{"id":"https://openalex.org/W4413917542","doi":"https://doi.org/10.1109/icra55743.2025.11127286","title":"Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-Tuning","display_name":"Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-Tuning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917542","doi":"https://doi.org/10.1109/icra55743.2025.11127286"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5012295217","display_name":"Zhiyu Huang","orcid":"https://orcid.org/0000-0003-1592-7215"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiyu Huang","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090287059","display_name":"Xinshuo Weng","orcid":"https://orcid.org/0000-0002-7894-4381"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinshuo Weng","raw_affiliation_strings":["NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024136382","display_name":"Maximilian Igl","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maximilian Igl","raw_affiliation_strings":["NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366786","display_name":"Yuxiao Chen","orcid":"https://orcid.org/0000-0001-5276-7156"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxiao Chen","raw_affiliation_strings":["NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102138164","display_name":"Yulong Cao","orcid":"https://orcid.org/0009-0006-2456-2093"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yulong Cao","raw_affiliation_strings":["NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091869385","display_name":"Boris Ivanovic","orcid":"https://orcid.org/0000-0002-8698-202X"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ivanovic","raw_affiliation_strings":["NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050003000","display_name":"Marco Pavone","orcid":"https://orcid.org/0000-0002-0206-4337"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Pavone","raw_affiliation_strings":["NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Research, NVIDIA Corporation,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108146266","display_name":"Chen Lv","orcid":"https://orcid.org/0009-0003-9168-7273"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Lv","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4954,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83250958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3445","last_page":"3451"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.9419999718666077,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9419999718666077,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8929775953292847},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6205715537071228},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6111664772033691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5968258380889893},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5947250127792358},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.49736812710762024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40146803855895996},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33080342411994934},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15208053588867188},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0652691125869751},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.057004958391189575}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8929775953292847},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6205715537071228},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6111664772033691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5968258380889893},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5947250127792358},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.49736812710762024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40146803855895996},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33080342411994934},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15208053588867188},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0652691125869751},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.057004958391189575},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W3176912151","https://openalex.org/W3199048838","https://openalex.org/W4327662239","https://openalex.org/W4381198967","https://openalex.org/W4383108499","https://openalex.org/W4386076407","https://openalex.org/W4386076672","https://openalex.org/W4388642362","https://openalex.org/W4390788068","https://openalex.org/W4390871698","https://openalex.org/W4390872108","https://openalex.org/W4399800593","https://openalex.org/W4401413933","https://openalex.org/W4401416666","https://openalex.org/W4401416944","https://openalex.org/W4402753718","https://openalex.org/W4403021210","https://openalex.org/W4404545718","https://openalex.org/W4409366385"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Autonomous":[0],"driving":[1,144],"necessitates":[2],"the":[3,23,29,60,101,105,123,127,141],"ability":[4],"to":[5,14,36,52,99,167,172],"reason":[6],"about":[7],"future":[8,56],"interactions":[9],"between":[10],"traffic":[11],"agents":[12],"and":[13,32,89,118,126],"make":[15],"informed":[16],"evaluations":[17],"for":[18,62,112,161],"planning.":[19],"This":[20],"paper":[21],"introduces":[22],"Gen-Drive":[24],"framework,":[25],"which":[26],"shifts":[27],"from":[28],"traditional":[30],"prediction":[31],"deterministic":[33],"planning":[34,39,113,120,150,169],"framework":[35,42,98],"a":[37,44,49,71,133],"generation-then-evaluation":[38,134],"paradigm.":[40],"The":[41],"employs":[43],"behavior":[45],"diffusion":[46,106],"model":[47,160],"as":[48],"scene":[50,72],"generator":[51],"produce":[53],"diverse":[54],"possible":[55],"scenarios,":[57],"thereby":[58,85],"enhancing":[59,90],"capability":[61],"joint":[63],"interaction":[64],"reasoning.":[65],"To":[66],"facilitate":[67],"decision-making,":[68],"we":[69,93],"propose":[70],"evaluator":[73],"(reward)":[74],"model,":[75,107],"trained":[76],"with":[77],"pairwise":[78],"preference":[79],"data":[80],"collected":[81],"through":[82],"VLM":[83],"assistance,":[84],"reducing":[86],"human":[87],"workload":[88],"scalability.":[91],"Furthermore,":[92],"utilize":[94],"an":[95],"RL":[96,164],"fine-tuning":[97,165],"improve":[100],"generation":[102],"quality":[103],"of":[104],"rendering":[108],"it":[109],"more":[110],"effective":[111],"tasks.":[114],"We":[115,152],"conduct":[116],"training":[117],"closed-loop":[119],"tests":[121],"on":[122,174],"nuPlan":[124],"dataset,":[125],"results":[128],"demonstrate":[129,154],"that":[130,155],"employing":[131],"such":[132],"strategy":[135],"outperforms":[136],"other":[137],"learning-based":[138],"approaches.":[139],"Additionally,":[140],"fine-tuned":[142],"generative":[143],"policy":[145],"shows":[146],"significant":[147],"enhancements":[148],"in":[149],"performance.":[151],"further":[153],"utilizing":[156],"our":[157],"learned":[158],"reward":[159],"evaluation":[162],"or":[163],"leads":[166],"better":[168],"performance":[170],"compared":[171],"relying":[173],"human-designed":[175],"rewards.":[176],"Project":[177],"website:":[178],"https://mczhi.github.io/GenDrive.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}