{"id":"https://openalex.org/W4415537185","doi":"https://doi.org/10.1145/3746027.3755730","title":"VLMPlanner: Integrating Visual Language Models with Motion Planning","display_name":"VLMPlanner: Integrating Visual Language Models with Motion Planning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537185","doi":"https://doi.org/10.1145/3746027.3755730"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755730","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5062215911","display_name":"Zhipeng Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhipeng Tang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0008-2339-8863","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764398","display_name":"Sha Zhang","orcid":"https://orcid.org/0000-0002-1814-6783"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sha Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1814-6783","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089561793","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0001-9624-7451"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiajun Deng","raw_affiliation_strings":["University of Adelaide, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9624-7451","affiliations":[{"raw_affiliation_string":"University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101872508","display_name":"Chenjie Wang","orcid":"https://orcid.org/0000-0001-9207-2076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenjie Wang","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9207-2076","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034921190","display_name":"Guoliang You","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang You","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0964-7279","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuting Huang","orcid":"https://orcid.org/0009-0002-5533-3972"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Huang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-5533-3972","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109990207","display_name":"Xia Lin","orcid":"https://orcid.org/0009-0008-6125-0341"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinrui Lin","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0008-6125-0341","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053344541","display_name":"Yanyong Zhang","orcid":"https://orcid.org/0000-0001-6520-255X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6520-255X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5062215911"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28643236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5040","last_page":"5049"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9983999729156494,"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/T11439","display_name":"Video Analysis and Summarization","score":0.991599977016449,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6621000170707703},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.6559000015258789},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.49639999866485596},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.476500004529953},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45089998841285706},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4142000079154968},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.400299996137619},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.39250001311302185},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.3772999942302704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210000157356262},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6621000170707703},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.6559000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5831000208854675},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.476500004529953},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45089998841285706},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.39250001311302185},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3815999925136566},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3772999942302704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3734999895095825},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3093000054359436},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755730","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":5,"referenced_works":["https://openalex.org/W2968983352","https://openalex.org/W3009593063","https://openalex.org/W4386076400","https://openalex.org/W4390872423","https://openalex.org/W4394862623"],"related_works":[],"abstract_inverted_index":{"Integrating":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"into":[5],"autonomous":[6],"driving":[7,63,136],"motion":[8],"planning":[9,154,175],"has":[10],"recently":[11],"emerged":[12],"as":[13,46],"a":[14,72,77,82],"promising":[15],"direction,":[16],"offering":[17],"enhanced":[18],"interpretability,":[19],"better":[20],"controllability,":[21],"and":[22,27,103,117,156,183],"improved":[23],"generalization":[24],"in":[25,61,114,177],"rare":[26],"long-tail":[28],"scenarios.":[29],"However,":[30],"existing":[31],"methods":[32],"often":[33],"rely":[34],"on":[35,145,163],"abstracted":[36],"perception":[37],"or":[38,52],"map-based":[39],"inputs,":[40],"missing":[41],"crucial":[42],"visual":[43,101],"context,":[44],"such":[45],"fine-grained":[47],"road":[48,181],"cues,":[49],"accident":[50],"aftermath,":[51],"unexpected":[53],"obstacles,":[54],"which":[55],"are":[56],"essential":[57],"for":[58],"robust":[59,116],"decision-making":[60],"complex":[62],"environments.":[64],"To":[65],"bridge":[66],"this":[67],"gap,":[68],"we":[69,121],"propose":[70],"VLMPlanner,":[71],"hybrid":[73],"framework":[74],"that":[75,129],"combines":[76],"learning-based":[78],"real-time":[79,112],"planner":[80,113],"with":[81,169,179],"vision-language":[83],"model":[84],"(VLM)":[85],"capable":[86],"of":[87],"reasoning":[88,107],"over":[89],"raw":[90],"images.":[91],"The":[92],"VLM":[93,132],"processes":[94],"multi-view":[95],"images":[96],"to":[97,109,133],"capture":[98],"rich,":[99],"detailed":[100],"information":[102],"leverages":[104],"its":[105,141],"common-sense":[106],"capabilities":[108],"guide":[110],"the":[111,123,131,164],"generating":[115],"safe":[118],"trajectories.":[119],"Furthermore,":[120],"develop":[122],"Context-Adaptive":[124],"Inference":[125],"Gate":[126],"(CAI-Gate)":[127],"mechanism":[128],"enables":[130],"mimic":[134],"human":[135],"behavior":[137],"by":[138],"dynamically":[139],"adjusting":[140],"inference":[142],"frequency":[143],"based":[144],"scene":[146],"complexity,":[147],"thereby":[148],"achieving":[149],"an":[150],"optimal":[151],"balance":[152],"between":[153],"performance":[155,176],"computational":[157],"efficiency.":[158],"We":[159],"evaluate":[160],"our":[161],"approach":[162],"large-scale,":[165],"challenging":[166],"nuPlan":[167],"benchmark,":[168],"comprehensive":[170],"experimental":[171],"results":[172],"demonstrating":[173],"superior":[174],"scenarios":[178],"intricate":[180],"conditions":[182],"dynamic":[184],"elements.":[185]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}