{"id":"https://openalex.org/W4379740312","doi":"https://doi.org/10.1109/tai.2023.3283488","title":"Learning Visual Representation for Autonomous Drone Navigation via a Contrastive World Model","display_name":"Learning Visual Representation for Autonomous Drone Navigation via a Contrastive World Model","publication_year":2023,"publication_date":"2023-06-07","ids":{"openalex":"https://openalex.org/W4379740312","doi":"https://doi.org/10.1109/tai.2023.3283488"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2023.3283488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3283488","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-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/A5057902114","display_name":"Jiang Zhao","orcid":"https://orcid.org/0000-0002-9873-156X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiang Zhao","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101882645","display_name":"Yibo Wang","orcid":"https://orcid.org/0000-0003-0088-8217"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibo Wang","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","Unmanned System Research Institute, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Unmanned System Research Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027960407","display_name":"Zhihao Cai","orcid":"https://orcid.org/0009-0003-8507-1448"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Cai","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032857207","display_name":"Ningjun Liu","orcid":"https://orcid.org/0000-0002-0879-2992"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningjun Liu","raw_affiliation_strings":["Unmanned System Research Institute, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Unmanned System Research Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101585859","display_name":"Kun Wu","orcid":"https://orcid.org/0000-0002-2912-4256"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wu","raw_affiliation_strings":["Flying College, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Flying College, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083517876","display_name":"Yingxun Wang","orcid":"https://orcid.org/0000-0002-7544-4365"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingxun Wang","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","Unmanned System Research Institute, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Unmanned System Research Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5057902114"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.2036,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81036196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"5","issue":"3","first_page":"1263","last_page":"1276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.9031615257263184},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6447226405143738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5634769201278687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5510532855987549},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4190911054611206},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3449772596359253},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.07458102703094482},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.06120207905769348}],"concepts":[{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.9031615257263184},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6447226405143738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5634769201278687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5510532855987549},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4190911054611206},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3449772596359253},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.07458102703094482},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.06120207905769348},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2023.3283488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3283488","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6600785105","display_name":null,"funder_award_id":"YWF-22-L-539","funder_id":"https://openalex.org/F4320329878","funder_display_name":"Central University Basic Research Fund of China"}],"funders":[{"id":"https://openalex.org/F4320329878","display_name":"Central University Basic Research Fund of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2296673577","https://openalex.org/W2482392012","https://openalex.org/W2512051764","https://openalex.org/W2787666871","https://openalex.org/W2798991696","https://openalex.org/W2900559324","https://openalex.org/W2949924544","https://openalex.org/W2962858109","https://openalex.org/W2963305465","https://openalex.org/W2967464230","https://openalex.org/W2982095652","https://openalex.org/W3035524453","https://openalex.org/W3102552342","https://openalex.org/W3129860168","https://openalex.org/W3132100459","https://openalex.org/W3140042148","https://openalex.org/W3171007011","https://openalex.org/W3174559407","https://openalex.org/W3206042616","https://openalex.org/W3217536461","https://openalex.org/W4214730142","https://openalex.org/W4249244053","https://openalex.org/W4280524650","https://openalex.org/W4297808394","https://openalex.org/W4312289535","https://openalex.org/W4313072750","https://openalex.org/W4383066575","https://openalex.org/W4385245566","https://openalex.org/W6674711614","https://openalex.org/W6752941136","https://openalex.org/W6755207826","https://openalex.org/W6755999739","https://openalex.org/W6756256016","https://openalex.org/W6771217966","https://openalex.org/W6775186109","https://openalex.org/W6776901495","https://openalex.org/W6782858274","https://openalex.org/W6783990618","https://openalex.org/W6785996349","https://openalex.org/W6790878036","https://openalex.org/W6794471905","https://openalex.org/W6796613488","https://openalex.org/W6803185011","https://openalex.org/W6810536332","https://openalex.org/W6838544366","https://openalex.org/W6844194202","https://openalex.org/W6845226490"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Visuomotor":[0],"policy":[1,18,128,137],"learning":[2,53,129,161,182],"for":[3,12,71,95],"vision-based":[4,72],"navigation":[5,73,143],"tasks":[6],"is":[7],"still":[8],"challenging":[9,164],"and":[10,31,58,97,145,158,177,191],"necessary":[11],"autonomous":[13],"systems.":[14],"Learning":[15],"a":[16,42,50,62,84,90,109,121],"task-specific":[17,157],"from":[19,27],"scratch":[20],"simplifies":[21],"the":[22,78,127,133,140,146,172,187],"training":[23,112],"pipeline":[24],"while":[25],"suffering":[26],"poor":[28],"data":[29,175],"efficiency":[30,176],"transfer":[32],"ability.":[33],"This":[34],"problem":[35],"intends":[36],"to":[37,67,88,125],"be":[38],"more":[39,169],"intractable":[40],"under":[41],"low-data":[43],"regime.":[44],"In":[45],"this":[46,106],"work,":[47],"we":[48],"present":[49],"self-supervised":[51],"representation":[52,70],"architecture":[54,107],"that":[55,152],"incorporates":[56],"Spatial":[57],"Temporal":[59],"information":[60],"via":[61],"Contrastive":[63],"world":[64],"model":[65,81,118],"(STC)":[66],"extract":[68],"image":[69],"tasks.":[74],"Specifically,":[75],"STC":[76],"leverages":[77],"dynamics":[79],"transition":[80],"based":[82],"on":[83,138],"recurrent":[85],"neural":[86],"network":[87],"construct":[89],"joint":[91],"low-dimensional":[92],"latent":[93],"space":[94],"spatial":[96],"temporal":[98],"representations.":[99],"We":[100,131],"simultaneously":[101],"optimize":[102],"all":[103],"components":[104],"of":[105],"using":[108],"multiobjective":[110],"contrastive":[111,160],"loss.":[113],"The":[114],"resulting":[115],"pretrained":[116],"encoder":[117],"acts":[119],"as":[120,184,186],"standalone":[122],"feature":[123],"extractor":[124],"promote":[126],"procedure.":[130],"evaluate":[132],"final":[134,188],"optimized":[135],"visuomotor":[136],"both":[139],"simulated":[141],"drone":[142],"environment":[144],"out-of-domain":[147],"dataset.":[148],"Experimental":[149],"results":[150],"demonstrate":[151],"our":[153],"proposed":[154],"method":[155],"outperforms":[156],"representative":[159],"baselines":[162],"in":[163,174,181],"complex":[165],"visual":[166],"environments":[167],"with":[168],"than":[170],"half":[171],"improvement":[173],"provides":[178],"significant":[179],"gains":[180],"speed":[183],"well":[185],"performance.":[189],"Code":[190],"video":[192],"are":[193],"available":[194],"at:":[195],"<uri":[196],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[197],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/yibow-wang/cwm4drone</uri>":[198],".":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}