{"id":"https://openalex.org/W4408696853","doi":"https://doi.org/10.1109/itsc58415.2024.10919532","title":"AirVista: Empowering UAVs with 3D Spatial Reasoning Abilities Through a Multimodal Large Language Model Agent","display_name":"AirVista: Empowering UAVs with 3D Spatial Reasoning Abilities Through a Multimodal Large Language Model Agent","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4408696853","doi":"https://doi.org/10.1109/itsc58415.2024.10919532"},"language":"en","primary_location":{"id":"doi:10.1109/itsc58415.2024.10919532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10919532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","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/A5039912568","display_name":"Fei Lin","orcid":"https://orcid.org/0000-0002-5832-1128"},"institutions":[{"id":"https://openalex.org/I111950717","display_name":"Macau University of Science and Technology","ror":"https://ror.org/03jqs2n27","country_code":"MO","type":"education","lineage":["https://openalex.org/I111950717","https://openalex.org/I4391767947"]}],"countries":["MO"],"is_corresponding":true,"raw_author_name":"Fei Lin","raw_affiliation_strings":["Macau University of Science and Technology,Faculty of Innovation Engineering,Department of Engineering Science,Macau,China,999078"],"affiliations":[{"raw_affiliation_string":"Macau University of Science and Technology,Faculty of Innovation Engineering,Department of Engineering Science,Macau,China,999078","institution_ids":["https://openalex.org/I111950717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115594196","display_name":"Yonglin Tian","orcid":"https://orcid.org/0009-0005-4035-7332"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonglin Tian","raw_affiliation_strings":["State Key Laboratory for Management and Control of Complex Systems, Institute of Automation,Chinese Academy of Sciences,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Management and Control of Complex Systems, Institute of Automation,Chinese Academy of Sciences,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102956206","display_name":"Yunzhe Wang","orcid":"https://orcid.org/0000-0002-1755-6430"},"institutions":[{"id":"https://openalex.org/I90259746","display_name":"Capital University of Economics and Business","ror":"https://ror.org/01r5sf951","country_code":"CN","type":"education","lineage":["https://openalex.org/I90259746"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunzhe Wang","raw_affiliation_strings":["Capital University of Economics and Business,Beijing,China,100070"],"affiliations":[{"raw_affiliation_string":"Capital University of Economics and Business,Beijing,China,100070","institution_ids":["https://openalex.org/I90259746"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078400575","display_name":"Tengchao Zhang","orcid":"https://orcid.org/0000-0003-1730-4185"},"institutions":[{"id":"https://openalex.org/I111950717","display_name":"Macau University of Science and Technology","ror":"https://ror.org/03jqs2n27","country_code":"MO","type":"education","lineage":["https://openalex.org/I111950717","https://openalex.org/I4391767947"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Tengchao Zhang","raw_affiliation_strings":["Macau University of Science and Technology,Faculty of Innovation Engineering,Department of Engineering Science,Macau,China,999078"],"affiliations":[{"raw_affiliation_string":"Macau University of Science and Technology,Faculty of Innovation Engineering,Department of Engineering Science,Macau,China,999078","institution_ids":["https://openalex.org/I111950717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042385641","display_name":"Xinyuan Zhang","orcid":"https://orcid.org/0000-0002-4636-1202"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyuan Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences,Department of Artificial Intelligence,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Department of Artificial Intelligence,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455707","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0001-5297-0859"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei-Yue Wang","raw_affiliation_strings":["State Key Laboratory for Management and Control of Complex Systems,Chinese Academy of Sciences,Beijing,100190"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Management and Control of Complex Systems,Chinese Academy of Sciences,Beijing,100190","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5039912568"],"corresponding_institution_ids":["https://openalex.org/I111950717"],"apc_list":null,"apc_paid":null,"fwci":1.0215,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79083109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"476","last_page":"481"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9984999895095825,"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/T12031","display_name":"Speech and dialogue