{"id":"https://openalex.org/W7225388166","doi":"https://doi.org/10.1145/3860544","title":"AeroGuide: Grounded Vision-Language Navigation in Aerial Environments","display_name":"AeroGuide: Grounded Vision-Language Navigation in Aerial Environments","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225388166","doi":"https://doi.org/10.1145/3860544"},"language":"en","primary_location":{"id":"doi:10.1145/3860544","doi":"https://doi.org/10.1145/3860544","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3860544","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3860544?download=true","source":{"id":"https://openalex.org/S4387288942","display_name":"ACM Journal on Autonomous Transportation Systems","issn_l":"2833-0528","issn":["2833-0528"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-c","cwts-core"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Journal on Autonomous Transportation Systems","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3860544?download=true","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101882843","display_name":"Abhinav Upadhyay","orcid":"https://orcid.org/0000-0001-8201-5959","observed_orcids":["https://orcid.org/0000-0001-8201-5959"]},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhinav Upadhyay","raw_affiliation_strings":["Computer Science & Engineering, Indian Institute of Technology Ropar"],"raw_orcid":"https://orcid.org/0000-0001-8201-5959","affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, Indian Institute of Technology Ropar","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101642653","display_name":"Siddharth Singh","orcid":"https://orcid.org/0009-0007-3583-8603","observed_orcids":["https://orcid.org/0009-0007-3583-8603","https://orcid.org/0009-0001-7036-071X"]},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Siddharth Singh","raw_affiliation_strings":["Computer Science & Engineering, Indian Institute of Technology Ropar"],"raw_orcid":"https://orcid.org/0009-0007-3583-8603","affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, Indian Institute of Technology Ropar","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113065796","display_name":"Satvik Srivastava","orcid":"https://orcid.org/0009-0002-0096-9068","observed_orcids":["https://orcid.org/0009-0002-0096-9068","https://orcid.org/0009-0002-9137-2223"]},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Satvik Srivastava","raw_affiliation_strings":["Computer Science & Engineering, Indian Institute of Technology Ropar"],"raw_orcid":"https://orcid.org/0009-0002-9137-2223","affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, Indian Institute of Technology Ropar","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161051712","display_name":"Tanya Khanna","orcid":"https://orcid.org/0009-0009-0107-4160","observed_orcids":["https://orcid.org/0009-0009-0107-4160"]},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanya Khanna","raw_affiliation_strings":["Computer Science & Engineering, Indian Institute of Technology Ropar"],"raw_orcid":"https://orcid.org/0009-0009-0107-4160","affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, Indian Institute of Technology Ropar","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161006188","display_name":"Ashutosh Pandey","orcid":"https://orcid.org/0009-0001-1511-3126","observed_orcids":["https://orcid.org/0009-0001-1511-3126"]},"institutions":[{"id":"https://openalex.org/I200813526","display_name":"Harman (United Kingdom)","ror":"https://ror.org/05fzcfb55","country_code":"GB","type":"company","lineage":["https://openalex.org/I200813526","https://openalex.org/I2250650973","https://openalex.org/I4210101778","https://openalex.org/I4210131281"]},{"id":"https://openalex.org/I4210131103","display_name":"Harman (Germany)","ror":"https://ror.org/02hnr5x72","country_code":"DE","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778","https://openalex.org/I4210131103","https://openalex.org/I4210131281"]},{"id":"https://openalex.org/I4210131281","display_name":"Harman (United States)","ror":"https://ror.org/03yfbaq97","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778","https://openalex.org/I4210131281"]}],"countries":["DE","GB","US"],"is_corresponding":false,"raw_author_name":"Ashutosh Pandey","raw_affiliation_strings":["AI, CoE, HARMAN International"],"raw_orcid":"https://orcid.org/0009-0001-1511-3126","affiliations":[{"raw_affiliation_string":"AI, CoE, HARMAN International","institution_ids":["https://openalex.org/I200813526","https://openalex.org/I4210131103","https://openalex.org/I4210131281"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003320528","display_name":"Shashi Shekhar Jha","orcid":"https://orcid.org/0000-0002-1375-2266","observed_orcids":["https://orcid.org/0000-0002-1375-2266"]},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shashi Jha","raw_affiliation_strings":["Computer Science & Engineering, Indian Institute of Technology Ropar"],"raw_orcid":"https://orcid.org/0000-0002-1375-2266","affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, Indian Institute of Technology Ropar","institution_ids":["https://openalex.org/I119241673"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7378000020980835,"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":0.7378000020980835,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1266999989748001,"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":0.04740000143647194,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/uav-navigation","display_name":"UAV navigation","score":0.859000027179718},{"id":"https://openalex.org/keywords/natural-language-instructions","display_name":"natural language instructions","score":0.7770000100135803},{"id":"https://openalex.org/keywords/reasoning-distillation","display_name":"reasoning distillation","score":0.8619999885559082},{"id":"https://openalex.org/keywords/qwen3-vl","display_name":"Qwen3-VL","score":0.8130000233650208},{"id":"https://openalex.org/keywords/spatial-reasoning","display_name":"spatial