{"id":"https://openalex.org/W7138042012","doi":"https://doi.org/10.1609/aaai.v40i22.38885","title":"History-Enhanced Two-Stage Transformer for Aerial Vision-and-Language Navigation","display_name":"History-Enhanced Two-Stage Transformer for Aerial Vision-and-Language Navigation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138042012","doi":"https://doi.org/10.1609/aaai.v40i22.38885"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i22.38885","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38885","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38885/42847","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38885/42847","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080106267","display_name":"Xichen Ding","orcid":"https://orcid.org/0009-0003-5649-058X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xichen Ding","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102589918","display_name":"Jianzhe Gao","orcid":"https://orcid.org/0000-0002-0215-5984"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhe Gao","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011457041","display_name":"Cong Pan","orcid":"https://orcid.org/0000-0001-5959-4294"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Pan","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129724053","display_name":"Wenguan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenguan Wang","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129644021","display_name":"Jie Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Qin","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080106267"],"corresponding_institution_ids":["https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33432836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"22","first_page":"18225","last_page":"18233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8605999946594238,"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":0.8605999946594238,"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":0.051500000059604645,"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":0.04479999840259552,"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/grid","display_name":"Grid","score":0.5522000193595886},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49050000309944153},{"id":"https://openalex.org/keywords/grid-reference","display_name":"Grid reference","score":0.34529998898506165},{"id":"https://openalex.org/keywords/navigation-system","display_name":"Navigation system","score":0.3228999972343445},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.31439998745918274},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3122999966144562},{"id":"https://openalex.org/keywords/mobile-robot-navigation","display_name":"Mobile robot navigation","score":0.29339998960494995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124000191688538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6093999743461609},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.572700023651123},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5522000193595886},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49050000309944153},{"id":"https://openalex.org/C156172958","wikidata":"https://www.wikidata.org/wiki/Q3438407","display_name":"Grid reference","level":4,"score":0.34529998898506165},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.29339998960494995},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28769999742507935},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C2983008078","wikidata":"https://www.wikidata.org/wiki/Q863495","display_name":"Grid cell","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C2989549987","wikidata":"https://www.wikidata.org/wiki/Q350882","display_name":"Route planning","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C2778761605","wikidata":"https://www.wikidata.org/wiki/Q3565782","display_name":"Navigational aid","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i22.38885","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38885","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38885/42847","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.v40i22.38885","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38885","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38885/42847","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":[{"score":0.8131124377250671,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138042012.pdf","grobid_xml":"https://content.openalex.org/works/W7138042012.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Aerial":[0,6],"Vision-and-Language":[1],"Navigation":[2],"(AVLN)":[3],"requires":[4],"Unmanned":[5],"Vehicle":[7],"(UAV)":[8],"agents":[9,35],"to":[10,42,99,121],"localize":[11],"targets":[12],"in":[13],"large-scale":[14],"urban":[15],"environments":[16],"based":[17],"on":[18,126],"linguistic":[19],"instructions.":[20],"While":[21],"successful":[22],"navigation":[23,68],"demands":[24],"both":[25],"global":[26],"environmental":[27],"reasoning":[28],"and":[29,81],"local":[30],"scene":[31,111],"comprehension,":[32],"existing":[33],"UAV":[34],"typically":[36],"adopt":[37],"mono-granularity":[38],"frameworks":[39],"that":[40,132],"struggle":[41],"balance":[43],"these":[44],"two":[45,63],"aspects.":[46],"To":[47],"address":[48],"this":[49,51],"limitation,":[50],"work":[52],"proposes":[53],"a":[54,66,93,105],"History-Enhanced":[55],"Two-Stage":[56],"Transformer":[57],"(HETT)":[58],"framework,":[59],"which":[60],"integrates":[61],"the":[62,114,127,144],"aspects":[64],"through":[65],"coarse-to-fine":[67],"pipeline.":[69],"Specifically,":[70],"HETT":[71,133],"first":[72],"predicts":[73],"coarse-grained":[74],"target":[75],"positions":[76],"by":[77],"fusing":[78],"spatial":[79,107],"landmarks":[80],"historical":[82,94],"context,":[83],"then":[84],"refines":[85],"actions":[86],"via":[87],"fine-grained":[88],"visual":[89,102],"analysis.":[90],"In":[91],"addition,":[92],"grid":[95],"map":[96],"is":[97],"designed":[98],"dynamically":[100],"aggregate":[101],"features":[103],"into":[104],"structured":[106],"memory,":[108],"enhancing":[109],"comprehensive":[110],"awareness.":[112],"Additionally,":[113],"CityNav":[115,129],"dataset":[116,130],"annotations":[117],"are":[118],"manually":[119],"refined":[120,128],"enhance":[122],"data":[123],"quality.":[124],"Experiments":[125],"show":[131],"delivers":[134],"significant":[135],"performance":[136],"gains,":[137],"while":[138],"extensive":[139],"ablation":[140],"studies":[141],"further":[142],"verify":[143],"effectiveness":[145],"of":[146],"each":[147],"component.":[148]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}
