{"id":"https://openalex.org/W4416748391","doi":"https://doi.org/10.1109/iros60139.2025.11246116","title":"DRARL: Disengagement-Reason-Augmented Reinforcement Learning for Efficient Improvement of Autonomous Driving Policy","display_name":"DRARL: Disengagement-Reason-Augmented Reinforcement Learning for Efficient Improvement of Autonomous Driving Policy","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748391","doi":"https://doi.org/10.1109/iros60139.2025.11246116"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5050020266","display_name":"Weitao Zhou","orcid":"https://orcid.org/0000-0002-1266-3843"},"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":"Weitao Zhou","raw_affiliation_strings":["Tsinghua University,School of Vehicle and Mobility"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Vehicle and Mobility","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100335202","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0001-8052-782X"},"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":"Bo Zhang","raw_affiliation_strings":["Tsinghua University,School of Vehicle and Mobility"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Vehicle and Mobility","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016651437","display_name":"Zhong Cao","orcid":"https://orcid.org/0000-0002-2243-5705"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong Cao","raw_affiliation_strings":["University of Michigan,Department of Civil and Environmental Engineering"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Civil and Environmental Engineering","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101959718","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0003-3437-9568"},"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":"Xiang Li","raw_affiliation_strings":["Tsinghua University,Lab for High Technology"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Lab for High Technology","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101914017","display_name":"Cheng Qian","orcid":"https://orcid.org/0009-0005-2822-6321"},"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":"Qian Cheng","raw_affiliation_strings":["Tsinghua University,School of Vehicle and Mobility"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Vehicle and Mobility","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011341171","display_name":"Chunyang Liu","orcid":"https://orcid.org/0000-0002-0115-4592"},"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":"Chunyang Liu","raw_affiliation_strings":["Tsinghua University,School of Vehicle and Mobility"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Vehicle and Mobility","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663312","display_name":"Ya-Qin Zhang","orcid":null},"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":"Yaqin Zhang","raw_affiliation_strings":["Tsinghua University,Institute for AI Industry Research"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for AI Industry Research","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","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":["Tsinghua University,School of Vehicle and Mobility"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Vehicle and Mobility","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5050020266"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38951033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"604","last_page":"611"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.429500013589859,"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":0.429500013589859,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4120999872684479,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.02759999968111515,"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/disengagement-theory","display_name":"Disengagement theory","score":0.9674000144004822},{"id":"https://openalex.org/keywords/casual","display_name":"Casual","score":0.6565999984741211},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5414999723434448},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5299000144004822},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.5181000232696533},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4325999915599823}],"concepts":[{"id":"https://openalex.org/C25740722","wikidata":"https://www.wikidata.org/wiki/Q3044915","display_name":"Disengagement theory","level":2,"score":0.9674000144004822},{"id":"https://openalex.org/C2781426162","wikidata":"https://www.wikidata.org/wiki/Q2275793","display_name":"Casual","level":2,"score":0.6565999984741211},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5414999723434448},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.5181000232696533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4609000086784363},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3409000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33709999918937683},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28679999709129333},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.28610000014305115},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27619999647140503},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C109986646","wikidata":"https://www.wikidata.org/wiki/Q546113","display_name":"Public policy","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.26829999685287476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.263700008392334},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.26269999146461487},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1965455100","https://openalex.org/W1972060013","https://openalex.org/W2021096542","https://openalex.org/W2056877664","https://openalex.org/W2100488636","https://openalex.org/W2118020555","https://openalex.org/W2504001346","https://openalex.org/W2784675945","https://openalex.org/W2805093171","https://openalex.org/W2963737762","https://openalex.org/W2967549667","https://openalex.org/W3116651890","https://openalex.org/W3121012756","https://openalex.org/W3129292912","https://openalex.org/W3141426068","https://openalex.org/W3178012085","https://openalex.org/W3181350748","https://openalex.org/W3207915602","https://openalex.org/W4281392159","https://openalex.org/W4285145842","https://openalex.org/W4285278949","https://openalex.org/W4312803983","https://openalex.org/W4321611535","https://openalex.org/W4366308958","https://openalex.org/W4415797755"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,34,57,64,70,96,102,116,120,137,148,174,182,196,199],"increasing":[2],"presence":[3],"of":[4,37,66,98,104,151],"automated":[5],"vehicles":[6],"on":[7],"open":[8],"roads":[9],"under":[10,142],"driver":[11,71],"supervision,":[12],"disengagement":[13,29,38,51,58,99,105,128,152,163,179,221],"cases":[14,30,153,164,191],"are":[15],"becoming":[16,202],"more":[17],"prevalent.":[18],"While":[19],"some":[20,50],"data-driven":[21],"planning":[22],"systems":[23],"attempt":[24],"to":[25,95,184,215],"directly":[26],"utilize":[27],"these":[28],"for":[31,75],"policy":[32,91,134,138,149,206,218],"improvement,":[33],"inherent":[35],"scarcity":[36],"data":[39,52],"(often":[40],"occurring":[41],"as":[42,125],"a":[43,76,126,143],"single":[44],"instance)":[45],"restricts":[46],"training":[47],"effectiveness.":[48],"Furthermore,":[49,195],"should":[53],"be":[54,123,140],"excluded":[55],"since":[56],"may":[59,72],"not":[60],"always":[61],"come":[62],"from":[63,201],"failure":[65],"driving":[67,90,168,217],"policies,":[68],"e.g.":[69],"casually":[73],"intervene":[74],"while.":[77],"To":[78],"this":[79,81,209],"end,":[80],"work":[82,210],"proposes":[83],"disengagement-reason-augmented":[84],"reinforcement":[85],"learning":[86],"(DRARL),":[87],"which":[88,130],"enhances":[89],"improvement":[92],"process":[93],"according":[94],"reason":[97,103,117],"cases.":[100,222],"Specifically,":[101],"is":[106,159],"identified":[107,124],"by":[108,166],"an":[109,212],"out-of-distribution":[110],"(OOD)":[111],"state":[112],"estimation":[113],"model.":[114],"When":[115],"doesn\u2019t":[118,131],"exist,":[119],"case":[121],"will":[122],"casual":[127],"case,":[129],"require":[132],"additional":[133],"adjustment.":[135],"Otherwise,":[136],"can":[139],"updated":[141],"reason-augmented":[144,193],"imagination":[145],"environment,":[146],"improving":[147],"performance":[150,219],"with":[154,220],"similar":[155,190],"reasons.":[156],"The":[157],"method":[158,175],"evaluated":[160],"using":[161],"real-world":[162],"collected":[165],"autonomous":[167],"robotaxi.":[169],"Experimental":[170],"results":[171],"demonstrate":[172],"that":[173],"accurately":[176],"identifies":[177],"policy-related":[178],"reasons,":[180],"allowing":[181],"agent":[183,200],"handle":[185],"both":[186],"original":[187],"and":[188],"semantically":[189],"through":[192],"training.":[194],"approach":[197],"prevents":[198],"overly":[203],"conservative":[204],"after":[205],"adjustments.":[207],"Overall,":[208],"provides":[211],"efficient":[213],"way":[214],"improve":[216]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}