{"id":"https://openalex.org/W4417438696","doi":"https://doi.org/10.1109/lra.2025.3645525","title":"Online Policy Adaptation for Personalized Lane-Keeping via Driver Intervention Guided Reinforcement Learning","display_name":"Online Policy Adaptation for Personalized Lane-Keeping via Driver Intervention Guided Reinforcement Learning","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W4417438696","doi":"https://doi.org/10.1109/lra.2025.3645525"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2025.3645525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3645525","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5103192109","display_name":"J. C. S. Yang","orcid":"https://orcid.org/0009-0000-8198-132X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaxin Yang","raw_affiliation_strings":["School of Automotive Studies, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118899943","display_name":"Hui Chen","orcid":"https://orcid.org/0000-0002-5783-1716"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Chen","raw_affiliation_strings":["School of Automotive Studies, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111339722","display_name":"Shaoka Su","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoka Su","raw_affiliation_strings":["School of Automotive Studies, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053468308","display_name":"Chaopeng Guo","orcid":"https://orcid.org/0000-0001-5022-5919"},"institutions":[{"id":"https://openalex.org/I4210097564","display_name":"JTEKT (Japan)","ror":"https://ror.org/00w91z143","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210097564"]},{"id":"https://openalex.org/I910227697","display_name":"JTEKT (France)","ror":"https://ror.org/04n3fbh55","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210097564","https://openalex.org/I910227697"]}],"countries":["FR","JP"],"is_corresponding":false,"raw_author_name":"Chaopeng Guo","raw_affiliation_strings":["Development Department, JTEKT Corporation, Kariya, Japan","Development Department, JTEKT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Development Department, JTEKT Corporation, Kariya, Japan","institution_ids":["https://openalex.org/I4210097564"]},{"raw_affiliation_string":"Development Department, JTEKT Corporation, Japan","institution_ids":["https://openalex.org/I4210097564","https://openalex.org/I910227697"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104123679","display_name":"Youyu Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I2799321762","display_name":"WuXi AppTec (China)","ror":"https://ror.org/04eh3ca90","country_code":"CN","type":"company","lineage":["https://openalex.org/I2799321762"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youyu Yin","raw_affiliation_strings":["JTEKT Research and Development Center (Wuxi) Company, Ltd., Wuxi, China","JTEKT Research and Development Center (Wuxi) Co., Ltd., Wuxi, China"],"affiliations":[{"raw_affiliation_string":"JTEKT Research and Development Center (Wuxi) Company, Ltd., Wuxi, China","institution_ids":["https://openalex.org/I2799321762"]},{"raw_affiliation_string":"JTEKT Research and Development Center (Wuxi) Co., Ltd., Wuxi, China","institution_ids":["https://openalex.org/I2799321762"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103192109"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43608714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"2","first_page":"1898","last_page":"1905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.5839999914169312,"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":0.5839999914169312,"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":0.05790000036358833,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.051100000739097595,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7752000093460083},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.6383000016212463},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.5857999920845032},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5746999979019165},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5740000009536743},{"id":"https://openalex.org/keywords/intervention","display_name":"Intervention (counseling)","score":0.4235000014305115},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.41200000047683716},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.3747999966144562},{"id":"https://openalex.org/keywords/driving-simulator","display_name":"Driving