reasoning","score":0.5830000042915344}],"concepts":[{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.8422999978065491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6471999883651733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5503000020980835},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4708999991416931},{"id":"https://openalex.org/C133214962","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial photography","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.3465999960899353},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3860544","doi":"https://doi.org/10.1145/3860544","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3860544","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3860544?download=true","source":{"id":"https://openalex.org/S4387288942","display_name":"ACM Journal on Autonomous Transportation Systems","issn_l":"2833-0528","issn":["2833-0528"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-c","cwts-core"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Journal on Autonomous Transportation Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3860544","doi":"https://doi.org/10.1145/3860544","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3860544","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3860544?download=true","source":{"id":"https://openalex.org/S4387288942","display_name":"ACM Journal on Autonomous Transportation Systems","issn_l":"2833-0528","issn":["2833-0528"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-c","cwts-core"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Journal on Autonomous Transportation Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225388166.pdf","grobid_xml":"https://content.openalex.org/works/W7225388166.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W4385570907","https://openalex.org/W4390872901","https://openalex.org/W4390873312","https://openalex.org/W4391631327","https://openalex.org/W4402353981","https://openalex.org/W4406809220","https://openalex.org/W4407123610","https://openalex.org/W4409049124","https://openalex.org/W4409581185","https://openalex.org/W4412889756","https://openalex.org/W4414050442","https://openalex.org/W4414322676","https://openalex.org/W4415314119","https://openalex.org/W4415538112","https://openalex.org/W4415539729","https://openalex.org/W4415798545","https://openalex.org/W4416036728","https://openalex.org/W4416780398","https://openalex.org/W4417355699","https://openalex.org/W4417513084","https://openalex.org/W7083697494","https://openalex.org/W7102696117","https://openalex.org/W7117670051","https://openalex.org/W7119479350","https://openalex.org/W7127370489","https://openalex.org/W7133224126","https://openalex.org/W7133233472","https://openalex.org/W7135039250","https://openalex.org/W7138173364","https://openalex.org/W7138404632","https://openalex.org/W7138448999","https://openalex.org/W7153354821","https://openalex.org/W7154595386","https://openalex.org/W7160169212","https://openalex.org/W7220999220"],"related_works":["https://openalex.org/W7164020514","https://openalex.org/W4411996937","https://openalex.org/W4416591427","https://openalex.org/W7153187043","https://openalex.org/W4390872901","https://openalex.org/W7134831559","https://openalex.org/W4413277612","https://openalex.org/W7223656506","https://openalex.org/W4417355699","https://openalex.org/W7223307626"],"abstract_inverted_index":{"Aerial":[0,15],"vision-language":[1,47],"navigation":[2,41,143,181],"(VLN)":[3],"requires":[4,42],"a":[5,34,65,150],"UAV":[6,24,90],"to":[7,52,129,148,173],"follow":[8],"natural":[9],"language":[10],"instructions":[11],"from":[12,57,146],"visual":[13,55,83,164],"observations.":[14,61],"VLN":[16,22,68],"is":[17,115,187],"more":[18],"challenging":[19],"than":[20,109],"ground-level":[21],"because":[23],"observations":[25],"cover":[26],"large":[27],"outdoor":[28],"areas,":[29],"landmarks":[30],"often":[31,50],"occupy":[32],"only":[33],"small":[35],"part":[36],"of":[37,179],"the":[38,87,138,155,177],"image,":[39],"and":[40,92,125,134,166],"complex":[43],"spatial":[44],"reasoning.":[45],"General-purpose":[46],"models":[48],"(VLMs)":[49],"struggle":[51],"identify":[53],"instruction-relevant":[54,82],"evidence":[56,107],"such":[58],"dense":[59],"aerial":[60,67,183],"We":[62],"propose":[63],"AeroGuide,":[64],"grounded":[66,131,180],"framework":[69],"built":[70],"on":[71,86],"Qwen3-VL.":[72],"AeroGuide":[73,96,141],"introduces":[74],"Navigation-conditioned":[75],"Visual":[76],"Token":[77],"Routing":[78],"(NVTR),":[79],"which":[80],"selects":[81],"tokens":[84],"conditioned":[85],"current":[88],"observation,":[89],"pose,":[91],"temporal":[93,100,168],"landmark":[94,101,106],"memory.":[95],"maintains":[97],"an":[98],"egocentric":[99],"memory":[102,169],"that":[103,162],"retains":[104],"compact":[105,167],"rather":[108],"full":[110],"historical":[111],"frames.":[112],"The":[113],"model":[114],"trained":[116],"through":[117],"multiple":[118],"phases,":[119],"including":[120],"supervised":[121],"learning,":[122],"reasoning":[123],"distillation,":[124],"simulator-based":[126],"policy":[127],"optimization,":[128],"improve":[130],"action":[132],"prediction":[133],"closed-loop":[135],"navigation.":[136],"On":[137],"OpenFly":[139],"benchmark,":[140],"improves":[142],"success":[144],"rate":[145],"34.3%":[147],"45.1%,":[149],"31.5%":[151],"relative":[152],"improvement":[153],"over":[154],"best-performing":[156],"prior":[157],"baseline.":[158],"Ablation":[159],"studies":[160],"show":[161],"explicit":[163],"grounding":[165],"are":[170],"key":[171],"contributors":[172],"this":[174],"improvement,":[175],"demonstrating":[176],"effectiveness":[178],"for":[182],"VLN.":[184],"Project":[185],"page":[186],"available":[188],"at":[189],"https://aeroguide-frontend-iota.vercel.app/.":[190]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-07T00:00:00"}