systems","score":0.9976000189781189,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9934999942779541,"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/computer-science","display_name":"Computer science","score":0.7287616729736328},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.582905650138855},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.45963627099990845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4197675883769989},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4110630750656128},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3674653172492981}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287616729736328},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.582905650138855},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45963627099990845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4197675883769989},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4110630750656128},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3674653172492981}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc58415.2024.10919532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc58415.2024.10919532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","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":34,"referenced_works":["https://openalex.org/W2615547864","https://openalex.org/W2754582354","https://openalex.org/W3088429312","https://openalex.org/W3168867926","https://openalex.org/W3185205840","https://openalex.org/W3185341429","https://openalex.org/W4291653324","https://openalex.org/W4312081617","https://openalex.org/W4312420092","https://openalex.org/W4322616103","https://openalex.org/W4322718191","https://openalex.org/W4366330503","https://openalex.org/W4383108457","https://openalex.org/W4385262477","https://openalex.org/W4385436553","https://openalex.org/W4385900995","https://openalex.org/W4386088221","https://openalex.org/W4388685466","https://openalex.org/W4389115629","https://openalex.org/W4390041933","https://openalex.org/W4390189932","https://openalex.org/W4390872901","https://openalex.org/W4390874575","https://openalex.org/W4394862582","https://openalex.org/W4394862623","https://openalex.org/W4402716288","https://openalex.org/W4402727764","https://openalex.org/W4404356490","https://openalex.org/W4405787555","https://openalex.org/W6745935785","https://openalex.org/W6791353385","https://openalex.org/W6849177959","https://openalex.org/W6851592950","https://openalex.org/W6855425132"],"related_works":["https://openalex.org/W2124759987","https://openalex.org/W1999714552","https://openalex.org/W2167086559","https://openalex.org/W2153102768","https://openalex.org/W1593007803","https://openalex.org/W2367213291","https://openalex.org/W2169518243","https://openalex.org/W2176663493","https://openalex.org/W2395908292","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"urban":[1,29,45],"environments,":[2],"complex":[3,170],"transportation":[4,23],"demands,":[5],"including":[6],"land,":[7],"air,":[8],"and":[9,24,56,65,91,94,165],"maritime":[10],"transport,":[11],"are":[12,99],"increasingly":[13],"growing.":[14],"While":[15],"significant":[16],"advancements":[17],"have":[18],"been":[19,121],"made":[20],"in":[21,36,102,168],"land":[22],"autonomous":[25],"driving,":[26],"research":[27],"on":[28,59],"air":[30,46],"mobility":[31],"(UAM)":[32],"systems":[33],"is":[34,54],"still":[35],"its":[37,125],"early":[38],"stages.":[39],"This":[40],"paper":[41,107,141],"presents":[42],"an":[43,110],"innovative":[44],"unmanned":[47],"aerial":[48],"vehicle":[49],"(UAV)":[50],"framework:":[51],"AirVista,":[52],"which":[53,119],"designed":[55],"built":[57],"based":[58],"the":[60,130,133,158],"Artificial":[61],"Systems,":[62],"Computational":[63],"experiments,":[64],"Parallel":[66],"execution":[67,166],"(ACP)":[68],"approach,":[69],"integrated":[70,114],"with":[71,115],"a":[72],"multimodal":[73],"large":[74],"language":[75],"model":[76],"(MLLM)":[77],"agent.":[78],"Considering":[79],"that":[80,96,157],"UAM":[81],"tasks":[82],"often":[83],"require":[84],"UAVs":[85],"to":[86,128],"possess":[87],"fine-grained":[88],"spatial":[89,117],"perception":[90],"reasoning":[92],"capabilities,":[93],"given":[95],"existing":[97],"MLLMs":[98],"somewhat":[100],"lacking":[101],"exploring":[103],"3D":[104,116],"spaces,":[105],"this":[106,140],"further":[108],"proposes":[109],"instruction":[111],"fine-tuning":[112,145],"strategy":[113],"knowledge,":[118],"has":[120],"validated":[122],"experimentally":[123],"for":[124,137,148],"effectiveness.":[126],"Additionally,":[127],"enhance":[129],"understanding":[131],"of":[132,135],"efficiency":[134],"MLLM":[136,160],"UAV":[138,149,171],"tasks,":[139],"delves":[142],"into":[143],"prompt":[144],"templates":[146],"tailored":[147],"task":[150,163],"decomposition.":[151],"Through":[152],"experimental":[153],"demonstrations,":[154],"we":[155],"showcase":[156],"prompt-tuned":[159],"exhibits":[161],"efficient":[162],"decomposition":[164],"capabilities":[167],"handling":[169],"tasks.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}