simulator","score":0.35510000586509705}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7752000093460083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6416000127792358},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.6383000016212463},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.5857999920845032},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5746999979019165},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5740000009536743},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4056999981403351},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.367000013589859},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35519999265670776},{"id":"https://openalex.org/C2780689630","wikidata":"https://www.wikidata.org/wiki/Q2081815","display_name":"Driving simulator","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.31540000438690186},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3645525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3645525","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1667312704","https://openalex.org/W2107338474","https://openalex.org/W2963588172","https://openalex.org/W2991431362","https://openalex.org/W2994918793","https://openalex.org/W3022220688","https://openalex.org/W3082508441","https://openalex.org/W3111019965","https://openalex.org/W3121045039","https://openalex.org/W3127557877","https://openalex.org/W3134002512","https://openalex.org/W4285027812","https://openalex.org/W4285125144","https://openalex.org/W4286253093","https://openalex.org/W4379055788","https://openalex.org/W4397040233","https://openalex.org/W4400447773","https://openalex.org/W4400524848","https://openalex.org/W4401386967","https://openalex.org/W4401717567","https://openalex.org/W4406457544","https://openalex.org/W4407951205","https://openalex.org/W4408017261","https://openalex.org/W4413917648"],"related_works":[],"abstract_inverted_index":{"Learning-based":[0],"online":[1,89],"adaptive":[2],"driving":[3,12,75,218],"policies":[4,219],"hold":[5],"considerable":[6],"promise":[7],"for":[8],"enabling":[9,87],"human-preferred":[10],"autonomous":[11],"or":[13,28],"advanced":[14],"driver":[15,56,116],"assistance":[16],"systems.":[17],"However,":[18],"existing":[19],"personalization":[20],"approaches":[21],"often":[22],"rely":[23],"on":[24,38,54,62,112,204],"limited":[25],"style":[26],"definitions":[27],"behavior":[29],"cloning,":[30],"requiring":[31],"extensive":[32],"data":[33],"and":[34,66,94,131,141,173,210],"placing":[35],"cognitive":[36],"burdens":[37],"users.":[39],"To":[40,91],"address":[41],"these":[42],"limitations,":[43],"an":[44],"Online":[45],"Personalized":[46],"Policy":[47],"Adaptation":[48],"(OPPA)":[49],"framework":[50,119,170,215],"is":[51,108,120],"proposed":[52,169],"based":[53,111],"direct":[55],"interventions,":[57],"where":[58],"real-time":[59],"corrective":[60],"actions":[61],"the":[63,101,128,160,163,168,189,208,213],"steering":[64],"wheel":[65],"pedals":[67],"are":[68,148],"treated":[69],"as":[70],"implicit":[71],"feedback":[72],"reflecting":[73],"individual":[74,221],"preferences.":[76,117,222],"A":[77],"hybrid":[78],"learning":[79,83],"strategy":[80],"integrates":[81],"reinforcement":[82],"with":[84,150,220],"intervention-guided":[85],"updates,":[86],"efficient":[88],"adaptation.":[90],"mitigate":[92],"overfitting":[93],"prevent":[95],"catastrophic":[96],"forgetting":[97],"during":[98],"long-term":[99],"personalization,":[100,175],"Memory":[102],"Aware":[103],"Synapses":[104],"(MAS)":[105],"regularization":[106],"technique":[107],"selectively":[109],"activated":[110],"detected":[113],"shifts":[114],"in":[115,216],"The":[118,191],"initialized":[121],"from":[122,198],"a":[123,132],"generalized":[124],"policy":[125],"pretrained":[126],"using":[127],"TD3":[129],"algorithm":[130],"composite":[133],"reward":[134],"function":[135],"that":[136,167],"captures":[137],"perceived":[138],"risk,":[139],"comfort,":[140],"efficiency.":[142],"Driver-in-the-loop":[143],"experiments":[144],"incorporating":[145],"subjective":[146],"evaluations":[147],"conducted":[149],"21":[151],"drivers":[152],"across":[153],"four":[154],"representative":[155],"curved-lane":[156],"scenarios":[157],"to":[158,200],"assess":[159],"effectiveness":[161,209],"of":[162,212],"personalization.":[164],"Results":[165],"demonstrate":[166],"achieves":[171],"rapid":[172],"effective":[174],"typically":[176],"needing":[177],"fewer":[178],"than":[179],"two":[180],"intervention":[181,196],"episodes.":[182],"Subjective":[183],"satisfaction":[184],"improves":[185],"by":[186],"18.9%":[187],"over":[188],"baseline.":[190],"average":[192],"adaptation":[193],"time":[194],"per":[195],"ranges":[197],"0.75":[199],"1.04":[201],"seconds,":[202],"depending":[203],"MAS":[205],"activation,":[206],"confirming":[207],"responsiveness":[211],"OPPA":[214],"aligning":[217]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-17T00:00:00"}