{"id":"https://openalex.org/W3009411535","doi":"https://doi.org/10.1109/iros45743.2020.9341049","title":"Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal Representations","display_name":"Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal Representations","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3009411535","doi":"https://doi.org/10.1109/iros45743.2020.9341049","mag":"3009411535"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1909.06993","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062522127","display_name":"Rogerio Bonatti","orcid":"https://orcid.org/0000-0003-3015-9613"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rogerio Bonatti","raw_affiliation_strings":["Carnegie Mellon University,The Robotics Institute,Pittsburgh,PA","Carnegie Mellon University, The Robotics Institute, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,The Robotics Institute,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, The Robotics Institute, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052528942","display_name":"Ratnesh Madaan","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ratnesh Madaan","raw_affiliation_strings":["Microsoft Corporation,Redmond,WA","Microsoft Corporation, Redmond, WA;;"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA;;","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045147286","display_name":"Vibhav Vineet","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vibhav Vineet","raw_affiliation_strings":["Microsoft Corporation,Redmond,WA","Microsoft Corporation, Redmond, WA;;"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA;;","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032584934","display_name":"Sebastian Scherer","orcid":"https://orcid.org/0000-0002-8373-4688"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastian Scherer","raw_affiliation_strings":["Carnegie Mellon University,The Robotics Institute,Pittsburgh,PA","Carnegie Mellon University, The Robotics Institute, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,The Robotics Institute,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, The Robotics Institute, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101933711","display_name":"Ashish Kapoor","orcid":"https://orcid.org/0009-0004-3764-8449"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Kapoor","raw_affiliation_strings":["Microsoft Corporation,Redmond,WA","Microsoft Corporation, Redmond, WA;;"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA;;","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5062522127"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.6876,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71101207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1637","last_page":"1644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9991000294685364,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.7524878978729248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6509339213371277},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6054756045341492},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5151571035385132},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5005161762237549},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4511609673500061},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4430370032787323},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4114193618297577},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11917966604232788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7524878978729248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6509339213371277},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6054756045341492},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5151571035385132},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5005161762237549},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4511609673500061},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4430370032787323},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4114193618297577},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11917966604232788},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros45743.2020.9341049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1909.06993","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.06993","pdf_url":"https://arxiv.org/pdf/1909.06993","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"mag:3009411535","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1909.06993","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1909.06993","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1909.06993","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1909.06993","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.06993","pdf_url":"https://arxiv.org/pdf/1909.06993","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3009411535.pdf","grobid_xml":"https://content.openalex.org/works/W3009411535.