{"id":"https://openalex.org/W4398151096","doi":"https://doi.org/10.1109/tits.2024.3397700","title":"Safe Reinforcement Learning in Autonomous Driving With Epistemic Uncertainty Estimation","display_name":"Safe Reinforcement Learning in Autonomous Driving With Epistemic Uncertainty Estimation","publication_year":2024,"publication_date":"2024-05-20","ids":{"openalex":"https://openalex.org/W4398151096","doi":"https://doi.org/10.1109/tits.2024.3397700"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2024.3397700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3397700","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/A5012212325","display_name":"Zheng Zhang","orcid":"https://orcid.org/0009-0006-7173-9138"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-7173-9138","affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453159","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-7485-6344"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7485-6344","affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677178","display_name":"Yanjie Li","orcid":"https://orcid.org/0000-0001-7890-9677"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjie Li","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7890-9677","affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055451322","display_name":"Ke Lin","orcid":"https://orcid.org/0000-0002-3429-5877"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Lin","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3429-5877","affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101937754","display_name":"Linyu Li","orcid":"https://orcid.org/0009-0005-8626-0608"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linyu Li","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5012212325"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":5.8125,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96531584,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"25","issue":"10","first_page":"13653","last_page":"13666"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9297000169754028,"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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9297000169754028,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9007999897003174,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8096691370010376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4930855929851532},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48076245188713074},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.44468724727630615},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.44379156827926636},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4125324785709381},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32485610246658325},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3097611665725708},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2067750096321106},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11387607455253601},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.11276131868362427}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8096691370010376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4930855929851532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48076245188713074},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.44468724727630615},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.44379156827926636},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4125324785709381},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32485610246658325},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3097611665725708},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2067750096321106},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11387607455253601},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.11276131868362427}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2024.3397700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3397700","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":[],"awards":[{"id":"https://openalex.org/G1665521743","display_name":null,"funder_award_id":"61977019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1777445492","display_name":null,"funder_award_id":"JSGG20201103093802006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7007812877","display_name":null,"funder_award_id":"KJZD20230923114222045","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7386022970","display_name":null,"funder_award_id":"U1813206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7917848647","display_name":null,"funder_award_id":"JCYJ20220818102415033","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W594357522","https://openalex.org/W1518931405","https://openalex.org/W1845972764","https://openalex.org/W1971918058","https://openalex.org/W2071983464","https://openalex.org/W2094387729","https://openalex.org/W2165131254","https://openalex.org/W2170798819","https://openalex.org/W2462906003","https://openalex.org/W2736601468","https://openalex.org/W2804791273","https://openalex.org/W2904688694","https://openalex.org/W2953303875","https://openalex.org/W2956805085","https://openalex.org/W2962977206","https://openalex.org/W2963523627","https://openalex.org/W2963625099","https://openalex.org/W2970857152","https://openalex.org/W2991391803","https://openalex.org/W3014596384","https://openalex.org/W3035711539","https://openalex.org/W3090027660","https://openalex.org/W3102961490","https://openalex.org/W3119981760","https://openalex.org/W3127561923","https://openalex.org/W3134774296","https://openalex.org/W3162902207","https://openalex.org/W3164473225","https://openalex.org/W3165002413","https://openalex.org/W3197203826","https://openalex.org/W3203076355","https://openalex.org/W3203124669","https://openalex.org/W3203477356","https://openalex.org/W3209285784","https://openalex.org/W4237591687","https://openalex.org/W4250589301","https://openalex.org/W4285114615","https://openalex.org/W4286897021","https://openalex.org/W4293645819","https://openalex.org/W4296567640","https://openalex.org/W4301501993","https://openalex.org/W4378190882","https://openalex.org/W4390939851","https://openalex.org/W6683113397","https://openalex.org/W6684338915","https://openalex.org/W6687063787","https://openalex.org/W6718836005","https://openalex.org/W6728155968","https://openalex.org/W6730042731","https://openalex.org/W6735443497","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6751725685","https://openalex.org/W6761342191","https://openalex.org/W6773555910","https://openalex.org/W6774126978","https://openalex.org/W6795857475","https://openalex.org/W6801801719","https://openalex.org/W6803326663","https://openalex.org/W6843202480"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Safety":[0],"is":[1,70],"one":[2],"of":[3,36],"the":[4,8,15,34,37,81,111,121],"critical":[5],"challenges":[6],"in":[7],"autonomous":[9,65],"driving":[10],"task.":[11],"Recent":[12],"works":[13],"address":[14],"safety":[16,62,97],"by":[17,75,94],"implementing":[18],"a":[19,91,134],"safe":[20,54,73,126],"reinforcement":[21,55],"learning":[22],"(safe":[23],"RL)":[24],"mechanism.":[25],"However,":[26],"most":[27],"approaches":[28],"make":[29,133],"conservative":[30],"decisions":[31],"without":[32],"knowing":[33],"confidence":[35],"actions,":[38],"which":[39],"ultimately":[40],"causes":[41],"traffic":[42],"congestion":[43],"and":[44,61,88,140],"low":[45],"travel":[46],"efficiency.":[47],"This":[48],"paper":[49],"proposes":[50],"an":[51,102],"uncertainty-augmented":[52],"Lagrangian":[53],"algorithm":[56],"(Lag-U)":[57],"to":[58,85,89,105],"improve":[59],"exploration":[60,87],"performance":[63],"for":[64],"driving.":[66],"First,":[67],"epistemic":[68,83,113],"uncertainty":[69,84,114],"introduced":[71],"into":[72],"RL":[74,127],"using":[76],"deep":[77],"ensemble.":[78],"We":[79],"use":[80],"estimated":[82],"encourage":[86],"learn":[90],"risk-sensitive":[92],"policy":[93],"adaptively":[95],"modifying":[96],"constraints.":[98],"Second,":[99],"we":[100],"facilitate":[101],"intervention":[103],"assurance":[104],"choose":[106],"safer":[107],"actions":[108],"based":[109],"on":[110],"quantified":[112],"during":[115],"deployment.":[116],"Experimental":[117],"results":[118],"prove":[119],"that":[120],"proposed":[122],"method":[123],"outperforms":[124],"other":[125],"baselines.":[128],"The":[129],"trained":[130],"vehicle":[131],"can":[132],"decent":[135],"trade-off":[136],"between":[137],"high":[138],"efficiency":[139],"avoiding":[141],"risks,":[142],"thus":[143],"preventing":[144],"ultra-conservative":[145],"policy.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}