{"id":"https://openalex.org/W4415538112","doi":"https://doi.org/10.1145/3746027.3754498","title":"AeroDuo: Aerial Duo for UAV-based Vision and Language Navigation","display_name":"AeroDuo: Aerial Duo for UAV-based Vision and Language Navigation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538112","doi":"https://doi.org/10.1145/3746027.3754498"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754498","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754498","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":"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/A5113409491","display_name":"Ruipu Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruipu Wu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-7763-0111","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yige Zhang","orcid":"https://orcid.org/0009-0006-4757-8629"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yige Zhang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-4757-8629","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730367","display_name":"Jinyu Chen","orcid":"https://orcid.org/0009-0002-7106-8312"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyu Chen","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-7106-8312","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103005183","display_name":"Linjiang Huang","orcid":"https://orcid.org/0000-0001-9701-6487"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linjiang Huang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9701-6487","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042265409","display_name":"Shifeng Zhang","orcid":"https://orcid.org/0000-0003-3109-5770"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shifeng Zhang","raw_affiliation_strings":["Sangfor Technologies Inc., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3109-5770","affiliations":[{"raw_affiliation_string":"Sangfor Technologies Inc., Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085431083","display_name":"Zhou Xu","orcid":"https://orcid.org/0009-0002-7695-5834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Zhou","raw_affiliation_strings":["Sangfor Technologies Inc., Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-7695-5834","affiliations":[{"raw_affiliation_string":"Sangfor Technologies Inc., Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5224-8647","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9180-2935","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2576","last_page":"2585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9986000061035156,"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":0.9954000115394592,"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":0.6664999723434448},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6068000197410583},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.58160001039505},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.520799994468689},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4754999876022339},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4722000062465668},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.40450000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739999890327454},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6664999723434448},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6068000197410583},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.58160001039505},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5317000150680542},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5149999856948853},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4722000062465668},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.39969998598098755},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3605000078678131},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26339998841285706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754498","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754498","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":[{"id":"https://openalex.org/G4919710511","display_name":null,"funder_award_id":"62461160308, U23B2010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1969483458","https://openalex.org/W2615547864","https://openalex.org/W2788239209","https://openalex.org/W2963110888","https://openalex.org/W2963800628","https://openalex.org/W2991625383","https://openalex.org/W3109085430","https://openalex.org/W3132655151","https://openalex.org/W3172675210","https://openalex.org/W3204524295","https://openalex.org/W4304097971","https://openalex.org/W4385570443","https://openalex.org/W4390100400"],"related_works":[],"abstract_inverted_index":{"Aerial":[0,11],"Vision-and-Language":[1],"Navigation":[2],"(VLN)":[3],"is":[4,40],"an":[5,143,222],"emerging":[6],"task":[7,76],"that":[8,219],"enables":[9],"Unmanned":[10],"Vehicles":[12],"(UAVs)":[13],"to":[14,27,148,213,230],"navigate":[15],"outdoor":[16],"environments":[17,157],"using":[18],"natural":[19],"language":[20,134,182],"instructions":[21],"and":[22,31,42,100,112,142,158,199,207,245],"visual":[23],"cues.":[24],"However,":[25],"due":[26],"the":[28,53,110,115,119,151,175,189,235],"extended":[29],"trajectories":[30],"complex":[32],"maneuverability":[33],"of":[34,55,114,237],"UAVs,":[35],"achieving":[36],"reliable":[37],"UAV-VLN":[38],"performance":[39],"challenging":[41],"often":[43],"requires":[44],"human":[45],"intervention":[46],"or":[47],"overly":[48],"detailed":[49],"instructions.":[50,135],"To":[51,108,161],"harness":[52],"advantages":[54],"UAVs'":[56],"high":[57],"mobility,":[58],"which":[59],"could":[60],"provide":[61],"multi-grained":[62],"perspectives,":[63],"while":[64,188],"maintaining":[65],"a":[66,74,92,101,121,168,179,193],"manageable":[67],"motion":[68],"space":[69],"for":[70,96,185,197],"learning,":[71],"we":[72,117,166],"introduce":[73],"novel":[75,156],"called":[77],"Dual-Altitude":[78],"UAV":[79,94,103,127,177,191],"Collaborative":[80],"VLN":[81,171],"(DuAl-VLN).":[82],"In":[83],"this":[84],"task,":[85],"two":[86,203],"UAVs":[87,204],"operate":[88],"at":[89],"distinct":[90],"altitudes:":[91],"high-altitude":[93,176],"responsible":[95],"broad":[97],"environmental":[98,242],"reasoning,":[99,187],"low-altitude":[102,190],"tasked":[104],"with":[105,132],"precise":[106],"navigation.":[107],"support":[109],"training":[111],"evaluation":[113],"DuAl-VLN,":[116],"construct":[118],"HaL-13k,":[120],"dataset":[122,137],"comprising":[123],"13,838":[124],"collaborative":[125,170],"high-low":[126],"demonstration":[128],"trajectories,":[129],"each":[130],"paired":[131],"target-oriented":[133],"This":[136],"includes":[138],"both":[139],"unseen":[140,144],"maps":[141],"object":[145],"validation":[146],"set":[147],"systematically":[149],"evaluate":[150],"model's":[152],"generalization":[153],"capabilities":[154],"across":[155],"unfamiliar":[159],"targets.":[160],"consolidate":[162],"their":[163],"complementary":[164],"strengths,":[165],"propose":[167],"dual-UAV":[169],"framework,":[172],"AeroDuo,":[173],"where":[174],"integrates":[178],"multimodal":[180],"large":[181],"model":[183],"(Pilot-LLM)":[184],"target":[186,200],"employs":[192],"lightweight":[194],"multi-stage":[195],"policy":[196],"navigation":[198],"grounding.":[201],"The":[202],"work":[205],"collaboratively":[206],"only":[208],"exchange":[209],"minimal":[210],"coordinate":[211],"information":[212],"ensure":[214],"efficiency.":[215],"Experimental":[216],"results":[217],"indicate":[218],"AeroDuo":[220],"achieves":[221],"evident":[223],"9.71%":[224],"improvement":[225],"in":[226,240],"success":[227],"rates":[228],"compared":[229],"existing":[231],"single-UAV":[232],"methods,":[233],"demonstrating":[234],"effectiveness":[236],"dual-altitude":[238],"collaboration":[239],"balancing":[241],"coverage,":[243],"precision,":[244],"operational":[246],"autonomy.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-25T00:00:00"}