{"id":"https://openalex.org/W4416750936","doi":"https://doi.org/10.1109/iros60139.2025.11247462","title":"Continuously Improved Reinforcement Learning for Automated Driving","display_name":"Continuously Improved Reinforcement Learning for Automated Driving","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750936","doi":"https://doi.org/10.1109/iros60139.2025.11247462"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247462","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":"conference-paper","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/A5077213298","display_name":"Xuerun Yan","orcid":"https://orcid.org/0009-0000-1515-4019"},"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":"Xuerun Yan","raw_affiliation_strings":["Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035368905","display_name":"Zhexi Lian","orcid":"https://orcid.org/0000-0002-6920-5114"},"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":"Zhexi Lian","raw_affiliation_strings":["Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031111706","display_name":"Jia Hu","orcid":"https://orcid.org/0000-0002-0900-7992"},"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":"Jia Hu","raw_affiliation_strings":["Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003836390","display_name":"Yongwei Feng","orcid":"https://orcid.org/0009-0001-4711-3067"},"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":"Yongwei Feng","raw_affiliation_strings":["Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103052909","display_name":"Binyang Song","orcid":"https://orcid.org/0000-0002-0322-796X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Binyang Song","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102813363","display_name":"Haoran Wang","orcid":"https://orcid.org/0000-0002-6098-4772"},"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":"Haoran Wang","raw_affiliation_strings":["Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15268","last_page":"15275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.5472000241279602,"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":0.5472000241279602,"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":0.15489999949932098,"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":0.07850000262260437,"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":0.8526999950408936},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.7664999961853027},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.5468999743461609},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.435699999332428},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4187000095844269},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.31520000100135803}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8526999950408936},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.7664999961853027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6244000196456909},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4927999973297119},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4050999879837036},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25839999318122864},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2574000060558319},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247462","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/F4320307110","display_name":"Delta","ror":"https://ror.org/03g9c1e75"},{"id":"https://openalex.org/F4320318553","display_name":"Shanghai Automotive Industry Science and Technology Development Foundation","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W79330797","https://openalex.org/W2015731569","https://openalex.org/W2056877664","https://openalex.org/W2525936901","https://openalex.org/W2951360122","https://openalex.org/W2973229164","https://openalex.org/W2980161450","https://openalex.org/W2991448601","https://openalex.org/W3141426068","https://openalex.org/W3168892396","https://openalex.org/W4206497039","https://openalex.org/W4210444794","https://openalex.org/W4226286144","https://openalex.org/W4319449817","https://openalex.org/W4321611535","https://openalex.org/W4375796951","https://openalex.org/W4381733133","https://openalex.org/W4386412395","https://openalex.org/W4388936582","https://openalex.org/W4395069646","https://openalex.org/W4396599460","https://openalex.org/W4398194910","https://openalex.org/W4399432412","https://openalex.org/W4399527493"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0,46],"Learning":[1],"(RL)":[2],"offers":[3],"a":[4,41,63],"promising":[5],"solution":[6],"to":[7,26,32,51,134],"enable":[8],"evolutionary":[9],"automated":[10,57,93],"driving.":[11,58],"However,":[12],"conventional":[13,136],"RL":[14,65],"methods":[15],"often":[16],"struggle":[17],"with":[18,95,105],"risk":[19],"performance,":[20],"as":[21],"updated":[22],"policies":[23],"may":[24],"fail":[25],"enhance":[27],"performance":[28,80,98],"or":[29],"even":[30],"lead":[31],"deterioration.":[33],"To":[34],"address":[35],"this":[36,38],"challenge,":[37],"research":[39],"introduces":[40],"High":[42],"Confidence":[43],"Policy":[44],"Improvement":[45],"Learning-based":[47],"(HCPI-RL)":[48],"planner,":[49],"designed":[50],"achieve":[52],"the":[53,83,88,115,135],"monotonic":[54,79,97],"evolution":[55],"of":[56,102],"The":[59],"HCPI-RL":[60,85,117],"planner":[61,86,118],"features":[62],"novel":[64],"policy":[66,74,120],"update":[67],"paradigm,":[68],"ensuring":[69],"that":[70,114],"each":[71],"newly":[72],"learned":[73],"outperforms":[75],"previous":[76],"policies,":[77],"achieving":[78],"enhancement.":[81],"Hence,":[82],"proposed":[84,116],"has":[87],"following":[89],"features:":[90],"i)":[91],"Evolutionary":[92],"driving":[94,127],"guaranteed":[96],"enhancement;":[99],"ii)":[100],"Capability":[101],"handling":[103],"scenarios":[104],"emergency;":[106],"iii)":[107],"Enhanced":[108],"decision-making":[109],"optimality.":[110],"Experimental":[111],"results":[112],"demonstrate":[113],"enhances":[119],"return":[121],"by":[122,129],"at":[123,130],"least":[124,131],"20.1%":[125],"and":[126],"efficiency":[128],"15.6%,":[132],"compared":[133],"RL-based":[137],"planners.":[138]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}