{"id":"https://openalex.org/W7203690296","doi":"https://doi.org/10.48550/arxiv.2608.16476","title":"Exposing the Long-tail in Embodied Urban Navigation via Scalable Learning from In-the-Wild Videos","display_name":"Exposing the Long-tail in Embodied Urban Navigation via Scalable Learning from In-the-Wild Videos","publication_year":2026,"publication_date":"2026-08-17","ids":{"openalex":"https://openalex.org/W7203690296","doi":"https://doi.org/10.48550/arxiv.2608.16476"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.16476","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16476","pdf_url":"https://arxiv.org/pdf/2608.16476","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/2608.16476","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054913273","display_name":"Bingyi Xia","orcid":"https://orcid.org/0000-0003-3932-7070","observed_orcids":["https://orcid.org/0000-0003-3932-7070"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xia, Bingyi","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130603754","display_name":"Han Bao","orcid":"https://orcid.org/0009-0002-6289-6538","observed_orcids":["https://orcid.org/0009-0002-6289-6538"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bao, Han","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103192430","display_name":"Zhewei Chen","orcid":"https://orcid.org/0009-0004-6778-1988","observed_orcids":["https://orcid.org/0009-0004-6778-1988"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Zhewei","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005136300","display_name":"Hanjing Ye","orcid":"https://orcid.org/0000-0002-8522-3638","observed_orcids":["https://orcid.org/0000-0002-8522-3638"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye, Hanjing","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137528097","display_name":"Jingwen Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yu, Jingwen","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101242118","display_name":"Yuhan Pang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pang, Yuhan","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139126865","display_name":"Wenjun Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Wenjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5146420632","display_name":"Jiankun Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Jiankun","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.7919999957084656,"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":0.7919999957084656,"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":0.028300000354647636,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.02280000038444996,"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/long-tail-scenarios","display_name":"long-tail scenarios","score":0.7229999899864197},{"id":"https://openalex.org/keywords/vision-language-action-policies","display_name":"vision-language-action policies","score":0.7829999923706055},{"id":"https://openalex.org/keywords/navigation-planning","display_name":"navigation planning","score":0.671999990940094},{"id":"https://openalex.org/keywords/failure-mode-identification","display_name":"failure mode identification","score":0.75},{"id":"https://openalex.org/keywords/point-goal-navigation","display_name":"point-goal navigation","score":0.7649999856948853},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"knowledge transfer","score":0.43299999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638000249862671},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6632999777793884},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6050000190734863},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5843999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4797999858856201},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C43472768","wikidata":"https://www.wikidata.org/wiki/Q7855620","display_name":"Turn-by-turn navigation","level":5,"score":0.39559999108314514},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.3919000029563904},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3580999970436096},{"id":"https://openalex.org/C2778058735","wikidata":"https://www.wikidata.org/wiki/Q4692253","display_name":"Aggregate data","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.16476","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16476","pdf_url":"https://arxiv.org/pdf/2608.16476","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.2608.16476","doi":"https://doi.org/10.48550/arxiv.2608.16476","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.16476","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:2608.16476","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16476","pdf_url":"https://arxiv.org/pdf/2608.16476","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":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7646999955177307}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203690296.pdf","grobid_xml":"https://content.openalex.org/works/W7203690296.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W4416780398","https://openalex.org/W6947593395","https://openalex.org/W6947984999","https://openalex.org/W7083292721","https://openalex.org/W7101745443","https://openalex.org/W7130590664","https://openalex.org/W7130595065","https://openalex.org/W7133493150","https://openalex.org/W7140100117","https://openalex.org/W7140282847","https://openalex.org/W7165123881"],"related_works":["https://openalex.org/W4405134061","https://openalex.org/W4417291910","https://openalex.org/W7138145716","https://openalex.org/W7223052014","https://openalex.org/W7134911120","https://openalex.org/W7165123881","https://openalex.org/W7214962707","https://openalex.org/W4390871884","https://openalex.org/W2882977163","https://openalex.org/W2795911278"],"abstract_inverted_index":{"Learning":[0],"embodied":[1],"urban":[2,38,108],"navigation":[3,39,63,76,109,125],"policies":[4],"from":[5,40,115],"real-world":[6,107],"data":[7,15,105],"is":[8],"constrained":[9],"by":[10],"the":[11,18,80,88],"cost":[12],"of":[13,21,90],"task-specific":[14],"collection":[16],"and":[17,61,87,93,106,118],"limited":[19],"coverage":[20],"rare":[22],"yet":[23],"safety-critical":[24],"scenarios.":[25],"To":[26],"address":[27],"these":[28],"challenges,":[29],"we":[30],"present":[31],"a":[32,71],"scalable":[33],"framework":[34,52],"for":[35,74],"learning":[36],"point-goal":[37],"web-scale":[41],"in-the-wild":[42],"egocentric":[43],"videos":[44,57,117],"while":[45],"systematically":[46],"exposing":[47],"its":[48],"long":[49,81],"tail.":[50],"The":[51],"automatically":[53],"annotates":[54],"uncurated":[55],"web":[56],"with":[58],"metric":[59],"trajectories":[60],"structured":[62],"semantics,":[64],"which":[65],"are":[66],"then":[67],"used":[68],"to":[69,97],"train":[70],"vision-language-action":[72],"policy":[73],"interpretable":[75],"planning.":[77],"We":[78],"characterize":[79],"tail":[82],"based":[83],"on":[84,103],"model":[85],"performance":[86],"distribution":[89],"perception-motion":[91],"patterns,":[92],"employ":[94],"reflection-based":[95],"analysis":[96],"diagnose":[98],"recurring":[99],"failure":[100],"modes.":[101],"Experiments":[102],"web-video":[104],"tasks":[110],"demonstrate":[111],"effective":[112],"knowledge":[113],"transfer":[114],"unconstrained":[116],"reveal":[119],"coherent":[120],"long-tail":[121],"structures":[122],"beyond":[123],"aggregate":[124],"performance.":[126]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-19T00:00:00"}