{"id":"https://openalex.org/W7137908077","doi":"https://doi.org/10.1609/aaai.v40i8.37602","title":"Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning","display_name":"Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137908077","doi":"https://doi.org/10.1609/aaai.v40i8.37602"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i8.37602","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37602","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i8.37602","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129697932","display_name":"Yue Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Li","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129714184","display_name":"Meng Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Meng Tian","raw_affiliation_strings":["Yinwang Intelligent Technology Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yinwang Intelligent Technology Co. Ltd","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021950588","display_name":"Dechang Zhu","orcid":"https://orcid.org/0000-0002-4375-5644"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dechang Zhu","raw_affiliation_strings":["Yinwang Intelligent Technology Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yinwang Intelligent Technology Co. Ltd","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129730382","display_name":"Jiangtong Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiangtong Zhu","raw_affiliation_strings":["Yinwang Intelligent Technology Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yinwang Intelligent Technology Co. Ltd","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040619778","display_name":"Zhenyu Lin","orcid":"https://orcid.org/0000-0003-4020-4422"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhenyu Lin","raw_affiliation_strings":["Huawei Technologies Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129653311","display_name":"Zhiwei Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Xiong","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081400381","display_name":"Xinhai Zhao","orcid":"https://orcid.org/0000-0003-1158-3355"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xinhai Zhao","raw_affiliation_strings":["Huawei Technologies Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd","institution_ids":["https://openalex.org/I4210160618"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":"40","issue":"8","first_page":"6708","last_page":"6716"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9078999757766724,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9078999757766724,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.016300000250339508,"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":0.015799999237060547,"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/leverage","display_name":"Leverage (statistics)","score":0.7098000049591064},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.707099974155426},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.680400013923645},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5791000127792358},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.40139999985694885},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.39959999918937683},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.3792000114917755},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.36149999499320984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7195000052452087},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7098000049591064},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.707099974155426},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.680400013923645},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5791000127792358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5745999813079834},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.3792000114917755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3666999936103821},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35519999265670776},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3158999979496002},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.30489999055862427},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i8.37602","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37602","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37602","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37602","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37602","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"vision-language":[1],"models":[2],"(VLMs)":[3],"for":[4,103,155,194,204],"autonomous":[5],"driving":[6],"(AD)":[7],"are":[8,58,152],"evolving":[9],"beyond":[10],"perception":[11],"and":[12,51,66,91,100,118,164,172,197,207],"cognition":[13],"tasks":[14],"toward":[15],"motion":[16,63,101],"planning.":[17],"However,":[18],"we":[19,84],"identify":[20],"two":[21],"critical":[22],"challenges":[23],"in":[24,199],"this":[25,82],"direction:":[26],"(1)":[27],"VLMs":[28],"tend":[29],"to":[30,68,75,95,125,131,182],"learn":[31],"shortcuts":[32],"by":[33,158],"relying":[34],"heavily":[35],"on":[36,111,161,169],"history":[37],"input":[38,130],"information,":[39],"achieving":[40],"seemingly":[41],"strong":[42],"planning":[43,64,77,102,133,198],"results":[44],"without":[45],"genuinely":[46],"understanding":[47],"the":[48,53,62,71,97,108,146,170],"visual":[49,129],"inputs;":[50],"(2)":[52],"chain-of-thought":[54],"(COT)":[55],"reasoning":[56,73,99,149,196],"processes":[57],"always":[59],"misaligned":[60],"with":[61],"outcomes,":[65],"how":[67],"effectively":[69],"leverage":[70],"complex":[72],"capability":[74],"enhance":[76],"remains":[78],"largely":[79],"underexplored.":[80],"In":[81],"paper,":[83],"start":[85],"from":[86,128],"a":[87,140,191],"small-scale":[88],"domain-specific":[89],"VLM":[90],"propose":[92],"Drive-R1,":[93],"designed":[94],"bridge":[96],"scenario":[98],"AD.":[104],"Drive-R1":[105,122,136,177,189],"first":[106],"undergoes":[107],"supervised":[109],"finetuning":[110],"an":[112],"elaborate":[113],"dataset":[114],"containing":[115],"both":[116],"long":[117],"short":[119],"COT":[120],"data.":[121],"is":[123,137],"encouraged":[124],"reason":[126],"step-by-step":[127],"final":[132],"decisions.":[134],"Subsequently,":[135],"trained":[138],"within":[139],"reinforcement":[141],"learning":[142],"framework":[143],"that":[144,151,176,188],"incentivizes":[145],"discovery":[147],"of":[148],"paths":[150],"more":[153],"informative":[154],"planning,":[156],"guided":[157],"rewards":[159],"based":[160],"predicted":[162],"trajectories":[163],"meta":[165],"actions.":[166],"Experimental":[167],"evaluations":[168],"nuScenes":[171],"DriveLM-nuScenes":[173],"benchmarks":[174],"demonstrate":[175],"achieves":[178],"superior":[179],"performance":[180],"compared":[181],"existing":[183],"state-of-the-art":[184],"VLMs.":[185],"We":[186],"believe":[187],"presents":[190],"promising":[192],"direction":[193],"bridging":[195],"AD,":[200],"offering":[201],"methodological":[202],"insights":[203],"future":[205],"research":[206],"applications.":[208]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}