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W1909320841","https://openalex.org/W1980969546","https://openalex.org/W2021851106","https://openalex.org/W2162991084","https://openalex.org/W2184188583","https://openalex.org/W2194775991","https://openalex.org/W2214613866","https://openalex.org/W2482392012","https://openalex.org/W2546190447","https://openalex.org/W2564322318","https://openalex.org/W2565902248","https://openalex.org/W2605102758","https://openalex.org/W2615547864","https://openalex.org/W2747013247","https://openalex.org/W2753738274","https://openalex.org/W2759194679","https://openalex.org/W2782147774","https://openalex.org/W2783375473","https://openalex.org/W2785519580","https://openalex.org/W2787666871","https://openalex.org/W2788239209","https://openalex.org/W2794268423","https://openalex.org/W2794908222","https://openalex.org/W2810124307","https://openalex.org/W2883702102","https://openalex.org/W2889582485","https://openalex.org/W2911448865","https://openalex.org/W2929174622","https://openalex.org/W2950004691","https://openalex.org/W2950872548","https://openalex.org/W2951004968","https://openalex.org/W2963207848","https://openalex.org/W2963428623","https://openalex.org/W2967452881","https://openalex.org/W2967464230","https://openalex.org/W2969329576","https://openalex.org/W2982095652","https://openalex.org/W3003412316","https://openalex.org/W3101780148","https://openalex.org/W4255045719","https://openalex.org/W6637618735","https://openalex.org/W6639732818","https://openalex.org/W6686207219","https://openalex.org/W6731094094","https://openalex.org/W6737769214","https://openalex.org/W6744627333","https://openalex.org/W6747912417","https://openalex.org/W6748223763","https://openalex.org/W6750253780","https://openalex.org/W6752941136","https://openalex.org/W6756256016","https://openalex.org/W6758420182","https://openalex.org/W6764654403","https://openalex.org/W6769227165"],"related_works":["https://openalex.org/W3129860168","https://openalex.org/W2972396961","https://openalex.org/W3095605783","https://openalex.org/W2766653014","https://openalex.org/W2967853831","https://openalex.org/W3192660112","https://openalex.org/W3034728521","https://openalex.org/W3031782360","https://openalex.org/W3130102915","https://openalex.org/W2962887844","https://openalex.org/W2769112066","https://openalex.org/W3014717641","https://openalex.org/W2787718229","https://openalex.org/W3106169723","https://openalex.org/W3022280754","https://openalex.org/W3112506728","https://openalex.org/W2964290968","https://openalex.org/W3004116079","https://openalex.org/W3200100735","https://openalex.org/W2520377600"],"abstract_inverted_index":{"Machines":[0],"are":[1,34],"a":[2,74,108,150,156,171,184],"long":[3],"way":[4],"from":[5],"robustly":[6],"solving":[7],"open-world":[8],"perception-control":[9],"tasks,":[10],"such":[11,128],"as":[12,129,211],"first-person":[13],"view":[14],"(FPV)":[15],"aerial":[16],"navigation.":[17],"While":[18],"recent":[19],"advances":[20],"in":[21,65,138,183,231],"end-to-":[22],"end":[23],"Machine":[24],"Learning,":[25],"especially":[26],"Imitation":[27],"Learning":[28],"and":[29,101,120,197,235,251,255],"Reinforcement":[30],"appear":[31],"promising,":[32],"they":[33],"constrained":[35],"by":[36],"the":[37,51,116,121,126,130,136,139,188,200,248],"need":[38],"of":[39,42,133,141,202],"large":[40],"amounts":[41],"difficult-to-collect":[43],"labeled":[44],"real-":[45],"world":[46],"data.":[47,92,104],"Simulated":[48],"data,":[49],"on":[50],"other":[52],"hand,":[53],"is":[54,167],"easy":[55],"to":[56,115,125,135,213],"generate,":[57],"but":[58],"generally":[59],"does":[60],"not":[61],"render":[62],"safe":[63],"behaviors":[64],"diverse":[66],"real-life":[67],"scenarios.":[68],"In":[69],"this":[70],"work":[71],"we":[72,175],"propose":[73],"novel":[75,151],"method":[76],"for":[77,82,226],"learning":[78,179,215],"robust":[79],"visuomotor":[80],"policies":[81,252],"real-world":[83,224],"deployment":[84],"which":[85,154,174,241],"can":[86,245],"be":[87],"trained":[88,176],"purely":[89,217],"with":[90,180,193],"simulated":[91],"We":[93,144,186,221],"develop":[94],"rich":[95,189],"state":[96],"representations":[97,250],"that":[98,199],"combine":[99],"supervised":[100],"unsupervised":[102,218],"environment":[103],"Our":[105,238],"approach":[106],"takes":[107],"cross-modal":[109,204],"perspective,":[110],"where":[111],"separate":[112],"modalities":[113,148],"correspond":[114],"raw":[117],"camera":[118],"data":[119,147],"system":[122],"states":[123],"relevant":[124],"task,":[127],"relative":[131],"pose":[132],"gates":[134,230],"drone":[137,142,227],"case":[140],"racing.":[143],"feed":[145],"both":[146],"into":[149,170],"factored":[152],"architecture,":[153],"learns":[155],"joint":[157],"lowdimensional":[158],"embedding":[159],"via":[160],"Variational":[161],"Auto":[162],"Encoders.":[163],"This":[164],"compact":[165],"representation":[166],"then":[168],"fed":[169],"control":[172,208],"policy,":[173],"using":[177],"imitation":[178],"expert":[181],"trajectories":[182],"simulator.":[185],"analyze":[187],"latent":[190],"spaces":[191],"learned":[192,249],"our":[194,203],"proposed":[195,239],"representations,":[196],"show":[198],"use":[201],"architecture":[205],"significantly":[206,257],"improves":[207],"policy":[209],"performance":[210],"compared":[212],"end-to-end":[214],"or":[216],"feature":[219],"extractors.":[220],"also":[222],"present":[223],"results":[225],"navigation":[228],"through":[229],"different":[232],"track":[233],"configurations":[234],"environmental":[236],"conditions.":[237],"method,":[240],"runs":[242],"fully":[243],"onboard,":[244],"successfully":[246],"generalize":[247],"across":[253],"simulation":[254],"reality,":[256],"outperforming":[258],"baseline":[259],"approaches.":[260]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}