{"id":"https://openalex.org/W4283463401","doi":"https://doi.org/10.48550/arxiv.2206.11610","title":"1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)","display_name":"1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4283463401","doi":"https://doi.org/10.48550/arxiv.2206.11610"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2206.11610","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.11610","pdf_url":"https://arxiv.org/pdf/2206.11610","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/2206.11610","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101399813","display_name":"Dong Un An","orcid":"https://orcid.org/0000-0002-1347-8535","observed_orcids":["https://orcid.org/0000-0002-1347-8535"]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4401727009","display_name":"Sensetime (China)","ror":"https://ror.org/049wsmj07","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401727009"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An, Dong","raw_affiliation_strings":["Institute of Automation , CAS ,","SenseTime"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , CAS ,","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"SenseTime","institution_ids":["https://openalex.org/I4401727009"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101452807","display_name":"Zun Wang","orcid":"https://orcid.org/0009-0006-1478-5963","observed_orcids":["https://orcid.org/0009-0006-1478-5963"]},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Wang, Zun","raw_affiliation_strings":["Shanghai AI Laboratory ,","The Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory ,","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Yangguang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401727009","display_name":"Sensetime (China)","ror":"https://ror.org/049wsmj07","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401727009"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yangguang","raw_affiliation_strings":["SenseTime"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime","institution_ids":["https://openalex.org/I4401727009"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365047","display_name":"Yi Wang","orcid":"https://orcid.org/0009-0008-0443-2480","observed_orcids":["https://orcid.org/0009-0008-0443-2480"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yi","raw_affiliation_strings":["Shanghai AI Laboratory ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory ,","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036105537","display_name":"Yicong Hong","orcid":"https://orcid.org/0000-0002-5068-1508","observed_orcids":["https://orcid.org/0000-0002-5068-1508"]},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hong, Yicong","raw_affiliation_strings":["The Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101550628","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-8239-7229","observed_orcids":["https://orcid.org/0000-0002-8239-7229"]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Yan","raw_affiliation_strings":["Institute of Automation , CAS ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , CAS ,","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647","observed_orcids":["https://orcid.org/0000-0001-5224-8647","https://orcid.org/0000-0002-5247-6727","https://orcid.org/0000-0002-3247-1080"]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Liang","raw_affiliation_strings":["Institute of Automation , CAS ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , CAS ,","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102006926","display_name":"Jing Shao","orcid":"https://orcid.org/0000-0002-2500-2366","observed_orcids":["https://orcid.org/0000-0002-2500-2366"]},"institutions":[{"id":"https://openalex.org/I4401727009","display_name":"Sensetime (China)","ror":"https://ror.org/049wsmj07","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401727009"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shao, Jing","raw_affiliation_strings":["SenseTime"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime","institution_ids":["https://openalex.org/I4401727009"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":33,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.447299987077713,"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":0.447299987077713,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.38960000872612,"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":0.03779999911785126,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-and-language-navigation","display_name":"vision-and-language navigation","score":0.9810000061988831},{"id":"https://openalex.org/keywords/continuous-environments","display_name":"continuous