{"id":"https://openalex.org/W4416748475","doi":"https://doi.org/10.1109/iros60139.2025.11247057","title":"From Learning to Mastery: Achieving Safe and Efficient Real-World Autonomous Driving with Human-in-the-Loop Reinforcement Learning","display_name":"From Learning to Mastery: Achieving Safe and Efficient Real-World Autonomous Driving with Human-in-the-Loop Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748475","doi":"https://doi.org/10.1109/iros60139.2025.11247057"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247057","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/A5003483531","display_name":"Zeqiao Li","orcid":"https://orcid.org/0009-0002-5783-9790"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeqiao Li","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695050","display_name":"Yijing Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijing Wang","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427183","display_name":"Haoyu Wang","orcid":"https://orcid.org/0000-0002-4229-0347"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Wang","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102009618","display_name":"Zheng Li","orcid":"https://orcid.org/0000-0002-3895-3830"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Li","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086149037","display_name":"Peng Li","orcid":"https://orcid.org/0000-0003-4496-439X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Li","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101692387","display_name":"Wenfei Liu","orcid":"https://orcid.org/0000-0002-5079-8466"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfei Liu","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037713727","display_name":"Zhiqiang Zuo","orcid":"https://orcid.org/0000-0002-4566-7488"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Zuo","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System, School of Electrical and Information Engineering,Tianjin,China,300072","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.174888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7925","last_page":"7932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6965000033378601,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6965000033378601,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.1467999964952469,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.03840000182390213,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8413000106811523},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.487199991941452},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.486299991607666},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.4771000146865845},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4262000024318695},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.39879998564720154},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.39399999380111694},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8413000106811523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6906999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5192999839782715},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.487199991941452},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.4771000146865845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4399999976158142},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.39399999380111694},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3199000060558319},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3192000091075897},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247057","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/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null},{"id":"https://openalex.org/F4320335669","display_name":"Key Laboratory of System Control and Information Processing","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2174803659","https://openalex.org/W2736791111","https://openalex.org/W2837605352","https://openalex.org/W2909718913","https://openalex.org/W2951360122","https://openalex.org/W2964177756","https://openalex.org/W2966994213","https://openalex.org/W3003342008","https://openalex.org/W3015082424","https://openalex.org/W3044015199","https://openalex.org/W3088218629","https://openalex.org/W3090027660","https://openalex.org/W3121045039","https://openalex.org/W3127561923","https://openalex.org/W3130717831","https://openalex.org/W3157893055","https://openalex.org/W3203076355","https://openalex.org/W3207713159","https://openalex.org/W4286253093","https://openalex.org/W4401009784","https://openalex.org/W4402354084","https://openalex.org/W4406983280","https://openalex.org/W4413362511"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"driving":[1,145],"with":[2],"reinforcement":[3],"learning":[4,32,56,147,168],"(RL)":[5],"has":[6],"significant":[7],"potential.":[8],"However,":[9],"applying":[10],"RL":[11],"in":[12,82],"real-world":[13,83,144,157],"settings":[14],"remains":[15],"challenging":[16],"due":[17],"to":[18,76,111,125],"the":[19,31,89,98,128],"need":[20],"for":[21,169],"safe,":[22,164],"efficient,":[23],"and":[24,43,71,79,114,156,166,174],"robust":[25],"learning.":[26],"Incorporating":[27],"human":[28,104,119],"expertise":[29],"into":[30],"process":[33],"can":[34],"help":[35],"overcome":[36],"these":[37,123],"challenges":[38],"by":[39,106],"reducing":[40],"risky":[41],"exploration":[42],"improving":[44],"sample":[45],"efficiency.":[46],"In":[47],"this":[48],"work,":[49],"we":[50],"propose":[51],"a":[52,92,137],"reward-free,":[53],"active":[54],"human-in-the-loop":[55],"method":[57,65,142],"called":[58],"Human-Guided":[59],"Distributional":[60,72],"Soft":[61,73],"Actor-Critic":[62,74],"(H-DSAC).":[63],"Our":[64],"combines":[66],"Proxy":[67],"Value":[68],"Propagation":[69],"(PVP)":[70],"(DSAC)":[75],"enable":[77],"efficient":[78],"safe":[80],"training":[81,150],"environments.":[84],"The":[85,172],"key":[86],"innovation":[87],"is":[88,130],"construction":[90],"of":[91],"distributed":[93],"proxy":[94],"value":[95],"function":[96,102],"within":[97,148],"DSAC":[99],"framework.":[100],"This":[101],"encodes":[103],"intent":[105],"assigning":[107],"higher":[108],"expected":[109],"returns":[110],"expert":[112],"demonstrations":[113],"penalizing":[115],"actions":[116],"that":[117,160],"require":[118],"intervention.":[120],"By":[121],"extrapolating":[122],"labels":[124],"unlabeled":[126],"states,":[127],"policy":[129,146],"effectively":[131],"guided":[132],"toward":[133],"expert-like":[134],"be-havior.":[135],"With":[136],"well-designed":[138],"state":[139],"space,":[140],"our":[141,161],"achieves":[143],"practical":[149],"times.":[151],"Results":[152],"from":[153],"both":[154],"simulation":[155],"experiments":[158],"demonstrate":[159],"framework":[162],"enables":[163],"robust,":[165],"sample-efficient":[167],"autonomous":[170],"driving.":[171],"videos":[173],"code":[175],"are":[176],"available":[177],"at:":[178],"https://github.com/lzqw/H-DSAC.":[179]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}