{"id":"https://openalex.org/W4416731372","doi":"https://doi.org/10.1007/s44267-025-00095-w","title":"DriveMLM: aligning multi-modal large language models with behavioral planning states for autonomous driving","display_name":"DriveMLM: aligning multi-modal large language models with behavioral planning states for autonomous driving","publication_year":2025,"publication_date":"2025-11-26","ids":{"openalex":"https://openalex.org/W4416731372","doi":"https://doi.org/10.1007/s44267-025-00095-w"},"language":"en","primary_location":{"id":"doi:10.1007/s44267-025-00095-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00095-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00095-w.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00095-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114653164","display_name":"Erfei Cui","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"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Erfei Cui","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China","Shanghai Jiao Tong University, Shanghai, 200240, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101827340","display_name":"Wenhai Wang","orcid":"https://orcid.org/0000-0002-2418-3134"},"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"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Wenhai Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China","The Chinese University of Hong Kong, Hong Kong, 999077, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, 999077, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675974","display_name":"Zhiqi Li","orcid":"https://orcid.org/0000-0002-7041-0748"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqi Li","raw_affiliation_strings":["Nanjing University, Nanjing, 210023, China","Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, 210023, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007317446","display_name":"Jiangwei Xie","orcid":"https://orcid.org/0009-0008-2216-9145"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangwei Xie","raw_affiliation_strings":["SenseTime Research, Shanghai, 200233, China"],"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, 200233, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012714850","display_name":"Haoming Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoming Zou","raw_affiliation_strings":["Stanford University, Stanford, CA, 94305, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077375709","display_name":"Hanming Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanming Deng","raw_affiliation_strings":["SenseTime Research, Shanghai, 200233, China"],"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, 200233, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102997988","display_name":"Gen Luo","orcid":"https://orcid.org/0000-0001-5334-1843"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gen Luo","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000474748","display_name":"Lewei Lu","orcid":"https://orcid.org/0009-0009-9809-3818"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lewei Lu","raw_affiliation_strings":["SenseTime Research, Shanghai, 200233, China"],"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, 200233, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026890219","display_name":"Xiaolong Zhu","orcid":"https://orcid.org/0000-0002-4301-8724"},"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":"Xizhou Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, 100084, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026944066","display_name":"Jifeng Dai","orcid":"https://orcid.org/0000-0002-6785-0785"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]},{"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":"Jifeng Dai","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Beijing, 100084, China","Tsinghua University, Beijing, 100084, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Beijing, 100084, China","institution_ids":["https://openalex.org/I4210156423"]},{"raw_affiliation_string":"Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5114653164"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210100255","https://openalex.org/I4391012619"],"apc_list":null,"apc_paid":null,"fwci":1.2512,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85780824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"3","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7211999893188477,"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":0.7211999893188477,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.041200000792741776,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.03959999978542328,"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/autopilot","display_name":"Autopilot","score":0.8141999840736389},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5548999905586243},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.47870001196861267},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.47510001063346863},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.3937999904155731},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.38519999384880066},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3776000142097473},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3668000102043152},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.36039999127388}],"concepts":[{"id":"https://openalex.org/C18020424","wikidata":"https://www.wikidata.org/wiki/Q220858","display_name":"Autopilot","level":2,"score":0.8141999840736389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5777000188827515},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5548999905586243},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4708999991416931},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39739999175071716},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3061000108718872},{"id":"https://openalex.org/C78639753","wikidata":"https://www.wikidata.org/wiki/Q3318160","display_name":"Behavioral modeling","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2989549987","wikidata":"https://www.wikidata.org/wiki/Q350882","display_name":"Route planning","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.267300009727478},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.2596000134944916}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44267-025-00095-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00095-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00095-w.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:270b3ee872db4fb6990761cd9c822ff9","is_oa":true,"landing_page_url":"https://doaj.org/article/270b3ee872db4fb6990761cd9c822ff9","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Visual Intelligence, Vol 3, Iss 1, Pp 1-15 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44267-025-00095-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00095-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00095-w.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2438210826","display_name":null,"funder_award_id":"62321005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2538748788","display_name":null,"funder_award_id":"U24A2032","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4092911450","display_name":null,"funder_award_id":"62376134","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416731372.pdf","grobid_xml":"https://content.openalex.org/works/W4416731372.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W4292347911","https://openalex.org/W4389519587","https://openalex.org/W4390696496","https://openalex.org/W4401386967","https://openalex.org/W4404782770","https://openalex.org/W4405595839","https://openalex.org/W4405907309"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Large":[1],"language":[2,31,64],"models":[3,32],"(LLMs)":[4,33],"have":[5],"opened":[6],"up":[7],"new":[8],"possibilities":[9],"for":[10,137,159,212],"intelligent":[11],"agents,":[12],"endowing":[13],"them":[14],"with":[15,180,215],"human-like":[16],"thinking":[17],"and":[18,66,107,117,121,135,155,162,168,178,188],"cognitive":[19],"abilities.":[20],"In":[21],"this":[22,55,205],"work,":[23],"we":[24,58],"delve":[25],"into":[26],"the":[27,60,63,67,73,78,92,172,176,192,198],"potential":[28],"of":[29,96,175,186,200],"large":[30],"in":[34,51,128,183],"autonomous":[35,49,213],"driving":[36,50,103,119,214],"(AD).":[37],"We":[38,84,141,164,203],"introduce":[39],"DriveMLM,":[40],"an":[41,143],"LLM-based":[42],"AD":[43,99,130],"framework":[44],"that":[45,151,170],"can":[46,126,207],"perform":[47],"close-loop":[48,138],"realistic":[52],"simulators.":[53],"To":[54],"end,":[56],"(1)":[57],"bridge":[59],"gap":[61],"between":[62],"decisions":[65,120],"vehicle":[68],"control":[69],"commands":[70],"by":[71],"standardizing":[72],"decision":[74,153],"states":[75],"according":[76],"to":[77,90,147],"off-the-shelf":[79],"motion":[80],"planning":[81,94],"module.":[82],"(2)":[83],"employ":[85],"a":[86,97,149,210],"multimodal":[87],"LLM":[88],"(MLLM)":[89],"model":[91,125,160],"behavior":[93],"module":[95,98],"system,":[100],"which":[101],"uses":[102],"rules,":[104],"user":[105],"commands,":[106],"inputs":[108],"from":[109],"various":[110],"sensors":[111],"(e.g.,":[112],"camera,":[113],"LiDAR)":[114],"as":[115,133,209],"input":[116],"makes":[118],"provide":[122],"explanations.":[123],"This":[124],"plug-and-play":[127],"existing":[129],"systems":[131],"such":[132],"Autopilot":[134,177],"Apollo":[136,179],"driving.":[139],"(3)":[140],"design":[142],"effective":[144],"data":[145],"engine":[146],"collect":[148],"dataset":[150],"includes":[152],"state":[154],"corresponding":[156],"explanation":[157],"annotation":[158],"training":[161],"evaluation.":[163],"conduct":[165],"extensive":[166],"experiments":[167],"show":[169],"replacing":[171],"decision-making":[173],"modules":[174],"DriveMLM":[181],"resulted":[182],"significant":[184],"improvements":[185],"3.2":[187],"4.7":[189],"points":[190],"on":[191],"CARLA":[193],"Town05":[194],"Long,":[195],"respectively,":[196],"demonstrating":[197],"effectiveness":[199],"our":[201],"model.":[202],"hope":[204],"work":[206],"serve":[208],"baseline":[211],"LLMs.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-11-27T00:00:00"}