{"id":"https://openalex.org/W7150806666","doi":"https://doi.org/10.1016/j.neucom.2026.133551","title":"From multi-view images to control: End-to-end autonomous driving via scene-representation-based reinforcement learning","display_name":"From multi-view images to control: End-to-end autonomous driving via scene-representation-based reinforcement learning","publication_year":2026,"publication_date":"2026-04-06","ids":{"openalex":"https://openalex.org/W7150806666","doi":"https://doi.org/10.1016/j.neucom.2026.133551"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2026.133551","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133551","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neucom.2026.133551","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133036723","display_name":"Jie Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158445","display_name":"Institute of Natural Science","ror":"https://ror.org/004tze884","country_code":"KP","type":"education","lineage":["https://openalex.org/I4210158445"]}],"countries":["KP"],"is_corresponding":false,"raw_author_name":"Jie Xia","raw_affiliation_strings":["Institute of Intelligent Vehicles, Shanghai Jiao Tong University, Shanghai, 200240, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-9160-3206","affiliations":[{"raw_affiliation_string":"Institute of Intelligent Vehicles, Shanghai Jiao Tong University, Shanghai, 200240, Shanghai, China","institution_ids":["https://openalex.org/I4210158445"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126497497","display_name":"Kexu Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131005","display_name":"Chery Automobile (China)","ror":"https://ror.org/02xab7z06","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210131005"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kexu Zhan","raw_affiliation_strings":["Chery Automobile Co., Ltd., Anhui, Wuhu, 241000, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chery Automobile Co., Ltd., Anhui, Wuhu, 241000, Anhui, China","institution_ids":["https://openalex.org/I4210131005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133047933","display_name":"Xiaodong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158445","display_name":"Institute of Natural Science","ror":"https://ror.org/004tze884","country_code":"KP","type":"education","lineage":["https://openalex.org/I4210158445"]}],"countries":["KP"],"is_corresponding":true,"raw_author_name":"Xiaodong Wu","raw_affiliation_strings":["Institute of Intelligent Vehicles, Shanghai Jiao Tong University, Shanghai, 200240, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0096-3830","affiliations":[{"raw_affiliation_string":"Institute of Intelligent Vehicles, Shanghai Jiao Tong University, Shanghai, 200240, Shanghai, China","institution_ids":["https://openalex.org/I4210158445"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127959298","display_name":"Yuanbo Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158445","display_name":"Institute of Natural Science","ror":"https://ror.org/004tze884","country_code":"KP","type":"education","lineage":["https://openalex.org/I4210158445"]}],"countries":["KP"],"is_corresponding":false,"raw_author_name":"Yuanbo Han","raw_affiliation_strings":["Institute of Intelligent Vehicles, Shanghai Jiao Tong University, Shanghai, 200240, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Vehicles, Shanghai Jiao Tong University, Shanghai, 200240, Shanghai, China","institution_ids":["https://openalex.org/I4210158445"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121540640","display_name":"Boran Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158445","display_name":"Institute of Natural Science","ror":"https://ror.org/004tze884","country_code":"KP","type":"education","lineage":["https://openalex.org/I4210158445"]}],"countries":["KP"],"is_corresponding":false,"raw_author_name":"Boran Shi","raw_affiliation_strings":["Institute of Intelligent Vehicles, Shanghai Jiao Tong University, Shanghai, 200240, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Vehicles, Shanghai Jiao Tong University, Shanghai, 200240, Shanghai, China","institution_ids":["https://openalex.org/I4210158445"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133010896","display_name":"Min Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Xu","raw_affiliation_strings":["School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5133047933"],"corresponding_institution_ids":["https://openalex.org/I4210158445"],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":{"value":2470,"currency":"USD","value_usd":2470},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3819844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"684","issue":null,"first_page":"133551","last_page":"133551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.27230000495910645,"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":0.27230000495910645,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.27160000801086426,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.039000000804662704,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6392