{"id":"https://openalex.org/W4415539729","doi":"https://doi.org/10.1145/3746027.3758251","title":"UAV-ON: A Benchmark for Open-World Object Goal Navigation with Aerial Agents","display_name":"UAV-ON: A Benchmark for Open-World Object Goal Navigation with Aerial Agents","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539729","doi":"https://doi.org/10.1145/3746027.3758251"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3758251","doi":"https://doi.org/10.1145/3746027.3758251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758251","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.00288","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043249256","display_name":"Jianqiang Xiao","orcid":"https://orcid.org/0000-0002-5054-0318","observed_orcids":["https://orcid.org/0000-0002-5054-0318"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Xiao","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5054-0318","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuexuan Sun","orcid":"https://orcid.org/0009-0000-0692-7470","observed_orcids":["https://orcid.org/0009-0000-0692-7470"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexuan Sun","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0000-0692-7470","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101129491","display_name":"Yixin Shao","orcid":"https://orcid.org/0009-0006-1546-7801","observed_orcids":["https://orcid.org/0009-0006-1546-7801"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Shao","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-1546-7801","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120132148","display_name":"Boxi Gan","orcid":"https://orcid.org/0009-0002-1134-1575","observed_orcids":["https://orcid.org/0009-0002-1134-1575"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boxi Gan","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-1134-1575","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079973893","display_name":"Rongqiang Liu","orcid":"https://orcid.org/0000-0003-3731-6650","observed_orcids":["https://orcid.org/0000-0003-3731-6650"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongqiang Liu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3731-6650","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107836821","display_name":"Ye Wu","orcid":"https://orcid.org/0009-0000-3997-5524","observed_orcids":["https://orcid.org/0009-0000-3997-5524"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjin Wu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0000-3997-5524","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075938343","display_name":"Weili Guan","orcid":"https://orcid.org/0000-0002-5658-5509","observed_orcids":["https://orcid.org/0000-0002-5658-5509"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weili Guan","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5658-5509","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101697908","display_name":"Xiang Hua Deng","orcid":"https://orcid.org/0000-0003-3963-509X","observed_orcids":["https://orcid.org/0000-0003-3963-509X"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Deng","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3963-509X","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":15.0641,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.99374353,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13023","last_page":"13029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8432999849319458,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8432999849319458,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.04859999939799309,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T13855","display_name":"Aerospace Engineering and Control Systems","score":0.015399999916553497,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/object-goal-navigation","display_name":"object-goal navigation","score":0.8309999704360962},{"id":"https://openalex.org/keywords/unmanned-aerial-vehicles","display_name":"unmanned aerial vehicles","score":0.8659999966621399},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.6489999890327454},{"id":"https://openalex.org/keywords/3d-navigation","display_name":"3D