{"id":"https://openalex.org/W7138866553","doi":"https://doi.org/10.1109/globecom59602.2025.11431772","title":"MauBa: A Multi-Agent Coordination Framework for Vision-Language-Guided Zero-Shot Control of Unmanned Aerial Vehicles","display_name":"MauBa: A Multi-Agent Coordination Framework for Vision-Language-Guided Zero-Shot Control of Unmanned Aerial Vehicles","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7138866553","doi":"https://doi.org/10.1109/globecom59602.2025.11431772"},"language":null,"primary_location":{"id":"doi:10.1109/globecom59602.2025.11431772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom59602.2025.11431772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2025 - 2025 IEEE Global Communications Conference","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/A5129866029","display_name":"Yulin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yulin Zhu","raw_affiliation_strings":["Hosei University,Graduate School of Science and Engineering,Tokyo,Japan,184-8584"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hosei University,Graduate School of Science and Engineering,Tokyo,Japan,184-8584","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130049498","display_name":"Zihan Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zihan Zhao","raw_affiliation_strings":["Hosei University,Graduate School of Science and Engineering,Tokyo,Japan,184-8584"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hosei University,Graduate School of Science and Engineering,Tokyo,Japan,184-8584","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121499895","display_name":"Shilong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shilong Zhang","raw_affiliation_strings":["Hosei University,Graduate School of Science and Engineering,Tokyo,Japan,184-8584"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hosei University,Graduate School of Science and Engineering,Tokyo,Japan,184-8584","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107906906","display_name":"J. Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junzhe Sun","raw_affiliation_strings":["Hosei University,Graduate School of Science and Engineering,Tokyo,Japan,184-8584"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hosei University,Graduate School of Science and Engineering,Tokyo,Japan,184-8584","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121496786","display_name":"Keping Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keping Yu","raw_affiliation_strings":["Hosei University,Graduate School of Science and Engineering,Tokyo,Japan,184-8584"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hosei University,Graduate School of Science and Engineering,Tokyo,Japan,184-8584","institution_ids":["https://openalex.org/I204291657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67702317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6238","last_page":"6243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8826000094413757,"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":0.8826000094413757,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.014700000174343586,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.010700000450015068,"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/task","display_name":"Task (project management)","score":0.650600016117096},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6176000237464905},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.6003000140190125},{"id":"https://openalex.org/keywords/supervisor","display_name":"Supervisor","score":0.5924000144004822},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5163000226020813},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49239999055862427},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4683000147342682},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.38019999861717224},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3785000145435333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770799994468689},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.650600016117096},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6176000237464905},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.6003000140190125},{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.5924000144004822},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49239999055862427},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4453999996185303},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3785000145435333},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C86532276","wikidata":"https://www.wikidata.org/wiki/Q1184065","display_name":"Delegation","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33379998803138733},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.328000009059906},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.31839999556541443},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C92991967","wikidata":"https://www.wikidata.org/wiki/Q7644329","display_name":"Supervisory control","level":3,"score":0.30140000581741333},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globecom59602.2025.11431772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom59602.2025.11431772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2025 - 2025 IEEE Global Communications Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6391874551773071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W4309674289","https://openalex.org/W4383097638","https://openalex.org/W4394828156","https://openalex.org/W4400531953","https://openalex.org/W4402917081","https://openalex.org/W4404612908","https://openalex.org/W4405272725","https://openalex.org/W4415124086","https://openalex.org/W7133224126"],"related_works":[],"abstract_inverted_index":{"While":[0],"prompt-based":[1,135],"methods":[2],"have":[3],"shown":[4],"initial":[5],"potential":[6],"for":[7,55,95,121,125,174],"enabling":[8],"large":[9],"language":[10,73],"models":[11],"(LLMs)":[12],"to":[13,33,37],"control":[14,143],"unmanned":[15],"aerial":[16],"vehicles":[17],"(UAVs),":[18],"they":[19],"suffer":[20],"from":[21],"limited":[22],"flexibility,":[23],"inadequate":[24],"visual":[25,109],"perception,":[26],"and":[27,40,66,70,80,99,105,123,136,142,155],"low":[28],"code":[29,97],"generation":[30],"accuracy\u2014often":[31],"leading":[32],"hallucinated":[34],"outputs":[35],"due":[36],"static":[38],"templates":[39],"rigid":[41],"API":[42,88],"wrappers.":[43],"To":[44],"address":[45],"these":[46],"limitations,":[47],"we":[48],"propose":[49],"MauBa,":[50],"a":[51,86,171],"multi-agent":[52,168],"coordination":[53,154],"framework":[54],"zero-shot":[56],"vision-language":[57,126],"UAVs":[58],"control.":[59],"MauBa":[60,114],"comprises":[61],"three":[62],"collaborative":[63],"agents\u2014Supervisor,":[64],"Coder,":[65],"Tracker\u2014that":[67],"jointly":[68],"decompose":[69],"execute":[71],"natural":[72],"instructions.":[74],"The":[75],"Supervisor":[76],"manages":[77],"task":[78,116,153],"delegation":[79],"dialogue":[81],"context;":[82],"the":[83,100,129,149],"Coder":[84],"utilizes":[85],"vectorized":[87],"knowledge":[89,156],"base":[90],"with":[91],"Retrieval-Augmented":[92],"Generation":[93],"(RAG)":[94],"precise":[96],"synthesis;":[98],"Tracker":[101],"performs":[102],"object":[103],"detection":[104],"spatial":[106],"localization":[107],"via":[108],"grounding.":[110],"Without":[111],"any":[112],"fine-tuning,":[113],"achieves":[115],"success":[117],"rates":[118],"of":[119,152],"93.3%":[120],"language-action":[122],"83.3%":[124],"tasks":[127],"in":[128,139,158,178],"AirSim":[130],"simulation":[131],"environment,":[132],"significantly":[133],"outperforming":[134],"single-agent":[137],"baselines":[138],"both":[140],"accuracy":[141],"robustness.":[144],"Ablation":[145],"studies":[146],"further":[147],"validate":[148],"essential":[150],"role":[151],"retrieval":[157],"ensuring":[159],"reliable":[160],"UAV":[161],"decision-making.":[162],"These":[163],"findings":[164],"suggest":[165],"that":[166],"modular":[167],"collaboration":[169],"offers":[170],"promising":[172],"pathway":[173],"scalable":[175],"multimodal":[176],"reasoning":[177],"real-world":[179],"autonomous":[180],"systems.":[181]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-20T00:00:00"}
