{"id":"https://openalex.org/W4415309316","doi":"https://doi.org/10.1109/iccv51701.2025.02579","title":"ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving","display_name":"ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415309316","doi":"https://doi.org/10.1109/iccv51701.2025.02579"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.12499","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120047357","display_name":"Yuhang Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhang Lu","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120047358","display_name":"Jiadong Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiadong Tu","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120047359","display_name":"Yuexin Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexin Ma","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xinge Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xinge Zhu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5120047357"],"corresponding_institution_ids":["https://openalex.org/I30809798"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29870097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27783","last_page":"27793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9519000053405762,"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":0.9519000053405762,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9363999962806702,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9063000082969666,"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/process","display_name":"Process (computing)","score":0.5752999782562256},{"id":"https://openalex.org/keywords/situation-awareness","display_name":"Situation awareness","score":0.5737000107765198},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5412999987602234},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5401999950408936},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46549999713897705},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4237000048160553},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.39559999108314514},{"id":"https://openalex.org/keywords/situation-analysis","display_name":"Situation analysis","score":0.32589998841285706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6459000110626221},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5752999782562256},{"id":"https://openalex.org/C145804949","wikidata":"https://www.wikidata.org/wiki/Q478123","display_name":"Situation awareness","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5412999987602234},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.52920001745224},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3393999934196472},{"id":"https://openalex.org/C14911803","wikidata":"https://www.wikidata.org/wiki/Q7532148","display_name":"Situation analysis","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.29019999504089355},{"id":"https://openalex.org/C9114305","wikidata":"https://www.wikidata.org/wiki/Q1428317","display_name":"Situational ethics","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C9628104","wikidata":"https://www.wikidata.org/wiki/Q788009","display_name":"Autonomous system (mathematics)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.12499","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12499","pdf_url":"https://arxiv.org/pdf/2507.12499","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.12499","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.12499","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.12499","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12499","pdf_url":"https://arxiv.org/pdf/2507.12499","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5264657428","display_name":null,"funder_award_id":"62206173","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"autonomous":[1,65,177],"driving":[2,66,108,178],"has":[3],"emerged":[4],"as":[5,132],"a":[6,16,57],"promising":[7],"approach":[8],"to":[9,39,87],"unify":[10],"perception,":[11],"prediction,":[12],"and":[13,22,32,78,91,136,139,156,170,181],"planning":[14,168],"within":[15],"single":[17],"framework,":[18],"reducing":[19],"information":[20],"loss":[21],"improving":[23],"adaptability.":[24],"However,":[25],"existing":[26],"methods":[27],"often":[28],"rely":[29],"on":[30,68],"fixed":[31],"sparse":[33],"trajectory":[34,158],"supervision,":[35],"limiting":[36],"their":[37],"ability":[38],"capture":[40],"the":[41,69,101,119,141],"hierarchical":[42,185],"reasoning":[43,93],"process":[44],"that":[45,61,163],"human":[46,71],"drivers":[47],"naturally":[48],"employ.":[49],"To":[50],"bridge":[51],"this":[52],"gap,":[53],"we":[54,98],"propose":[55],"ReAL-AD,":[56],"Reasoning-Augmented":[58],"Learning":[59],"framework":[60,166],"structures":[62],"decision-making":[63],"in":[64],"based":[67],"three-tier":[70],"cognitive":[72],"model:":[73],"Driving":[74,76,79],"Strategy,":[75],"Decision,":[77],"Operation,":[80],"where":[81],"Vision-Language":[82],"Models":[83],"(VLMs)":[84],"are":[85],"incorporated":[86],"enhance":[88],"situational":[89],"awareness":[90],"structured":[92],"across":[94],"these":[95],"levels.":[96],"Specifically,":[97],"introduce:":[99],"(1)":[100],"Strategic":[102],"Reasoning":[103,121],"Injector,":[104],"which":[105,123,145],"formulates":[106],"high-level":[107],"strategies":[109],"by":[110,172],"interpreting":[111],"complex":[112],"traffic":[113],"contexts":[114],"from":[115],"VLM-generated":[116],"insights;":[117],"(2)":[118],"Tactical":[120],"Integrator,":[122],"refines":[124],"strategic":[125],"intent":[126],"into":[127,150],"interpretable":[128,180],"tactical":[129,148],"choices":[130],"such":[131],"lane":[133],"changes,":[134],"overtaking,":[135],"speed":[137],"adjustments;":[138],"(3)":[140],"Hierarchical":[142],"Trajectory":[143],"Decoder,":[144],"progressively":[146],"translates":[147],"decisions":[149],"precise":[151],"control":[152],"actions":[153],"for":[154],"smooth":[155],"human-like":[157,184],"execution.":[159],"Extensive":[160],"evaluations":[161],"show":[162],"integrating":[164],"our":[165],"improves":[167],"accuracy":[169],"safety":[171],"over":[173],"30%,":[174],"making":[175],"end-to-end":[176],"more":[179],"aligned":[182],"with":[183],"reasoning.":[186],"The":[187],"project":[188],"page":[189],"can":[190],"be":[191],"found":[192],"at:":[193],"\\href{https://4dvlab.github.io/project_page/realad}{\\texttt{4dvlab.github.io/project\\_page/realad}}":[194]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-18T00:00:00"}