{"id":"https://openalex.org/W4386076252","doi":"https://doi.org/10.1109/cvpr52729.2023.01041","title":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","display_name":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386076252","doi":"https://doi.org/10.1109/cvpr52729.2023.01041"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.01041","doi":"https://doi.org/10.1109/cvpr52729.2023.01041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.01041","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.03112","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077791956","display_name":"Aishwarya Kamath","orcid":"https://orcid.org/0000-0002-1902-3822","observed_orcids":["https://orcid.org/0000-0002-1902-3822"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aishwarya Kamath","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peter Anderson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Anderson","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100463046","display_name":"Su Wang","orcid":"https://orcid.org/0000-0001-7094-8890","observed_orcids":["https://orcid.org/0000-0001-7094-8890"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Su Wang","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009550511","display_name":"Jing Yu Koh","orcid":null,"observed_orcids":[]},"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":"Jing Yu Koh","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055207525","display_name":"Alexander Ku","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Ku","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Austin Waters","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin Waters","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112656212","display_name":"Yinfei Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinfei Yang","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048931310","display_name":"Jason Baldridge","orcid":"https://orcid.org/0000-0002-4712-1841","observed_orcids":["https://orcid.org/0000-0002-4712-1841"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Baldridge","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086908529","display_name":"Zarana Parekh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zarana Parekh","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9654,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.95844311,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"10813","last_page":"10823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5238999724388123,"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":0.5238999724388123,"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":0.4000999927520752,"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/T11904","display_name":"Spatial Cognition and Navigation","score":0.019600000232458115,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.9929999709129333},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.9490000009536743},{"id":"https://openalex.org/keywords/language-grounding","display_name":"language grounding","score":0.5180000066757202},{"id":"https://openalex.org/keywords/spatial-language-comprehension","display_name":"spatial language comprehension","score":0.8790000081062317},{"id":"https://openalex.org/keywords/360-degree-panorama","display_name":"360-degree panorama","score":0.7549999952316284},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.3479999899864197},{"id":"https://openalex.org/keywords/unknown-environments","display_name":"unknown environments","score":0.5920000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8624989986419678},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5492390394210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5368955731391907},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3870046138763428},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3694548010826111}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr52729.2023.01041","doi":"https://doi.org/10.1109/cvpr52729.2023.01041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.01041","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.03112","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.03112","pdf_url":"https://arxiv.org/pdf/2210.03112","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.03112","doi":"https://doi.org/10.48550/arxiv.2210.03112","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.03112","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.03112","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.03112","pdf_url":"https://arxiv.org/pdf/2210.03112","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386076252.pdf","grobid_xml":"https://content.openalex.org/works/W4386076252.grobid-xml"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1525482321","https://openalex.org/W1931877416","https://openalex.org/W1933065844","https://openalex.org/W1962416794","https://openalex.org/W1965680834","https://openalex.org/W2064675550","https://openalex.org/W2117539524","https://openalex.org/W2118781169","https://openalex.org/W2189089430","https://openalex.org/W2194775991","https://openalex.org/W2260756217","https://openalex.org/W2611884151","https://openalex.org/W2770387316","https://openalex.org/W2805395174","https://openalex.org/W2884565639","https://openalex.org/W2885185669","https://openalex.org/W2886641317","https://openalex.org/W2903172725","https://openalex.org/W2909303996","https://openalex.org/W2926977875","https://openalex.org/W2929928372","https://openalex.org/W2946948417","https://openalex.org/W2953127211","https://openalex.org/W2958574008","https://openalex.org/W2959918500","https://openalex.org/W2962784628","https://openalex.org/W2963341956","https://openalex.org/W2963726321","https://openalex.org/W2964339842","https://openalex.org/W2964935470","https://openalex.org/W2970231061","https://openalex.org/W2981852735","https://openalex.org/W2987914945","https://openalex.org/W2998926068","https://openalex.org/W3020712669","https://openalex.org/W3023306062","https://openalex.org/W3034500398","https://openalex.org/W3034578524","https://openalex.org/W3034984114","https://openalex.org/W3092825347","https://openalex.org/W3100923070","https://openalex.org/W3101009265","https://openalex.org/W3101638486","https://openalex.org/W3129576130","https://openalex.org/W3135367836","https://openalex.org/W3152079230","https://openalex.org/W3156559819","https://openalex.org/W3159619744","https://openalex.org/W3162235419","https://openalex.org/W3165915253","https://openalex.org/W3168640669","https://openalex.org/W3169483174","https://openalex.org/W3172675210","https://openalex.org/W3173220247","https://openalex.org/W3181158454","https://openalex.org/W3193402170","https://openalex.org/W3195026654","https://openalex.org/W3208220903","https://openalex.org/W3208883793","https://openalex.org/W3213148312","https://openalex.org/W4226052928","https://openalex.org/W4226167525","https://openalex.org/W4283388932","https://openalex.org/W4284666406","https://openalex.org/W4296406182","https://openalex.org/W4312434279","https://openalex.org/W4312501707","https://openalex.org/W4312707839","https://openalex.org/W4382468817","https://openalex.org/W6680724558","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W7218863670","https://openalex.org/W4402904106","https://openalex.org/W4404570880","https://openalex.org/W4405022959","https://openalex.org/W4390873167","https://openalex.org/W7117569334","https://openalex.org/W4390871884","https://openalex.org/W4412888464","https://openalex.org/W4416242603","https://openalex.org/W4389665189"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"in":[2,14,38,86,189,197],"Vision-and-Language":[3],"Navigation":[4],"(VLN)":[5],"train":[6,161],"RL":[7,179],"agents":[8,43],"to":[9,187,195,204,208],"execute":[10],"natural-language":[11],"navigation":[12,92,111],"instructions":[13],"photorealistic":[15],"environments,":[16,41,191],"as":[17],"a":[18,99,108,146,162,205],"step":[19],"towards":[20],"robots":[21],"that":[22],"can":[23],"follow":[24],"human":[25,32],"instructions.":[26,79,219],"However,":[27],"given":[28],"the":[29,39,62,69,170,182],"scarcity":[30],"of":[31,130,137,149],"instruction":[33,101,112],"data":[34,156],"and":[35,50,58,97,144,151,192],"limited":[36],"diversity":[37],"training":[40,214],"these":[42,95],"still":[44],"struggle":[45],"with":[46,77,166],"complex":[47],"language":[48,52],"grounding":[49],"spatial":[51],"understanding.":[53],"Pretraining":[54],"on":[55,215],"large":[56],"text":[57],"image-text":[59],"datasets":[60],"from":[61,119,185,193],"web":[63],"has":[64],"been":[65],"extensively":[66],"explored":[67],"but":[68],"improvements":[70],"are":[71],"limited.":[72],"We":[73,80,114],"investigate":[74],"large-scale":[75,213],"augmentation":[76],"synthetic":[78,218],"take":[81],"500+":[82],"indoor":[83],"environments":[84,150],"captured":[85],"densely-sampled":[87],"360":[88],"\u00b0":[89],"panoramas,":[90,96],"construct":[91],"trajectories":[93],"through":[94],"generate":[98],"visually-grounded":[100],"for":[102],"each":[103],"trajectory":[104],"using":[105,122],"Marky":[106],"[63],":[107],"high-quality":[109],"multilingual":[110],"generator.":[113],"also":[115],"synthesize":[116],"image":[117],"observations":[118],"novel":[120],"viewpoints":[121],"an":[123],"image-to-image":[124],"GAN":[125],"[27].":[126],"The":[127],"resulting":[128],"dataset":[129],"4.2M":[131],"instruction-trajectory":[132],"pairs":[133],"is":[134],"two":[135],"orders":[136],"magnitude":[138],"larger":[139],"than":[140],"existing":[141,178],"human-annotated":[142],"datasets,":[143],"contains":[145],"wider":[147],"variety":[148],"viewpoints.":[152],"To":[153],"efficiently":[154],"leverage":[155],"at":[157],"this":[158],"scale,":[159],"we":[160],"simple":[163],"transformer":[164],"agent":[165],"imitation":[167],"learning.":[168],"On":[169],"challenging":[171],"RxR":[172],"dataset,":[173],"our":[174],"approach":[175],"outperforms":[176],"all":[177],"agents,":[180,211],"improving":[181,209],"state-of-the-art":[183],"NDTW":[184],"71.1":[186],"79.1":[188],"seen":[190],"64.6":[194],"66.8":[196],"unseen":[198],"test":[199],"environments.":[200],"Our":[201],"work":[202],"points":[203],"new":[206],"path":[207],"instruction-following":[210],"emphasizing":[212],"near-human":[216],"quality":[217]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":6}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2023-08-23T00:00:00"}