{"id":"https://openalex.org/W7117501107","doi":"https://doi.org/10.1109/mra.2025.3639812","title":"Vision-Based Policy Learning for High-Speed Autonomous Racing: A Two-Phase Learning Paradigm","display_name":"Vision-Based Policy Learning for High-Speed Autonomous Racing: A Two-Phase Learning Paradigm","publication_year":2025,"publication_date":"2025-12-29","ids":{"openalex":"https://openalex.org/W7117501107","doi":"https://doi.org/10.1109/mra.2025.3639812"},"language":null,"primary_location":{"id":"doi:10.1109/mra.2025.3639812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mra.2025.3639812","pdf_url":null,"source":{"id":"https://openalex.org/S132261465","display_name":"IEEE Robotics & Automation Magazine","issn_l":"1070-9932","issn":["1070-9932","1558-223X"],"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 & Automation Magazine","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/A5121442828","display_name":"Haoran Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Xu","raw_affiliation_strings":["College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0003-3107-7852","affiliations":[{"raw_affiliation_string":"College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121516803","display_name":"Xianwei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianwei Chen","raw_affiliation_strings":["College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0004-6783-1463","affiliations":[{"raw_affiliation_string":"College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050210424","display_name":"Yilin Lang","orcid":"https://orcid.org/0000-0002-9381-9888"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilin Lang","raw_affiliation_strings":["College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-9381-9888","affiliations":[{"raw_affiliation_string":"College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100030100","display_name":"Qinyuan Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinyuan Ren","raw_affiliation_strings":["College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-9487-2675","affiliations":[{"raw_affiliation_string":"College of Control Science and Engineering, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74624926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"1","first_page":"101","last_page":"114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4706999957561493,"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":0.4706999957561493,"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":0.2434999942779541,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0771000012755394,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.8091999888420105},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.7361000180244446},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6205999851226807},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5874999761581421},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5209000110626221},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.5175999999046326},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4681999981403351},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4203000068664551},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.40880000591278076}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8091999888420105},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.7361000180244446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6557999849319458},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6205999851226807},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5874999761581421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343999862670898},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5209000110626221},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.5175999999046326},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4681999981403351},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38100001215934753},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.376800000667572},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.3668999969959259},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3343999981880188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3327000141143799},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.29809999465942383},{"id":"https://openalex.org/C2780368719","wikidata":"https://www.wikidata.org/wiki/Q5157342","display_name":"Computational thinking","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mra.2025.3639812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mra.2025.3639812","pdf_url":null,"source":{"id":"https://openalex.org/S132261465","display_name":"IEEE Robotics & Automation Magazine","issn_l":"1070-9932","issn":["1070-9932","1558-223X"],"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 & Automation Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.42054417729377747,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5219052750","display_name":null,"funder_award_id":"ICT2025A17","funder_id":"https://openalex.org/F4320326952","funder_display_name":"State Key Laboratory of Industrial Control Technology"}],"funders":[{"id":"https://openalex.org/F4320326952","display_name":"State Key Laboratory of Industrial Control Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Motion":[0],"planning":[1],"for":[2,39,132],"autonomous":[3,41],"vision-based":[4,89,157],"car":[5],"racing":[6,14,61,90,138,158],"is":[7,56,81,134,163],"a":[8,77,88,95,122,170],"challenging":[9,57],"task":[10,18],"in":[11,83,105,156,165],"robotics.":[12],"Classical":[13],"systems":[15],"divide":[16],"the":[17,65,71,106,115,141,166,177],"into":[19],"numerous":[20],"submodules,":[21],"undermining":[22],"computational":[23],"efficiency":[24],"and":[25,54,109,153,168,182],"leading":[26],"to":[27,58,64,86,117],"error":[28],"propagation.":[29],"Previous":[30],"studies":[31],"have":[32],"demonstrated":[33],"impressive":[34],"reinforcement":[35],"learning":[36,79],"(RL)":[37],"results":[38],"end-to-end":[40],"driving.":[42],"However,":[43],"RL":[44,93],"exhibits":[45],"poor":[46],"scalability":[47],"on":[48,127,169],"high-dimensional":[49],"data,":[50],"such":[51],"as":[52],"images,":[53],"it":[55],"learn":[59],"optimal":[60],"behaviors":[62],"due":[63],"lack":[66],"of":[67],"global":[68],"information":[69,112],"about":[70,114],"environments.":[72],"To":[73],"address":[74],"these":[75],"issues,":[76],"two-phase":[78],"paradigm":[80],"proposed":[82,161],"this":[84],"work":[85],"train":[87],"policy.":[91,143],"First,":[92],"trains":[94],"teacher":[96,142],"policy":[97,146],"that":[98,176],"integrates":[99],"progress":[100],"maximization":[101],"with":[102],"collision":[103],"avoidance":[104],"reward":[107],"function":[108],"utilizes":[110],"privileged":[111],"(P.I.)":[113],"racetrack":[116],"achieve":[118],"high-performance":[119],"racing.":[120],"Then,":[121],"student":[123,145],"policy,":[124],"relying":[125],"only":[126],"an":[128],"ego-centric":[129],"depth":[130],"camera":[131],"perception,":[133],"trained":[135],"by":[136],"distilling":[137],"knowledge":[139],"from":[140],"The":[144,160],"achieves":[147],"high-speed":[148],"drive,":[149],"high":[150],"success":[151],"rate,":[152],"smooth":[154],"control":[155],"games.":[159],"approach":[162,178],"validated":[164],"simulation":[167],"real-world":[171],"1/10-scale":[172],"race":[173],"car,":[174],"showing":[175],"outperforms":[179],"previous":[180],"model-based":[181],"learning-based":[183],"baselines.":[184]},"counts_by_year":[],"updated_date":"2026-03-26T06:05:38.182114","created_date":"2025-12-29T00:00:00"}