999887466431},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2924000024795532},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.29159998893737793},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.27160000801086426},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.24719999730587006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705299973487854},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6392999887466431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6338000297546387},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5184999704360962},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.24719999730587006},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.24650000035762787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2026.133551","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133551","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.neucom.2026.133551","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133551","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G688862353","display_name":null,"funder_award_id":"52472413","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2107726111","https://openalex.org/W2209913494","https://openalex.org/W3011462663","https://openalex.org/W3017275226","https://openalex.org/W4386472819","https://openalex.org/W4386918877","https://openalex.org/W4401109681","https://openalex.org/W4401873149","https://openalex.org/W4405219754","https://openalex.org/W4414598626"],"related_works":[],"abstract_inverted_index":{"In":[0,209],"autonomous":[1],"driving,":[2],"efficiently":[3],"mapping":[4],"high-dimensional":[5],"perception":[6,54],"to":[7,144,178],"low-dimensional":[8],"actions":[9],"remains":[10,240],"a":[11,88,102,158,167],"key":[12],"challenge":[13],"for":[14,242],"end-to-end":[15,64],"(E2E)":[16,65],"policy":[17,138,152],"learning.":[18],"While":[19,238],"imitation":[20],"learning":[21,33,221],"(IL)":[22],"approaches":[23],"achieve":[24],"high":[25],"training":[26,169],"efficiency":[27,225,249],"but":[28],"exhibit":[29],"poor":[30],"generalization,":[31,39],"reinforcement":[32],"(RL)":[34],"methods,":[35],"despite":[36],"offering":[37],"better":[38],"typically":[40],"rely":[41],"on":[42,184,205,245,267],"pseudo":[43],"bird\u2019s":[44],"eye":[45],"view":[46],"(BEV)":[47],"features":[48,131],"and":[49,55,97,114,123,148,174,181,188,215,223,248,263,270],"lack":[50],"deep":[51],"integration":[52],"between":[53],"planning.":[56],"To":[57],"address":[58],"these":[59],"limitations,":[60],"we":[61],"propose":[62],"an":[63,135],"framework":[66],"that":[67,192],"unifies":[68],"structured":[69,103],"spatial":[70,84,130],"representation":[71,85,107],"with":[72,172,176],"planning,":[73],"where":[74],"the":[75,185,200,211,216,253,256],"planning":[76,141],"module":[77,86],"is":[78],"optimized":[79],"via":[80,126],"RL.":[81],"Our":[82],"entity-structured":[83,212],"builds":[87],"360":[89],"\u2218":[90],"surround-view":[91],"system":[92],"using":[93],"6":[94],"RGB":[95],"cameras":[96],"transforms":[98],"multi-view":[99],"images":[100],"into":[101,134],"BEV":[104],"representation.":[105],"This":[106],"encodes":[108],"static":[109],"road":[110],"elements,":[111],"dynamic":[112],"agents,":[113],"ego-vehicle":[115],"states":[116],"as":[117],"separate":[118,159],"tokens,":[119],"enabling":[120,230],"semantic":[121],"disentanglement":[122],"relational":[124],"reasoning":[125],"attention":[127],"mechanisms.":[128],"The":[129],"are":[132],"input":[133],"enhanced":[136],"proximal":[137],"optimization":[139],"(PPO)":[140],"module,":[142],"designed":[143],"improve":[145,220],"both":[146],"exploration":[147,224],"stability.":[149],"A":[150],"lightweight":[151],"network":[153,161],"generates":[154],"control":[155],"commands,":[156],"while":[157],"value":[160],"estimates":[162],"state":[163],"values.":[164],"We":[165],"adopt":[166],"hybrid":[168],"paradigm,":[170],"pretraining":[171],"IL":[173],"fine-tuning":[175],"RL":[177],"enhance":[179],"generalization":[180],"robustness.":[182],"Evaluations":[183],"CARLA":[186],"simulator":[187,207],"Bench2Drive":[189],"benchmark":[190],"indicate":[191],"our":[193,259],"method":[194],"achieves":[195],"competitive":[196],"closed-loop":[197],"performance":[198],"under":[199],"image-to-control":[201],"setting":[202],"without":[203],"relying":[204],"privileged":[206],"states.":[208],"particular,":[210],"token":[213],"interface":[214],"stabilized":[217],"PPO":[218],"objective":[219],"stability":[222],"in":[226,250],"highly":[227],"interactive":[228],"scenarios,":[229],"robust":[231],"decision":[232],"making":[233],"across":[234],"diverse":[235],"driving":[236],"tasks.":[237],"there":[239],"room":[241],"further":[243],"improvement":[244],"overall":[246],"success":[247],"challenging":[251],"routes,":[252],"results":[254],"support":[255],"effectiveness":[257],"of":[258],"unified":[260],"perception-to-planning":[261],"design,":[262],"motivate":[264],"future":[265],"work":[266],"sim-to-real":[268],"transfer":[269],"on-road":[271],"validation.":[272]},"counts_by_year":[],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2026-04-07T00:00:00"}