environments","score":0.9369999766349792},{"id":"https://openalex.org/keywords/natural-language-instructions","display_name":"natural language instructions","score":0.5669999718666077},{"id":"https://openalex.org/keywords/long-horizon-navigation","display_name":"long-horizon navigation","score":0.8429999947547913},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"obstacle avoidance","score":0.7360000014305115},{"id":"https://openalex.org/keywords/synthetic-data-pre-training","display_name":"synthetic data pre-training","score":0.6660000085830688},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.9070000052452087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7021389007568359},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.6298621892929077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48589009046554565}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2206.11610","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.11610","pdf_url":"https://arxiv.org/pdf/2206.11610","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.2206.11610","doi":"https://doi.org/10.48550/arxiv.2206.11610","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.11610","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:2206.11610","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.11610","pdf_url":"https://arxiv.org/pdf/2206.11610","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/W4283463401.pdf","grobid_xml":"https://content.openalex.org/works/W4283463401.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2965373594","https://openalex.org/W2991416037","https://openalex.org/W3216334431","https://openalex.org/W4312996039"],"related_works":["https://openalex.org/W7162546573","https://openalex.org/W4417073331","https://openalex.org/W7138902549","https://openalex.org/W4412030766","https://openalex.org/W4416748461","https://openalex.org/W7163864834","https://openalex.org/W7213397834","https://openalex.org/W4416981710","https://openalex.org/W4415707796","https://openalex.org/W4415672211"],"abstract_inverted_index":{"This":[0],"report":[1],"presents":[2],"the":[3,6,10,19,49,57,62,67,92,95,111,115,125,150,157,163,179,194,215],"methods":[4,227],"of":[5,9,21,54,79,94,110,188],"winning":[7],"entry":[8],"RxR-Habitat":[11,216],"Competition":[12,217],"in":[13,24],"CVPR":[14],"2022.":[15],"The":[16,117],"competition":[17],"addresses":[18],"problem":[20],"Vision-and-Language":[22,189],"Navigation":[23,190],"Continuous":[25],"Environments":[26],"(VLN-CE),":[27],"which":[28,128,160],"requires":[29],"an":[30],"agent":[31,164,180],"to":[32,38,107,123,144,148,165,192],"follow":[33],"step-by-step":[34],"natural":[35],"language":[36],"instructions":[37],"reach":[39,149],"a":[40,44,77,102,138],"target.":[41],"We":[42,182],"present":[43],"modular":[45],"plan-and-control":[46],"approach":[47],"for":[48,132],"task.":[50],"Our":[51,212],"model":[52,210,213],"consists":[53],"three":[55,174],"modules:":[56],"candidate":[58,80,112],"waypoints":[59,81,113],"predictor":[60],"(CWP),":[61],"history":[63],"enhanced":[64],"planner":[65,104,118],"and":[66,98,168,208,221,230],"tryout":[68,143],"controller.":[69],"In":[70],"each":[71],"decision":[72],"loop,":[73],"CWP":[74],"first":[75],"predicts":[76],"set":[78],"based":[82,155,199],"on":[83,156,200,228],"depth":[84],"observations":[85],"from":[86,170],"multiple":[87],"views.":[88],"It":[89,153],"can":[90,161],"reduce":[91],"complexity":[93],"action":[96],"space":[97],"facilitate":[99],"planning.":[100],"Then,":[101],"history-enhanced":[103],"is":[105,129,154],"adopted":[106],"select":[108],"one":[109],"as":[114,197],"subgoal.":[116,152],"additionally":[119],"encodes":[120],"historical":[121],"memory":[122],"track":[124],"navigation":[126],"progress,":[127],"especially":[130],"effective":[131],"long-horizon":[133],"navigation.":[134],"Finally,":[135],"we":[136],"propose":[137],"non-parametric":[139],"heuristic":[140],"controller":[141],"named":[142],"execute":[145],"low-level":[146],"actions":[147],"planned":[151],"trial-and-error":[158],"mechanism":[159],"help":[162],"avoid":[166],"obstacles":[167],"escape":[169],"getting":[171],"stuck.":[172],"All":[173],"modules":[175],"work":[176],"hierarchically":[177],"until":[178],"stops.":[181],"further":[183],"take":[184],"several":[185],"recent":[186],"advances":[187],"(VLN)":[191],"improve":[193],"performance":[195],"such":[196],"pretraining":[198],"large-scale":[201],"synthetic":[202],"in-domain":[203],"dataset,":[204],"environment-level":[205],"data":[206],"augmentation":[207],"snapshot":[209],"ensemble.":[211],"won":[214],"2022,":[218],"with":[219],"48%":[220],"90%":[222],"relative":[223],"improvements":[224],"over":[225],"existing":[226],"NDTW":[229],"SR":[231],"metrics":[232],"respectively.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-06-26T00:00:00"}