{"id":"https://openalex.org/W7138449667","doi":"https://doi.org/10.1609/aaai.v40i22.38898","title":"Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology","display_name":"Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138449667","doi":"https://doi.org/10.1609/aaai.v40i22.38898"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i22.38898","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38898","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i22.38898","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015360017","display_name":"Yatai Ji","orcid":"https://orcid.org/0009-0000-8096-2928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yatai Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129728767","display_name":"Zhengqiu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengqiu Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129743944","display_name":"Yong Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124230999","display_name":"Beidan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beidan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129690216","display_name":"Chen Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129743439","display_name":"Yihao Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihao Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047122131","display_name":"Sihang Qiu","orcid":"https://orcid.org/0000-0001-7372-5203"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sihang Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129666426","display_name":"Yue Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100610160","display_name":"Quanjun Yin","orcid":"https://orcid.org/0000-0002-1207-8660"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quanjun Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"22","first_page":"18342","last_page":"18350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5565000176429749,"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":0.5565000176429749,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.19460000097751617,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.057500001043081284,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6651999950408936},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6444000005722046},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.4603999853134155},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4180999994277954},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.39890000224113464},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.39629998803138733},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38029998540878296},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.37209999561309814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979000210762024},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6651999950408936},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6444000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5906999707221985},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40209999680519104},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3431999981403351},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.33230000734329224},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i22.38898","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38898","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i22.38898","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38898","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.8220389485359192}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Aerial":[0,11],"Visual":[1],"Object":[2],"Search":[3],"(AVOS)":[4],"tasks":[5,73],"in":[6,32,197,223],"urban":[7,34,68],"environments":[8,35],"require":[9],"Unmanned":[10],"Vehicles":[12],"(UAVs)":[13],"to":[14,37,82,115,169],"autonomously":[15],"search":[16,65,86,202],"for":[17,63,126,151,159,183,220],"and":[18,44,51,117,154,175,201,212],"identify":[19],"target":[20,152,226],"objects":[21,174],"based":[22,146],"on":[23,121,147,189],"visual":[24,122,225],"inputs":[25],"without":[26],"external":[27],"guidance.":[28],"Existing":[29],"approaches":[30],"struggle":[31],"complex":[33],"due":[36],"redundant":[38],"semantic":[39,137,148],"processing,":[40],"similar":[41,173],"object":[42,79],"ambiguity,":[43],"the":[45,53,59,90,218],"exploration-exploitation":[46,161],"dilemma.":[47],"To":[48,88],"advance":[49],"research":[50],"support":[52],"AVOS":[54,91],"task,":[55,92],"we":[56,93,164],"introduce":[57],"CityAVOS,":[58],"first":[60],"benchmark":[61],"dataset":[62],"autonomous":[64],"of":[66,74],"static":[67],"objects.":[69,127],"It":[70],"features":[71],"2,420":[72],"varying":[75],"difficulty":[76],"across":[77],"six":[78],"categories,":[80],"designed":[81],"rigorously":[83],"evaluate":[84],"UAV":[85,113],"strategies.":[87],"solve":[89],"also":[94],"propose":[95,165],"PRPSearcher":[96,129,193],"(Perception-Reasoning-Planning":[97],"Searcher),":[98],"a":[99,112,142,155,166],"novel":[100],"agentic":[101],"method":[102],"powered":[103],"by":[104],"multi-modal":[105],"large":[106],"language":[107],"models":[108],"(MLLMs)":[109],"that":[110,192],"enables":[111],"agent":[114],"think":[116],"reason":[118],"like":[119],"humans":[120],"cues":[123],"when":[124],"searching":[125],"Specifically,":[128],"constructs":[130],"three":[131],"specialized":[132],"maps:":[133],"an":[134,177],"object-centric":[135],"dynamic":[136],"map":[138,145,158],"enhancing":[139],"spatial":[140],"perception,":[141],"3D":[143,156],"cognitive":[144],"\"attraction\"":[149],"values":[150],"reasoning,":[153],"uncertainty":[157],"balanced":[160],"search.":[162,227],"Moreover,":[163],"denoising":[167],"mechanism":[168,182],"mitigate":[170],"interference":[171],"from":[172],"design":[176],"Inspiration":[178],"Promote":[179],"Thought":[180],"prompting":[181],"adaptive":[184],"action":[185],"planning.":[186],"Experimental":[187],"results":[188],"CityAVOS":[190],"demonstrate":[191],"surpasses":[194],"existing":[195],"baselines":[196],"both":[198],"success":[199],"rate":[200],"efficiency":[203],"(on":[204],"average:":[205],"+37.69%":[206],"SR,":[207],"+28.96%":[208],"SPL,":[209],"-30.69%":[210],"MSS,":[211],"-46.40%":[213],"NE).":[214],"Our":[215],"work":[216],"paves":[217],"way":[219],"future":[221],"advances":[222],"embodied":[224]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}