{"id":"https://openalex.org/W7214099059","doi":"https://doi.org/10.48550/arxiv.2609.26007","title":"Skytopia: Monocular Drone Navigation with Action-Conditioned Latent World Models","display_name":"Skytopia: Monocular Drone Navigation with Action-Conditioned Latent World Models","publication_year":2026,"publication_date":"2026-09-22","ids":{"openalex":"https://openalex.org/W7214099059","doi":"https://doi.org/10.48550/arxiv.2609.26007"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.26007","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.26007","pdf_url":"https://arxiv.org/pdf/2609.26007","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.26007","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152563792","display_name":"Yuhang Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhang, Yuhang","raw_affiliation_strings":["Nanyang Technological University , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University , Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005149194","display_name":"Rangya Zhang","orcid":"https://orcid.org/0009-0000-9268-7716","observed_orcids":["https://orcid.org/0009-0000-9268-7716"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhang, Rangya","raw_affiliation_strings":["Nanyang Technological University , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University , Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133184602","display_name":"Yujing Shang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shang, Yujing","raw_affiliation_strings":["Nanyang Technological University , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University , Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152565609","display_name":"Zhuoyuan Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yu, Zhuoyuan","raw_affiliation_strings":["Nanyang Technological University , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University , Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152566327","display_name":"Weiying Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Weiying","raw_affiliation_strings":["Autel US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autel US","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143494222","display_name":"Steven Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Steven","raw_affiliation_strings":["Autel US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autel US","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152564696","display_name":"Qingsong Yan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Qingsong","raw_affiliation_strings":["XGRIDS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"XGRIDS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152504833","display_name":"Chao Yan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Chao","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026643234","display_name":"Mir Feroskhan","orcid":"https://orcid.org/0000-0002-2889-7222","observed_orcids":["https://orcid.org/0000-0002-2889-7222"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Feroskhan, Mir","raw_affiliation_strings":["Nanyang Technological University , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University , Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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":0.00039999998989515007,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.00039999998989515007,"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/world-models","display_name":"world models","score":0.7699999809265137},{"id":"https://openalex.org/keywords/3d-gaussian-splatting","display_name":"3D Gaussian Splatting","score":0.9369999766349792},{"id":"https://openalex.org/keywords/point-goal-navigation","display_name":"point-goal navigation","score":0.9150000214576721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715399980545044},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.7092999815940857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6455000042915344},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5652999877929688},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5317999720573425},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4616999924182892},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.32120001316070557},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.26007","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.26007","pdf_url":"https://arxiv.org/pdf/2609.26007","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.2609.26007","doi":"https://doi.org/10.48550/arxiv.2609.26007","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.26007","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:2609.26007","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.26007","pdf_url":"https://arxiv.org/pdf/2609.26007","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214099059.pdf","grobid_xml":"https://content.openalex.org/works/W7214099059.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W4385430674","https://openalex.org/W4414674749","https://openalex.org/W4416780398","https://openalex.org/W4417261359","https://openalex.org/W4417355699","https://openalex.org/W4417519313","https://openalex.org/W7083292721","https://openalex.org/W7117547654","https://openalex.org/W7127938716","https://openalex.org/W7134941703","https://openalex.org/W7137970561","https://openalex.org/W7143487602","https://openalex.org/W7147281152","https://openalex.org/W7150938507","https://openalex.org/W7160063469","https://openalex.org/W7161556097","https://openalex.org/W7163339952","https://openalex.org/W7163584174","https://openalex.org/W7166695133"],"related_works":["https://openalex.org/W7163696941","https://openalex.org/W7214777444","https://openalex.org/W7204555545","https://openalex.org/W7172429020","https://openalex.org/W7221102694","https://openalex.org/W7221816994","https://openalex.org/W7201881367","https://openalex.org/W7161556097","https://openalex.org/W4416341583","https://openalex.org/W7147336522"],"abstract_inverted_index":{"Monocular":[0],"drone":[1,212],"navigation":[2],"requires":[3],"reaching":[4],"a":[5,12,62,66,98,102,109,210],"goal":[6],"in":[7,80,218],"an":[8,113,144],"unseen":[9],"environment":[10],"from":[11,65,139,150],"single":[13],"forward-facing":[14],"camera,":[15],"which":[16,125],"offers":[17],"few":[18],"cues":[19],"for":[20],"depth":[21],"and":[22,48,118,143,165,171,189,215,222],"scale.":[23],"World":[24],"models":[25],"address":[26],"this":[27],"by":[28],"modelling":[29],"how":[30],"observations":[31],"evolve":[32],"under":[33,101,182],"actions,":[34],"but":[35,73],"they":[36],"are":[37],"built":[38,111],"to":[39,77,96],"be":[40],"executed:":[41],"the":[42,71,74,82,89,119,133,136,140,151,155,161,195,200],"prediction":[43,72,94,156],"is":[44,69,127,163,206],"produced":[45],"at":[46,54],"deployment":[47],"fed":[49],"back":[50],"into":[51],"action":[52,84,159],"generation":[53],"every":[55,180],"control":[56],"step.":[57],"We":[58,105],"argue":[59],"that":[60,148,177],"what":[61],"policy":[63,110,167,205],"needs":[64],"world":[67,116],"model":[68],"not":[70],"representation":[75,134],"required":[76],"produce":[78],"it:":[79],"flight":[81],"executed":[83],"explains":[85],"almost":[86],"all":[87,183],"of":[88,135,199],"change":[90],"between":[91],"observations,":[92],"so":[93],"reduces":[95],"reprojecting":[97],"static":[99],"scene":[100],"known":[103],"displacement.":[104],"therefore":[106],"introduce":[107],"skytopia,":[108],"on":[112,124,209],"action-conditioned":[114],"latent":[115],"model,":[117],"3D":[120],"Gaussian":[121],"Splatting":[122],"platform":[123],"it":[126],"trained.":[128],"A":[129],"forward":[130],"objective":[131,146],"predicts":[132],"next":[137],"observation":[138],"intended":[141],"motion,":[142],"inverse":[145],"recovers":[147],"motion":[149],"predicted":[152],"transition.":[153],"Because":[154],"never":[157],"reaches":[158,216],"generation,":[160],"predictor":[162,196],"discarded":[164],"one":[166],"serves":[168],"point-goal,":[169],"image-goal,":[170],"goal-free":[172],"navigation.":[173],"Simulation":[174],"experiments":[175],"show":[176],"skytopia":[178],"outperforms":[179],"baseline":[181],"three":[184],"specifications,":[185],"attaining":[186],"57.8%,":[187],"66.0%,":[188],"49.0%":[190],"success":[191],"rate,":[192],"while":[193],"discarding":[194],"removes":[197],"59.4%":[198],"inference":[201],"cost.":[202],"The":[203],"same":[204],"subsequently":[207],"deployed":[208],"physical":[211],"without":[213],"fine-tuning":[214],"goals":[217],"indoor,":[219],"open":[220],"outdoor,":[221],"woodland":[223],"environments.":[224]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-24T00:00:00"}