{"id":"https://openalex.org/W4413918705","doi":"https://doi.org/10.1109/icra55743.2025.11127961","title":"VLN-KHVR: Knowledge-And-History Aware Visual Representation for Continuous Vision-and-Language Navigation","display_name":"VLN-KHVR: Knowledge-And-History Aware Visual Representation for Continuous Vision-and-Language Navigation","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413918705","doi":"https://doi.org/10.1109/icra55743.2025.11127961"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127961","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":"article","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/A5055367753","display_name":"Ping Kong","orcid":"https://orcid.org/0000-0003-2843-8787"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ping Kong","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin,China,300350"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin,China,300350","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728390","display_name":"Ruonan Liu","orcid":"https://orcid.org/0000-0001-9963-7092"},"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":"Ruonan Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090938988","display_name":"Zongxia Xie","orcid":"https://orcid.org/0000-0003-4725-9290"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongxia Xie","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin,China,300350"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin,China,300350","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070930704","display_name":"Zhibo Pang","orcid":"https://orcid.org/0000-0002-7474-4294"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zhibo Pang","raw_affiliation_strings":["KTH Royal Institute of Technology, ABB Corporate Research,Västerås, Stockholm,Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, ABB Corporate Research,Västerås, Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055367753"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":1.304,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84145494,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5236","last_page":"5243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9940999746322632,"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":0.9940999746322632,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9746000170707703,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9606000185012817,"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":0.7064778804779053},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5355332493782043},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.45544955134391785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4514051675796509},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.43928804993629456},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42414480447769165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7064778804779053},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5355332493782043},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45544955134391785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4514051675796509},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.43928804993629456},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42414480447769165},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127961","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2561529111","https://openalex.org/W2951973805","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W2964935470","https://openalex.org/W2971974407","https://openalex.org/W2987086322","https://openalex.org/W3009928773","https://openalex.org/W3034578524","https://openalex.org/W3035232877","https://openalex.org/W3100923070","https://openalex.org/W3107094551","https://openalex.org/W3108864070","https://openalex.org/W3109085430","https://openalex.org/W3165915253","https://openalex.org/W3169884222","https://openalex.org/W3172675210","https://openalex.org/W3176974620","https://openalex.org/W3192009892","https://openalex.org/W3203338521","https://openalex.org/W3205276578","https://openalex.org/W3206064780","https://openalex.org/W4226052928","https://openalex.org/W4312253995","https://openalex.org/W4312434279","https://openalex.org/W4312544224","https://openalex.org/W4312729859","https://openalex.org/W4312996039","https://openalex.org/W4313591672","https://openalex.org/W4386065508","https://openalex.org/W4390871755","https://openalex.org/W4390872665","https://openalex.org/W4393148636","https://openalex.org/W4394627367"],"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":{"Vision-and-Language":[0,68],"Navigation":[1,69],"in":[2,17,98],"Continuous":[3,67],"Environments":[4],"(VLN-CE)":[5],"requires":[6],"agents":[7],"to":[8,30,79,118,123,143],"navigate":[9],"with":[10,131],"lowlevel":[11],"actions":[12],"following":[13],"natural":[14],"language":[15],"instructions":[16],"3D":[18],"environments.":[19],"Most":[20],"existing":[21],"approaches":[22],"utilize":[23],"observation":[24],"features":[25,90,115,128,140],"from":[26,91],"the":[27,32,48,54,92,99,104,107,111,120,132,138,152,156,159],"current":[28,93],"step":[29],"represent":[31],"viewpoint.":[33],"However,":[34],"these":[35],"representations":[36,77],"often":[37],"conflate":[38],"redundant":[39],"and":[40,102,113],"essential":[41],"information":[42,121],"for":[43,66,134],"navigation,":[44],"introducing":[45],"ambiguity":[46],"into":[47],"agent's":[49],"action":[50],"prediction.":[51],"To":[52],"address":[53],"problem":[55],"of":[56,106,158],"inadequate":[57],"representation,":[58],"we":[59],"propose":[60],"a":[61],"Knowledge-andHistory":[62],"Aware":[63],"Visual":[64],"Representation":[65],"(VLN-KHVR).":[70],"The":[71],"proposed":[72,160],"approach":[73],"constructs":[74],"enriched":[75],"visual":[76],"tailored":[78],"navigation":[80,84,108,124],"instructions,":[81],"enhancing":[82],"agents'":[83],"performance.":[85],"Specifically,":[86],"VLN-KHVR":[87],"extracts":[88],"image":[89],"observation,":[94],"retrieves":[95],"relevant":[96],"knowledge":[97,100,112],"base,":[101],"obtains":[103],"history":[105,114],"episode.":[109],"Subsequently,":[110],"are":[116,129,141],"filtered":[117],"eliminate":[119],"irrelevant":[122],"instruction.":[125],"These":[126],"refined":[127],"integrated":[130],"instruction":[133],"further":[135],"interaction.":[136],"Finally,":[137],"aggregated":[139],"used":[142],"guide":[144],"navigation.":[145],"Our":[146],"model":[147],"outperforms":[148],"previous":[149],"methods":[150],"on":[151],"VLN-CE":[153],"benchmark,":[154],"demonstrating":[155],"effectiveness":[157],"method.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}