{"id":"https://openalex.org/W3210962293","doi":"https://doi.org/10.1109/itsc48978.2021.9564576","title":"Belief state separated reinforcement learning for autonomous vehicle decision making under uncertainty","display_name":"Belief state separated reinforcement learning for autonomous vehicle decision making under uncertainty","publication_year":2021,"publication_date":"2021-09-19","ids":{"openalex":"https://openalex.org/W3210962293","doi":"https://doi.org/10.1109/itsc48978.2021.9564576","mag":"3210962293"},"language":"en","primary_location":{"id":"doi:10.1109/itsc48978.2021.9564576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc48978.2021.9564576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","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/A5030950316","display_name":"Ziqing Gu","orcid":"https://orcid.org/0000-0003-2990-9632"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziqing Gu","raw_affiliation_strings":["State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101620888","display_name":"Yujie Yang","orcid":"https://orcid.org/0000-0001-7222-0019"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujie Yang","raw_affiliation_strings":["State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067909017","display_name":"Jingliang Duan","orcid":"https://orcid.org/0000-0002-3697-1576"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingliang Duan","raw_affiliation_strings":["State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"https://orcid.org/0000-0003-4923-3633"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611364","display_name":"Jianyu Chen","orcid":"https://orcid.org/0000-0001-7211-7927"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyu Chen","raw_affiliation_strings":["Institute of Interdiscriplinary Information Sciences, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Interdiscriplinary Information Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102751432","display_name":"Wenhan Cao","orcid":"https://orcid.org/0009-0001-1367-4210"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Cao","raw_affiliation_strings":["State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036282981","display_name":"Sifa Zheng","orcid":"https://orcid.org/0000-0001-5160-1365"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifa Zheng","raw_affiliation_strings":["State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5030950316"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3666,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.5986584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"586","last_page":"592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9968000054359436,"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":0.9965000152587891,"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":0.7329548597335815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6739234924316406},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.5449777841567993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49118492007255554},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4866536259651184},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.48328712582588196},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4736441373825073},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4450254440307617},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41959500312805176},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41481783986091614},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.41437458992004395},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3740037679672241},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33840036392211914},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2989882528781891},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22144684195518494},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.16107189655303955},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10578370094299316}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7329548597335815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6739234924316406},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.5449777841567993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49118492007255554},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4866536259651184},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.48328712582588196},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4736441373825073},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4450254440307617},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41959500312805176},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41481783986091614},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.41437458992004395},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3740037679672241},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33840036392211914},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2989882528781891},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22144684195518494},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.16107189655303955},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10578370094299316},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc48978.2021.9564576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc48978.2021.9564576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G330528761","display_name":null,"funder_award_id":"2020YFB1600200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W834081922","https://openalex.org/W1662842982","https://openalex.org/W1959608418","https://openalex.org/W2055501135","https://openalex.org/W2121092017","https://openalex.org/W2140135625","https://openalex.org/W2168359464","https://openalex.org/W2741086815","https://openalex.org/W2744953678","https://openalex.org/W2781726626","https://openalex.org/W2786019934","https://openalex.org/W2889347284","https://openalex.org/W2900152462","https://openalex.org/W2962854145","https://openalex.org/W2962902376","https://openalex.org/W2962938178","https://openalex.org/W2963009616","https://openalex.org/W2963430173","https://openalex.org/W2966504041","https://openalex.org/W2970427641","https://openalex.org/W2994849131","https://openalex.org/W2995298643","https://openalex.org/W2995773109","https://openalex.org/W3099108819","https://openalex.org/W3106775416","https://openalex.org/W3114647763","https://openalex.org/W3128395826","https://openalex.org/W3132285497","https://openalex.org/W4285071855","https://openalex.org/W4289294484","https://openalex.org/W4294560979","https://openalex.org/W6623316541","https://openalex.org/W6640963894","https://openalex.org/W6677939520","https://openalex.org/W6680657880","https://openalex.org/W6731293529","https://openalex.org/W6747473740","https://openalex.org/W6748400484","https://openalex.org/W6751659697","https://openalex.org/W6754162236","https://openalex.org/W6766861245","https://openalex.org/W6771217966","https://openalex.org/W6771810092"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W3096874164","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W2937181779","https://openalex.org/W2386410636"],"abstract_inverted_index":{"In":[0],"autonomous":[1,77,183],"driving,":[2],"the":[3,84,97,102,106,136,144,168,187,208],"ego":[4],"vehicle":[5],"and":[6,16,131,195],"its":[7],"surrounding":[8,188],"traffic":[9],"environments":[10],"always":[11],"have":[12],"uncertainties":[13],"like":[14],"parameter":[15],"structural":[17],"errors,":[18],"behavior":[19,193],"randomness":[20],"of":[21,51,76,105,116,158,167],"road":[22],"users,":[23],"etc.":[24],"Furthermore,":[25],"environmental":[26],"sensors":[27],"are":[28,190],"noisy":[29],"or":[30],"even":[31],"biased.":[32],"This":[33,63,119],"problem":[34],"can":[35,211],"be":[36,112],"formulated":[37],"as":[38,101],"a":[39,48,66,113,159,181,213],"partially":[40],"observable":[41],"Markov":[42,152],"decision":[43,153],"process.":[44],"Existing":[45],"methods":[46],"lack":[47],"good":[49],"representation":[50],"historical":[52,117,129],"information,":[53],"making":[54],"it":[55],"very":[56],"challenging":[57],"to":[58,91,111,134,142,171,192],"find":[59],"an":[60],"optimal":[61,145],"policy.":[62],"paper":[64],"proposes":[65],"belief":[67,98,120],"state":[68,121],"separated":[69],"reinforcement":[70],"learning":[71,173],"(RL)":[72],"algorithm":[73,177],"for":[74,151],"decision-making":[75],"driving":[78,184,219],"in":[79,180],"uncertain":[80],"environments.":[81],"We":[82],"extend":[83],"separation":[85],"principle":[86],"from":[87,128],"linear":[88],"Gaussian":[89],"systems":[90],"general":[92],"nonlinear":[93],"stochastic":[94],"environments,":[95],"where":[96,186],"state,":[99,108],"defined":[100],"posterior":[103],"distribution":[104],"true":[107],"is":[109,122,132,163,178],"found":[110],"sufficient":[114],"statistic":[115],"information.":[118],"estimated":[123],"by":[124],"action-enhanced":[125],"variational":[126],"inference":[127],"information":[130],"proved":[133],"satisfy":[135],"Markovian":[137],"property,":[138],"thus":[139],"allowing":[140],"us":[141],"obtain":[143],"policy":[146,156],"using":[147],"traditional":[148],"RL":[149,206],"algorithms":[150],"processes.":[154],"The":[155,175,198],"gradient":[157],"task-specific":[160],"prior":[161],"model":[162],"mixed":[164],"with":[165,204,217],"that":[166,202],"interaction":[169],"data":[170],"improve":[172],"performance.":[174,220],"proposed":[176,209],"evaluated":[179],"multi-lane":[182],"task,":[185],"vehicles":[189],"subject":[191],"uncertainty":[194],"observation":[196],"noise.":[197],"simulation":[199],"results":[200],"show":[201],"compared":[203],"existing":[205],"algorithms,":[207],"method":[210],"achieve":[212],"higher":[214],"average":[215],"return":[216],"better":[218]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}