{"id":"https://openalex.org/W4406893040","doi":"https://doi.org/10.1109/fllm63129.2024.10852498","title":"VLM-Auto: VLM-based Autonomous Driving Assistant with Human-like Behavior and Understanding for Complex Road Scenes","display_name":"VLM-Auto: VLM-based Autonomous Driving Assistant with Human-like Behavior and Understanding for Complex Road Scenes","publication_year":2024,"publication_date":"2024-11-26","ids":{"openalex":"https://openalex.org/W4406893040","doi":"https://doi.org/10.1109/fllm63129.2024.10852498"},"language":"en","primary_location":{"id":"doi:10.1109/fllm63129.2024.10852498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","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/A5113173807","display_name":"Ziang Guo","orcid":"https://orcid.org/0009-0007-7322-8865"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Ziang Guo","raw_affiliation_strings":["Intelligent Space Robotics Laboratory Skoltech,Moscow,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Space Robotics Laboratory Skoltech,Moscow,Russia","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097424597","display_name":"Zakhar Yagudin","orcid":null},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Zakhar Yagudin","raw_affiliation_strings":["Intelligent Space Robotics Laboratory Skoltech,Moscow,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Space Robotics Laboratory Skoltech,Moscow,Russia","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059197603","display_name":"Artem Lykov","orcid":"https://orcid.org/0000-0001-6119-2366"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Artem Lykov","raw_affiliation_strings":["Intelligent Space Robotics Laboratory Skoltech,Moscow,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Space Robotics Laboratory Skoltech,Moscow,Russia","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092586333","display_name":"Mikhail Konenkov","orcid":"https://orcid.org/0009-0003-5979-487X"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Mikhail Konenkov","raw_affiliation_strings":["Intelligent Space Robotics Laboratory Skoltech,Moscow,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Space Robotics Laboratory Skoltech,Moscow,Russia","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056458774","display_name":"Dzmitry Tsetserukou","orcid":"https://orcid.org/0000-0001-8055-5345"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dzmitry Tsetserukou","raw_affiliation_strings":["Intelligent Space Robotics Laboratory Skoltech,Moscow,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Space Robotics Laboratory Skoltech,Moscow,Russia","institution_ids":["https://openalex.org/I125989756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113173807"],"corresponding_institution_ids":["https://openalex.org/I125989756"],"apc_list":null,"apc_paid":null,"fwci":4.1944,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.94709847,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"501","last_page":"507"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9857000112533569,"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":0.9857000112533569,"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/computer-science","display_name":"Computer science","score":0.6335780620574951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45380452275276184},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40810006856918335},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.35762864351272583},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33056044578552246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6335780620574951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45380452275276184},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40810006856918335},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.35762864351272583},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33056044578552246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fllm63129.2024.10852498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","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":24,"referenced_works":["https://openalex.org/W4280571816","https://openalex.org/W4309592030","https://openalex.org/W4382202657","https://openalex.org/W4386066695","https://openalex.org/W4386071585","https://openalex.org/W4386076400","https://openalex.org/W4392646028","https://openalex.org/W4400648861","https://openalex.org/W4402353994","https://openalex.org/W4402727495","https://openalex.org/W4402753802","https://openalex.org/W4406613045","https://openalex.org/W6745935785","https://openalex.org/W6853251322","https://openalex.org/W6856800273","https://openalex.org/W6857066902","https://openalex.org/W6858522248","https://openalex.org/W6859274857","https://openalex.org/W6859341508","https://openalex.org/W6859553595","https://openalex.org/W6860393137","https://openalex.org/W6860490637","https://openalex.org/W6861402905","https://openalex.org/W6861455346"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recent":[0],"research":[1],"on":[2,70,148],"Large":[3],"Language":[4,113],"Models":[5],"for":[6,131],"autonomous":[7,56,63],"driving":[8,39,57,67,159],"shows":[9],"promise":[10],"in":[11,153,167],"planning":[12],"and":[13,19,26,41,45,82,126,170],"control.":[14],"However,":[15],"high":[16],"computational":[17],"demands":[18],"hallucinations":[20],"still":[21],"challenge":[22],"accurate":[23],"trajectory":[24],"prediction":[25,165],"control":[27],"signal":[28],"generation.":[29],"Deterministic":[30],"algorithms":[31],"offer":[32],"reliability":[33],"but":[34],"lack":[35],"adaptability":[36],"to":[37,60],"complex":[38],"scenarios":[40],"struggle":[42],"with":[43,65],"context":[44],"uncertainty.":[46],"To":[47],"address":[48],"this":[49],"problem,":[50],"we":[51,117],"propose":[52],"VLM-Auto,":[53],"a":[54,97,120,127],"novel":[55],"assistant":[58],"system":[59,93,143,162],"empower":[61],"the":[62,71,79,89,105,111,133,157],"vehicles":[64],"adjustable":[66],"behaviors":[68],"based":[69],"understanding":[72],"of":[73,91,107,110,136,151],"road":[74],"scenes.":[75,172],"A":[76],"pipeline":[77],"involving":[78],"CARLA":[80,140],"simulator":[81],"Robot":[83],"Operating":[84],"System":[85],"2":[86],"(ROS2)":[87],"verifying":[88],"effectiveness":[90],"our":[92,137,142,154,161],"is":[94],"presented,":[95],"utilizing":[96],"single":[98],"Nvidia":[99],"4090":[100],"24G":[101],"GPU":[102],"while":[103],"exploiting":[104],"capacity":[106],"textual":[108],"output":[109],"Visual":[112],"Model":[114],"(VLM).":[115],"Besides,":[116],"also":[118],"contribute":[119],"dataset":[121,175],"containing":[122],"an":[123],"image":[124],"set":[125,130],"corresponding":[128],"prompt":[129],"fine-tuning":[132],"VLM":[134],"module":[135],"system.":[138],"In":[139,156],"experiments,":[141],"achieved":[144,163],"97.82%":[145],"average":[146],"precision":[147],"5":[149],"types":[150],"labels":[152],"dataset.":[155],"real-world":[158],"dataset,":[160],"96.97%":[164],"accuracy":[166],"night":[168],"scenes":[169],"gloomy":[171],"Our":[173],"VLM-Auto":[174],"will":[176],"be":[177],"released":[178],"at":[179],"https://github.com/ZionGo6/VLM-Auto.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}