{"id":"https://openalex.org/W7136657066","doi":"https://doi.org/10.1109/itsc60802.2025.11423557","title":"COVLM-RL: Critical Object-Oriented Reasoning for Autonomous Driving Using VLM-Guided Reinforcement Learning","display_name":"COVLM-RL: Critical Object-Oriented Reasoning for Autonomous Driving Using VLM-Guided Reinforcement Learning","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W7136657066","doi":"https://doi.org/10.1109/itsc60802.2025.11423557"},"language":null,"primary_location":{"id":"doi:10.1109/itsc60802.2025.11423557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5129560591","display_name":"Lin Li","orcid":null},"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":"Lin Li","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University,Singapore,639798"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University,Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088549136","display_name":"Yuxin Cai","orcid":"https://orcid.org/0000-0002-5628-7050"},"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":"Yuxin Cai","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University,Singapore,639798"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University,Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121676209","display_name":"Jianwu Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Fang","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129536966","display_name":"Jianru Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianru Xue","raw_affiliation_strings":["National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129512212","display_name":"Chen Lv","orcid":null},"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,639798"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University,Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":null,"issue":null,"first_page":"1044","last_page":"1051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.43560001254081726,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.43560001254081726,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09130000323057175,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.04910000041127205,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.48190000653266907},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.34450000524520874},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3294000029563904},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2687000036239624},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.26089999079704285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5541999936103821},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48190000653266907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47839999198913574},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25450000166893005},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.24979999661445618}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc60802.2025.11423557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2905333823","https://openalex.org/W2962894046","https://openalex.org/W3049006625","https://openalex.org/W3172863135","https://openalex.org/W3193987867","https://openalex.org/W4378833173","https://openalex.org/W4385331824","https://openalex.org/W4385569629","https://openalex.org/W4386471863","https://openalex.org/W4390871940","https://openalex.org/W4392172801","https://openalex.org/W4401109681","https://openalex.org/W4401415107","https://openalex.org/W4402713111","https://openalex.org/W4402721914","https://openalex.org/W4403755595","https://openalex.org/W4404820176","https://openalex.org/W4405156617","https://openalex.org/W4407730642","https://openalex.org/W4408701100","https://openalex.org/W4410020746","https://openalex.org/W4413858428"],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"autonomous":[1],"driving":[2,60,180],"frameworks":[3],"face":[4],"persistent":[5],"challenges":[6],"in":[7,33,164,178,185],"generalization,":[8],"training":[9,119,160],"efficiency,":[10],"and":[11,46,89,110,120,151,159,182],"interpretability.":[12,123],"While":[13],"recent":[14],"methods":[15],"leverage":[16],"VisionLanguage":[17],"Models":[18],"(VLMs)":[19],"through":[20],"supervised":[21],"learning":[22,38],"on":[23],"large-scale":[24],"datasets":[25],"to":[26,83],"improve":[27],"reasoning,":[28],"they":[29],"often":[30],"lack":[31,47],"robustness":[32],"novel":[34,58],"scenarios.":[35],"Conversely,":[36],"reinforcement":[37],"(RL)-based":[39],"approaches":[40],"enhance":[41],"adaptability":[42],"but":[43],"remain":[44],"datainefficient":[45],"transparent":[48],"decision-making.":[49],"To":[50,135],"address":[51],"these":[52],"limitations,":[53],"we":[54,72,138],"propose":[55],"COVLM-RL,":[56],"a":[57,74,140],"end-toend":[59],"framework":[61],"that":[62,79,143,169],"integrates":[63],"Critical":[64],"Object-oriented":[65],"(CO)":[66],"reasoning":[67],"with":[68,129],"VLM-guided":[69],"RL.":[70],"Specifically,":[71],"design":[73],"Chain-of-Thought":[75],"(CoT)":[76],"prompting":[77],"strategy":[78],"enables":[80],"the":[81,107,115,147,152,165,173],"VLM":[82],"reason":[84],"over":[85],"critical":[86],"traffic":[87],"elements":[88],"generate":[90],"high-level":[91,126],"semantic":[92,101,127,149],"decisions,":[93],"effectively":[94],"transforming":[95],"multiview":[96],"visual":[97],"inputs":[98],"into":[99,114],"structured":[100],"decision":[102],"priors.":[103],"These":[104],"priors":[105],"reduce":[106],"input":[108],"dimensionality":[109],"inject":[111],"taskrelevant":[112],"knowledge":[113],"RL":[116,153],"loop,":[117],"accelerating":[118],"improving":[121],"policy":[122],"However,":[124],"bridging":[125],"guidance":[128],"continuous":[130],"low-level":[131],"control":[132,155],"remains":[133],"non-trivial.":[134],"this":[136],"end,":[137],"introduce":[139],"consistency":[141],"loss":[142],"encourages":[144],"alignment":[145],"between":[146],"VLM's":[148],"plans":[150],"agent's":[154],"outputs,":[156],"enhancing":[157],"interpretability":[158],"stability.":[161],"Experiments":[162],"conducted":[163],"CARLA":[166],"simulator":[167],"demonstrate":[168],"COVLM-RL":[170],"significantly":[171],"improves":[172],"success":[174],"rate":[175],"by":[176,183],"30%":[177],"trained":[179],"environments":[181],"50%":[184],"previously":[186],"unseen":[187],"environments,":[188],"highlighting":[189],"its":[190],"strong":[191],"generalization":[192],"capability.":[193]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-17T00:00:00"}