navigation","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6176999807357788},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5472999811172485},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.475600004196167},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3746027.3758251","doi":"https://doi.org/10.1145/3746027.3758251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758251","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},{"id":"pmh:oai:arXiv.org:2508.00288","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.00288","pdf_url":"https://arxiv.org/pdf/2508.00288","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.00288","doi":"https://doi.org/10.48550/arxiv.2508.00288","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.00288","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.00288","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.00288","pdf_url":"https://arxiv.org/pdf/2508.00288","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7614402873","display_name":null,"funder_award_id":"62406092","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415539729.pdf","grobid_xml":"https://content.openalex.org/works/W4415539729.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2060303868","https://openalex.org/W2587548043","https://openalex.org/W2615547864","https://openalex.org/W2782715402","https://openalex.org/W3017177456","https://openalex.org/W3037849673","https://openalex.org/W3038460818","https://openalex.org/W3140673083","https://openalex.org/W3201759799","https://openalex.org/W3206795908","https://openalex.org/W4223954537","https://openalex.org/W4285151170","https://openalex.org/W4308731068","https://openalex.org/W4383108519","https://openalex.org/W4387092464","https://openalex.org/W4390872901"],"related_works":["https://openalex.org/W7214889365","https://openalex.org/W7119479350","https://openalex.org/W7127317677","https://openalex.org/W4403363603","https://openalex.org/W7163696941","https://openalex.org/W4390872901","https://openalex.org/W4415332570","https://openalex.org/W7138448999","https://openalex.org/W7212038424","https://openalex.org/W7160169212"],"abstract_inverted_index":{"Aerial":[0,155],"navigation":[1,21,189],"is":[2],"a":[3,54,159],"fundamental":[4],"yet":[5],"underexplored":[6],"capability":[7],"in":[8,15,65,83,180,208],"embodied":[9],"intelligence,":[10],"enabling":[11],"agents":[12,64,69],"to":[13,196],"operate":[14,70],"large-scale,":[16],"unstructured":[17],"environments":[18,91],"where":[19,68],"traditional":[20],"paradigms":[22],"fall":[23],"short.":[24],"However,":[25],"most":[26],"existing":[27],"research":[28,198],"follows":[29],"the":[30,147,184],"Vision-and-Language":[31],"Navigation":[32,60],"(VLN)":[33],"paradigm,":[34],"which":[35],"heavily":[36],"depends":[37],"on":[38,72,78,199],"sequential":[39],"linguistic":[40],"instructions,":[41],"limiting":[42],"its":[43],"scalability":[44],"and":[45,96,103,123,138,190],"autonomy.":[46],"To":[47,145],"address":[48],"this":[49,181],"gap,":[50],"we":[51,149],"introduce":[52],"UAV-ON,":[53],"benchmark":[55],"for":[56,142,169],"large-scale":[57],"Object":[58],"Goal":[59],"(ObjectNav)":[61],"by":[62,114,204],"aerial":[63,143,188],"open-world":[66],"environments,":[67],"based":[71],"high-level":[73],"semantic":[74,94,133,191,205],"goals":[75],"without":[76],"relying":[77],"detailed":[79],"instructional":[80],"guidance":[81],"as":[82,132],"VLN.":[84],"UAV-ON":[85,194],"comprises":[86],"14":[87],"high-fidelity":[88],"Unreal":[89],"Engine":[90],"with":[92,166],"diverse":[93],"regions":[95],"complex":[97,139,209],"spatial":[98],"layouts,":[99],"covering":[100],"urban,":[101],"natural,":[102],"mixed-use":[104],"settings.":[105],"It":[106],"defines":[107],"1270":[108],"annotated":[109],"target":[110],"objects,":[111],"each":[112],"characterized":[113],"an":[115],"instance-level":[116],"instruction":[117,164],"that":[118,162,176],"encodes":[119],"category,":[120],"physical":[121],"footprint,":[122],"visual":[124],"descriptors,":[125],"allowing":[126],"grounded":[127],"reasoning.":[128],"These":[129],"instructions":[130],"serve":[131],"goals,":[134],"introducing":[135],"realistic":[136],"ambiguity":[137],"reasoning":[140],"challenges":[141,186],"agents.":[144],"evaluate":[146],"benchmark,":[148],"implement":[150],"several":[151],"baseline":[152],"methods,":[153],"including":[154],"ObjectNav":[156],"Agent":[157],"(AOA),":[158],"modular":[160],"policy":[161],"integrates":[163],"semantics":[165],"egocentric":[167],"observations":[168],"long-horizon,":[170],"goal-directed":[171],"exploration.":[172],"Empirical":[173],"results":[174],"show":[175],"all":[177],"baselines":[178],"struggle":[179],"setting,":[182],"highlighting":[183],"compounded":[185],"of":[187],"goal":[192,206],"grounding.":[193],"aims":[195],"advance":[197],"scalable":[200],"UAV":[201],"autonomy":[202],"driven":[203],"descriptions":[207],"real-world":[210],"environments.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2025-10-25T00:00:00"}
