{"id":"https://openalex.org/W3141426068","doi":"https://doi.org/10.1109/tits.2021.3069497","title":"Confidence-Aware Reinforcement Learning for Self-Driving Cars","display_name":"Confidence-Aware Reinforcement Learning for Self-Driving Cars","publication_year":2021,"publication_date":"2021-04-06","ids":{"openalex":"https://openalex.org/W3141426068","doi":"https://doi.org/10.1109/tits.2021.3069497","mag":"3141426068"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2021.3069497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2021.3069497","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation 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/A5016651437","display_name":"Zhong Cao","orcid":"https://orcid.org/0000-0002-2243-5705"},"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":"Zhong Cao","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2243-5705","affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011184498","display_name":"Shaobing Xu","orcid":"https://orcid.org/0000-0002-4127-2411"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaobing Xu","raw_affiliation_strings":["Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0000-0002-4127-2411","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056009561","display_name":"Huei Peng","orcid":"https://orcid.org/0000-0002-7684-1696"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huei Peng","raw_affiliation_strings":["Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0000-0002-7684-1696","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009072257","display_name":"Diange Yang","orcid":"https://orcid.org/0000-0003-0825-5609"},"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":"Diange Yang","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0825-5609","affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065428032","display_name":"Robert A. E. Zidek","orcid":null},"institutions":[{"id":"https://openalex.org/I4391768151","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4391768151"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Zidek","raw_affiliation_strings":["Toyota Research Institute, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Research Institute, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I4391768151"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1142,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.95937476,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"23","issue":"7","first_page":"7419","last_page":"7430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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/T12095","display_name":"Vehicle emissions and performance","score":0.989799976348877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9211961030960083},{"id":"https://openalex.org/keywords/roundabout","display_name":"Roundabout","score":0.741595447063446},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6883344054222107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6408553719520569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.525931179523468},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5137330293655396},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46703195571899414},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44316360354423523},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20528018474578857},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.1488780975341797},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.09438586235046387},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.07642799615859985}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9211961030960083},{"id":"https://openalex.org/C109157449","wikidata":"https://www.wikidata.org/wiki/Q7371221","display_name":"Roundabout","level":2,"score":0.741595447063446},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6883344054222107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6408553719520569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.525931179523468},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5137330293655396},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46703195571899414},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44316360354423523},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20528018474578857},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.1488780975341797},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.09438586235046387},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.07642799615859985},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/tits.2021.3069497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2021.3069497","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W1965455100","https://openalex.org/W2056877664","https://openalex.org/W2525936901","https://openalex.org/W2589869525","https://openalex.org/W2594201198","https://openalex.org/W2604382266","https://openalex.org/W2798786289","https://openalex.org/W2894873440","https://openalex.org/W2904450917","https://openalex.org/W2909906617","https://openalex.org/W2913416895","https://openalex.org/W2972435663","https://openalex.org/W2991448601","https://openalex.org/W2997027240","https://openalex.org/W3000193750","https://openalex.org/W3005458448","https://openalex.org/W3113555494","https://openalex.org/W3121012756","https://openalex.org/W3148740559","https://openalex.org/W4214717370","https://openalex.org/W6640490175","https://openalex.org/W6718092244","https://openalex.org/W6745935785","https://openalex.org/W6752894541","https://openalex.org/W6753596642","https://openalex.org/W6784624102","https://openalex.org/W6785060721"],"related_works":["https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W4381573898","https://openalex.org/W4306674287","https://openalex.org/W2909304650","https://openalex.org/W4319083788"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"can":[3],"be":[4],"used":[5,155],"to":[6,48,75,92,99,134],"design":[7],"smart":[8],"driving":[9,62],"policies":[10],"in":[11,23,33,119,149],"complex":[12],"situations":[13],"where":[14,35],"traditional":[15],"methods":[16],"cannot.":[17],"However,":[18],"they":[19],"are":[20,39],"frequently":[21],"black-box":[22],"nature,":[24],"and":[25,64,79,140,146,172],"the":[26,66,71,81,84,107,115,120,137,141,157,164,168,173],"resulting":[27],"policy":[28,86,98,108,139,143,171],"may":[29],"perform":[30],"poorly,":[31],"including":[32],"scenarios":[34],"few":[36],"training":[37,121],"cases":[38],"available.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"propose":[45],"a":[46,59,94,150],"method":[47,73,166],"use":[49,93],"RL":[50,55,67,85,97,138,170],"under":[51],"two":[52],"conditions:":[53],"(i)":[54],"works":[56],"together":[57],"with":[58],"baseline":[60,142,174],"rule-based":[61,72,175],"policy;":[63],"(ii)":[65],"intervenes":[68],"only":[69],"when":[70,80],"seems":[74],"have":[76],"difficulty":[77],"handling":[78],"confidence":[82,105],"of":[83,106],"is":[87,91,109,126,144,154],"high.":[88],"Our":[89],"motivation":[90],"not-well":[95],"trained":[96],"reliably":[100],"improve":[101],"AV":[102],"performance.":[103],"The":[104,123,132],"evaluated":[110],"by":[111],"Lindeberg-Levy":[112],"Theorem":[113],"using":[114],"recorded":[116],"data":[117],"distribution":[118],"process.":[122],"overall":[124],"framework":[125],"named":[127],"\u201cconfidence-aware":[128],"reinforcement":[129],"learning\u201d":[130],"(CARL).":[131],"condition":[133],"switch":[135],"between":[136],"analyzed":[145],"presented.":[147],"Driving":[148],"two-lane":[151],"roundabout":[152],"scenario":[153],"as":[156],"application":[158],"case":[159],"study.":[160],"Simulation":[161],"results":[162],"show":[163],"proposed":[165],"outperforms":[167],"pure":[169],"policy.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}