{"id":"https://openalex.org/W4416887510","doi":"https://doi.org/10.1109/iccv51701.2025.02659","title":"World4Drive: End-to-End Autonomous Driving via Intention-Aware Physical Latent World Model","display_name":"World4Drive: End-to-End Autonomous Driving via Intention-Aware Physical Latent World Model","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416887510","doi":"https://doi.org/10.1109/iccv51701.2025.02659"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02659","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.00603","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103047903","display_name":"Yupeng Zheng","orcid":"https://orcid.org/0000-0003-4450-7586"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Yupeng Zheng","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pengxuan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengxuan Yang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100309450","display_name":"Zebin Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zebin Xing","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049454999","display_name":"Qichao Zhang","orcid":"https://orcid.org/0000-0001-9747-391X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qichao Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030295721","display_name":"Yuhang Zheng","orcid":"https://orcid.org/0000-0001-9628-1940"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Yuhang Zheng","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074076701","display_name":"Yinfeng Gao","orcid":"https://orcid.org/0000-0002-3513-1380"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinfeng Gao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339792","display_name":"Pengfei Li","orcid":"https://orcid.org/0009-0009-8114-6207"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Li","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103204155","display_name":"Teng Zhang","orcid":"https://orcid.org/0000-0002-3736-5594"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teng Zhang","raw_affiliation_strings":["School of Artificial Intelligence, UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, UCAS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065256108","display_name":"Zhongpu Xia","orcid":"https://orcid.org/0009-0003-4251-6849"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongpu Xia","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100550666","display_name":"Peng Jia","orcid":"https://orcid.org/0009-0003-7851-0609"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Jia","raw_affiliation_strings":["Li Auto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Li Auto","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"XianPeng Lang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"XianPeng Lang","raw_affiliation_strings":["Li Auto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Li Auto","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28632","last_page":"28642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.8736000061035156,"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":0.8736000061035156,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.039799999445676804,"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":0.026599999517202377,"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/perception","display_name":"Perception","score":0.6765999794006348},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5586000084877014},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.34940001368522644},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30720001459121704},{"id":"https://openalex.org/keywords/advanced-driver-assistance-systems","display_name":"Advanced driver assistance systems","score":0.30070000886917114},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2980000078678131}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6765999794006348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6636000275611877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5619000196456909},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5586000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.450300008058548},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3736000061035156},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.34940001368522644},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2587999999523163},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02659","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:2507.00603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.00603","pdf_url":"https://arxiv.org/pdf/2507.00603","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.00603","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.00603","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.00603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.00603","pdf_url":"https://arxiv.org/pdf/2507.00603","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2802874431","display_name":null,"funder_award_id":"L253007,4242052","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G6685660108","display_name":null,"funder_award_id":"62173325","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8385108863","display_name":null,"funder_award_id":"2022YFA1004000","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416887510.pdf","grobid_xml":"https://content.openalex.org/works/W4416887510.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"autonomous":[1,51],"driving":[2,31,52,78,105],"directly":[3],"generates":[4,95],"planning":[5,39,69,97,137],"trajectories":[6,98],"from":[7,149],"raw":[8],"sensor":[9],"data,":[10],"yet":[11],"it":[12,118],"typically":[13],"relies":[14],"on":[15,100,161],"costly":[16],"perception":[17,36,134,159],"supervision":[18],"to":[19,34,59,125],"extract":[20],"scene":[21,75,102],"information.":[22],"A":[23],"critical":[24],"research":[25],"challenge":[26],"arises:":[27],"constructing":[28],"an":[29,49,171],"informative":[30],"world":[32,62,81,121],"model":[33,122],"enable":[35],"annotation-free,":[37,135],"end-to-end":[38,50,136],"via":[40],"self-supervised":[41,139],"learning.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"present":[47],"World4Drive,":[48],"framework":[53],"that":[54],"employs":[55],"vision":[56,90],"foundation":[57,91],"models":[58,63],"build":[60],"latent":[61,82,115,151],"for":[64],"generating":[65],"and":[66,80,104,107,127,145,166,182],"evaluating":[67],"multi-modal":[68,96],"trajectories.":[70],"Specifically,":[71],"World4Drive":[72,153],"first":[73],"extracts":[74],"features,":[76],"including":[77],"intention":[79],"representations":[83],"enriched":[84],"with":[85],"spatial-semantic":[86],"priors":[87],"provided":[88],"by":[89],"models.":[92],"It":[93],"then":[94],"based":[99],"current":[101],"features":[103],"intentions":[106],"predicts":[108],"multiple":[109],"intention-driven":[110],"future":[111,143],"states":[112],"within":[113],"the":[114,129,150,163],"space.":[116,152],"Finally,":[117],"introduces":[119],"a":[120],"selector":[123],"module":[124],"evaluate":[126],"select":[128],"best":[130],"trajectory.":[131],"We":[132],"achieve":[133],"through":[138],"alignment":[140],"between":[141],"actual":[142],"observations":[144,147],"predicted":[146],"reconstructed":[148],"achieves":[154],"state-of-the-art":[155],"performance":[156],"without":[157],"manual":[158],"annotations":[160],"both":[162],"open-loop":[164],"nuScenes":[165],"closed-loop":[167],"NavSim":[168],"benchmarks,":[169],"demonstrating":[170],"18.1\\%":[172],"relative":[173],"reduction":[174],"in":[175],"L2":[176],"error,":[177],"46.7%":[178],"lower":[179],"collision":[180],"rate,":[181],"3.75":[183],"faster":[184],"training":[185],"convergence.":[186],"Codes":[187],"will":[188],"be":[189],"accessed":[190],"at":[191],"https://github.com/ucaszyp/World4Drive.":[192]},"counts_by_year":[],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}