.org/W7056011972"],"related_works":["https://openalex.org/W3121013427","https://openalex.org/W1574991376","https://openalex.org/W3188631122","https://openalex.org/W2163284801","https://openalex.org/W1526634272","https://openalex.org/W2029247269","https://openalex.org/W4244700267","https://openalex.org/W1562936359","https://openalex.org/W2530417802","https://openalex.org/W2949277377"],"abstract_inverted_index":{"There":[0],"are":[1,11],"still":[2],"some":[3],"problems":[4,25],"need":[5],"to":[6,78],"be":[7,55],"solved":[8],"though":[9],"there":[10],"a":[12,31,67,80,125],"lot":[13],"of":[14,19,23,29,71,92,103,118],"achievements":[15],"in":[16,47,124],"the":[17,27,45,93,101,104,116,119],"field":[18],"automatic":[20],"driving.":[21],"One":[22],"those":[24],"is":[26,95,106],"difficulty":[28],"designing":[30],"decision-making":[32,81,90],"system":[33,82],"for":[34,83],"complex":[35],"traffic":[36],"conditions.":[37],"In":[38,62],"recent":[39],"years,":[40],"reinforcement":[41],"learning":[42],"(RL)":[43],"shows":[44],"potential":[46],"solving":[48],"sequential":[49],"decision":[50,59],"optimization":[51],"problems,":[52],"which":[53],"can":[54],"modeled":[56,96],"as":[57,97],"Markov":[58],"processes":[60],"(MDPs).":[61],"this":[63],"paper,":[64],"we":[65,114],"establish":[66],"14-DOF":[68],"dynamic":[69],"model":[70],"an":[72,98,109],"autonomous":[73,84],"vehicle":[74,94],"and":[75,100],"use":[76],"RL":[77],"build":[79],"driving":[85],"based":[86],"on":[87],"simulation.":[88],"The":[89],"process":[91],"MDP,":[99],"performance":[102],"MDP":[105],"improved":[107],"using":[108],"approximate":[110],"RL.":[111],"At":[112],"last,":[113],"show":[115],"efficiency":[117],"proposed":[120],"method":[121],"by":[122],"simulation":[123],"highway":[126],"environment.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}