{"id":"https://openalex.org/W4413925205","doi":"https://doi.org/10.1109/icra55743.2025.11128467","title":"Na Vid-4D: Unleashing Spatial Intelligence in Egocentric RGB-D Videos for Vision-and-Language Navigation","display_name":"Na Vid-4D: Unleashing Spatial Intelligence in Egocentric RGB-D Videos for Vision-and-Language Navigation","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925205","doi":"https://doi.org/10.1109/icra55743.2025.11128467"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100449224","display_name":"Haoran Liu","orcid":"https://orcid.org/0000-0002-1744-3436"},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Haoran Liu","raw_affiliation_strings":["School of Computer Science, Peking University,CFCS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,CFCS","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103020298","display_name":"Weikang Wan","orcid":"https://orcid.org/0000-0002-8998-862X"},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Weikang Wan","raw_affiliation_strings":["School of Computer Science, Peking University,CFCS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,CFCS","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003076238","display_name":"Xin Yu","orcid":"https://orcid.org/0000-0002-0269-5649"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiqian Yu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100622894","display_name":"Minghan Li","orcid":"https://orcid.org/0000-0003-0055-9261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minghan Li","raw_affiliation_strings":["Galbot"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Galbot","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034850281","display_name":"Jiazhao Zhang","orcid":"https://orcid.org/0000-0001-9459-293X"},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jiazhao Zhang","raw_affiliation_strings":["School of Computer Science, Peking University,CFCS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,CFCS","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005734123","display_name":"Bo Zhao","orcid":"https://orcid.org/0000-0003-4264-2282"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079572598","display_name":"Zhibo Chen","orcid":"https://orcid.org/0000-0002-8525-5066"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibo Chen","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741750","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0000-0002-9796-488X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyuan Wang","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049237194","display_name":"Zhizheng Zhang","orcid":"https://orcid.org/0000-0001-7786-5107"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhizheng Zhang","raw_affiliation_strings":["Galbot"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Galbot","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075606222","display_name":"He Wang","orcid":"https://orcid.org/0000-0002-3365-4620"},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"He Wang","raw_affiliation_strings":["School of Computer Science, Peking University,CFCS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University,CFCS","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10607","last_page":"10615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.7653999924659729,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.7653999924659729,"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/T13382","display_name":"Robotics and Automated Systems","score":0.6844000220298767,"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"}},{"id":"https://openalex.org/T11325","display_name":"Inertial Sensor and Navigation","score":0.6837000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.722347617149353},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6946834325790405},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6202710270881653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6151517033576965},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3562403917312622},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3313937783241272}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722347617149353},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6946834325790405},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6202710270881653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6151517033576965},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3562403917312622},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3313937783241272}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W1969483458","https://openalex.org/W2172171378","https://openalex.org/W2251512949","https://openalex.org/W2560730294","https://openalex.org/W2963109634","https://openalex.org/W2963518342","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W2964935470","https://openalex.org/W2974759213","https://openalex.org/W3004268082","https://openalex.org/W3009928773","https://openalex.org/W3034578524","https://openalex.org/W3034758614","https://openalex.org/W3100923070","https://openalex.org/W3106859150","https://openalex.org/W3107069568","https://openalex.org/W3109085430","https://openalex.org/W3172675210","https://openalex.org/W3176974620","https://openalex.org/W3203338521","https://openalex.org/W3205276578","https://openalex.org/W3206064780","https://openalex.org/W4221167437","https://openalex.org/W4225675121","https://openalex.org/W4226052928","https://openalex.org/W4280571816","https://openalex.org/W4312253995","https://openalex.org/W4312544224","https://openalex.org/W4312846625","https://openalex.org/W4312996039","https://openalex.org/W4383108296","https://openalex.org/W4386075653","https://openalex.org/W4386083032","https://openalex.org/W4390873167","https://openalex.org/W4393154152","https://openalex.org/W4395481595","https://openalex.org/W4401414715","https://openalex.org/W4402353981","https://openalex.org/W4402670239","https://openalex.org/W4402716288","https://openalex.org/W4402776116","https://openalex.org/W4403002096","https://openalex.org/W4403923795"],"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":{"Understanding":[0],"and":[1,27,79,97,104,152,167,184],"reasoning":[2,80,105],"about":[3],"the":[4,48,53,59,92,111,127,131,140,148,170,194],"4D":[5],"space-time":[6],"is":[7,98],"crucial":[8],"for":[9,81],"Vision-and-Language":[10],"Navigation":[11],"(VLN).":[12],"However,":[13],"previous":[14],"works":[15,155],"lack":[16],"in-depth":[17],"exploration":[18],"in":[19,23,50,58,181,193],"this":[20,34],"aspect,":[21],"resulting":[22],"bottlenecked":[24],"spatial":[25,56,77,102,190],"perception":[26],"action":[28],"precision":[29],"of":[30,55,124,134,142],"VLN":[31,187],"agents.":[32],"In":[33],"work,":[35],"we":[36,119],"introduce":[37],"NaVid-4D,":[38],"a":[39,121,135],"Vision":[40],"Language":[41],"Model":[42],"(VLM)":[43],"based":[44],"navigation":[45,89],"agent":[46],"taking":[47],"lead":[49],"explicitly":[51],"showcasing":[52],"capabilities":[54,106],"intelligence":[57,191],"real":[60,195],"world.":[61,196],"Given":[62],"natural":[63],"language":[64],"instructions,":[65],"NaVid-4D":[66,87,154,177],"requires":[67],"only":[68],"egocentric":[69],"RGB-D":[70,116],"video":[71],"streams":[72],"as":[73],"observations":[74],"to":[75,113],"perform":[76],"understanding":[78,103],"generating":[82],"precise":[83,101],"instruction-following":[84],"robotic":[85],"actions.":[86],"learns":[88],"policies":[90],"using":[91,107,160],"data":[93],"from":[94],"simulation":[95,182],"environments":[96],"endowed":[99],"with":[100,147,157,189],"web":[108],"data.":[109],"Without":[110],"need":[112],"pre-train":[114],"an":[115],"foundation":[117],"model,":[118],"propose":[120],"method":[122],"capable":[123],"directly":[125],"injecting":[126],"depth":[128,145,162],"features":[129],"into":[130],"visual":[132],"encoder":[133],"VLM.":[136],"We":[137],"further":[138],"compare":[139],"use":[141],"factually":[143],"captured":[144],"information":[146],"monocularly":[149],"estimated":[150,161],"one":[151],"find":[153],"well":[156],"both":[158],"while":[159],"offers":[163],"greater":[164],"gener-alization":[165],"capability":[166],"better":[168],"mitigates":[169],"sim-to-real":[171],"gap.":[172],"Extensive":[173],"experiments":[174],"demonstrate":[175],"that":[176],"achieves":[178],"state-of-the-art":[179],"performance":[180,188],"environment":[183],"makes":[185],"impressive":[186],"happen":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}