{"id":"https://openalex.org/W4416749722","doi":"https://doi.org/10.1109/iros60139.2025.11247609","title":"SkyVLN: Vision-and-Language Navigation and NMPC Control for UAVs in Urban Environments","display_name":"SkyVLN: Vision-and-Language Navigation and NMPC Control for UAVs in Urban Environments","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749722","doi":"https://doi.org/10.1109/iros60139.2025.11247609"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","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/A5109637357","display_name":"Tianshun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Tianshun Li","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Intelligent Transportation, Hub of Systems,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Intelligent Transportation, Hub of Systems,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120340521","display_name":"Tianyi Huai","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tianyi Huai","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Intelligent Transportation, Hub of Systems,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Intelligent Transportation, Hub of Systems,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011466881","display_name":"Zongjin Li","orcid":"https://orcid.org/0000-0002-8477-6863"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhen Li","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Intelligent Transportation, Hub of Systems,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Intelligent Transportation, Hub of Systems,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101593817","display_name":"Yansheng Gao","orcid":"https://orcid.org/0000-0002-9741-217X"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yichun Gao","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Intelligent Transportation, Hub of Systems,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Intelligent Transportation, Hub of Systems,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040338788","display_name":"Haoang Li","orcid":"https://orcid.org/0000-0002-1576-9408"},"institutions":[{"id":"https://openalex.org/I4210105785","display_name":"Intelligent Systems Research (United States)","ror":"https://ror.org/01reevc91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105785"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Haoang Li","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Intelligent Transportation Thrust and Robotics and Autonomous Systems Thrust, Systems Hub,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Intelligent Transportation Thrust and Robotics and Autonomous Systems Thrust, Systems Hub,China","institution_ids":["https://openalex.org/I4210105785","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062424202","display_name":"Xinhu Zheng","orcid":"https://orcid.org/0000-0002-9898-5543"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I1320758411","display_name":"Entrust","ror":"https://ror.org/01deqjx32","country_code":"GB","type":"other","lineage":["https://openalex.org/I1320758411"]}],"countries":["GB","HK"],"is_corresponding":false,"raw_author_name":"Xinhu Zheng","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Intelligent Transportation Thrust, Systems Hub, Internet of Things Thrust, Information Hub,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Intelligent Transportation Thrust, Systems Hub, Internet of Things Thrust, Information Hub,China","institution_ids":["https://openalex.org/I1320758411","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5109637357"],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85421639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"17199","last_page":"17206"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.37869998812675476,"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":0.37869998812675476,"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":0.21850000321865082,"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":0.147599995136261,"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/trajectory","display_name":"Trajectory","score":0.6877999901771545},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.637499988079071},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.4871000051498413},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.43230000138282776},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.37940001487731934},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3785000145435333},{"id":"https://openalex.org/keywords/mobile-robot-navigation","display_name":"Mobile robot navigation","score":0.3393999934196472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610999941825867},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6877999901771545},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.637499988079071},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.4871000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47450000047683716},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4318000078201294},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.37940001487731934},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3774999976158142},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.3393999934196472},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.3041999936103821},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2687000036239624}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2539108539","https://openalex.org/W2618092744","https://openalex.org/W2963800628","https://openalex.org/W2979727876","https://openalex.org/W3019634450","https://openalex.org/W3081168214","https://openalex.org/W3100923070","https://openalex.org/W3109085430","https://openalex.org/W3174708786","https://openalex.org/W4220736817","https://openalex.org/W4281736204","https://openalex.org/W4309651816","https://openalex.org/W4386590944","https://openalex.org/W4387918101","https://openalex.org/W4393154152","https://openalex.org/W4393906134","https://openalex.org/W4402944034","https://openalex.org/W4405624835","https://openalex.org/W4405907293","https://openalex.org/W4407950247","https://openalex.org/W4409217930"],"related_works":[],"abstract_inverted_index":{"Unmanned":[0],"Aerial":[1],"Vehicles":[2],"(UAVs)":[3],"have":[4],"emerged":[5],"as":[6],"versatile":[7],"tools":[8],"across":[9],"various":[10],"sectors,":[11],"driven":[12],"by":[13],"their":[14],"mobility":[15],"and":[16,58,72,86,104,123,143,157,162],"adaptability.":[17],"This":[18],"paper":[19],"introduces":[20],"SkyVLN,":[21],"a":[22,76,82,87,132],"novel":[23],"framework":[24,109],"integrating":[25],"vision-and-language":[26],"navigation":[27,45,78,154],"(VLN)":[28],"with":[29,69,81],"Nonlinear":[30],"Model":[31],"Predictive":[32],"Control":[33],"(NMPC)":[34],"to":[35,53,63,97],"enhance":[36],"UAV":[37,96],"autonomy":[38],"in":[39,160],"complex":[40],"urban":[41,135,145],"environments.":[42,164],"Unlike":[43],"traditional":[44],"methods,":[46],"SkyVLN":[47,151],"leverages":[48],"Large":[49],"Language":[50],"Models":[51],"(LLMs)":[52],"interpret":[54],"natural":[55],"language":[56],"instructions":[57],"visual":[59],"observations,":[60],"enabling":[61],"UAVs":[62],"navigate":[64],"through":[65],"dynamic":[66,116,144],"3D":[67,134],"spaces":[68],"improved":[70],"accuracy":[71],"robustness.":[73],"We":[74],"present":[75],"multimodal":[77],"agent":[79],"equipped":[80],"fine-grained":[83],"spatial":[84,99],"verbalizer":[85],"history":[88],"path":[89],"memory":[90],"mechanism.":[91],"These":[92],"components":[93],"allow":[94],"the":[95],"disambiguate":[98],"contexts,":[100],"handle":[101],"ambiguous":[102],"instructions,":[103],"backtrack":[105],"when":[106],"necessary.":[107],"The":[108],"also":[110],"incorporates":[111],"an":[112],"NMPC":[113],"module":[114],"for":[115],"obstacle":[117],"avoidance,":[118],"ensuring":[119],"precise":[120],"trajectory":[121],"tracking":[122],"collision":[124],"prevention.":[125],"To":[126],"validate":[127],"our":[128],"approach,":[129],"we":[130],"developed":[131],"high-fidelity":[133],"simulation":[136],"environment":[137],"using":[138],"AirSim,":[139],"featuring":[140],"realistic":[141],"imagery":[142],"elements.":[146],"Extensive":[147],"experiments":[148],"demonstrate":[149],"that":[150],"significantly":[152],"improves":[153],"success":[155],"rates":[156],"efficiency,":[158],"particularly":[159],"new":[161],"unseen":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}