{"id":"https://openalex.org/W4401417232","doi":"https://doi.org/10.1109/icra57147.2024.10611565","title":"Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions","display_name":"Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401417232","doi":"https://doi.org/10.1109/icra57147.2024.10611565"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5049786228","display_name":"Yuxing Long","orcid":"https://orcid.org/0009-0006-3246-459X"},"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":"Yuxing Long","raw_affiliation_strings":["Peking University and National Key Laboratory for Multimedia Information Processing,CFCS, School of CS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University and National Key Laboratory for Multimedia Information Processing,CFCS, School of CS","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012981856","display_name":"Xiaoqi Li","orcid":"https://orcid.org/0000-0001-8855-7759"},"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":"Xiaoqi Li","raw_affiliation_strings":["Peking University and National Key Laboratory for Multimedia Information Processing,CFCS, School of CS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University and National Key Laboratory for Multimedia Information Processing,CFCS, School of CS","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084148642","display_name":"Wenzhe Cai","orcid":"https://orcid.org/0000-0001-6738-9880"},"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":"Wenzhe Cai","raw_affiliation_strings":["Peking University and National Key Laboratory for Multimedia Information Processing,CFCS, School of CS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University and National Key Laboratory for Multimedia Information Processing,CFCS, School of CS","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056150603","display_name":"Hao Dong","orcid":"https://orcid.org/0000-0002-7332-1505"},"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":"Hao Dong","raw_affiliation_strings":["Peking University and National Key Laboratory for Multimedia Information Processing,CFCS, School of CS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University and National Key Laboratory for Multimedia Information Processing,CFCS, School of CS","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]}],"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":false,"cited_by_count":51,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17380","last_page":"17387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11439","display_name":"Video Analysis and Summarization","score":0.987500011920929,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9848999977111816,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7613884806632996},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4941733181476593},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4228297472000122},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4173911511898041},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3732326626777649}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613884806632996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4941733181476593},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4228297472000122},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4173911511898041},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3732326626777649}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W2805984364","https://openalex.org/W2890163949","https://openalex.org/W2926977875","https://openalex.org/W2959918500","https://openalex.org/W2963800628","https://openalex.org/W2969765146","https://openalex.org/W2970231061","https://openalex.org/W2998008599","https://openalex.org/W3034500398","https://openalex.org/W3100923070","https://openalex.org/W3105746012","https://openalex.org/W3106806814","https://openalex.org/W3109085430","https://openalex.org/W3109097593","https://openalex.org/W3165647589","https://openalex.org/W3165915253","https://openalex.org/W3172675210","https://openalex.org/W3174887918","https://openalex.org/W3195026654","https://openalex.org/W3203663566","https://openalex.org/W3204763493","https://openalex.org/W3205276578","https://openalex.org/W3212555761","https://openalex.org/W3214642103","https://openalex.org/W4214700710","https://openalex.org/W4221143046","https://openalex.org/W4221161695","https://openalex.org/W4226052928","https://openalex.org/W4281557260","https://openalex.org/W4285294723","https://openalex.org/W4292779060","https://openalex.org/W4304099262","https://openalex.org/W4309591663","https://openalex.org/W4312434279","https://openalex.org/W4312501707","https://openalex.org/W4312581490","https://openalex.org/W4320165837","https://openalex.org/W4361866031","https://openalex.org/W4376312115","https://openalex.org/W4383108296","https://openalex.org/W4393154152","https://openalex.org/W4395091069","https://openalex.org/W4402917081","https://openalex.org/W6751885507","https://openalex.org/W6778883912","https://openalex.org/W6786247770","https://openalex.org/W6796242362","https://openalex.org/W6803039797","https://openalex.org/W6803342810","https://openalex.org/W6809646742","https://openalex.org/W6839459284","https://openalex.org/W6849732303","https://openalex.org/W6851513886"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"Visual":[0],"language":[1,48],"navigation":[2,93,116,139],"(VLN)":[3],"is":[4],"an":[5],"embodied":[6],"task":[7,159],"demanding":[8],"a":[9,21,73,172],"wide":[10],"range":[11],"of":[12,185],"skills":[13],"encompassing":[14],"understanding,":[15,120],"perception,":[16,122],"and":[17,123,147],"planning.":[18],"For":[19],"such":[20],"multifaceted":[22],"challenge,":[23],"previous":[24],"VLN":[25,76,158,169],"methods":[26],"totally":[27],"rely":[28],"on":[29,155,175],"one":[30,38],"model\u2019s":[31],"own":[32],"thinking":[33],"to":[34,103],"make":[35],"predictions":[36],"within":[37],"round.":[39],"However,":[40],"existing":[41],"models,":[42],"even":[43],"the":[44,67,156,166,182,198],"most":[45],"advanced":[46],"large":[47,81,173],"model":[49,170],"GPT4,":[50],"still":[51],"struggle":[52],"with":[53,55,100,133],"dealing":[54],"multiple":[56],"tasks":[57],"by":[58,140,171],"single-round":[59,189],"self-thinking.":[60,190],"In":[61],"this":[62,79],"work,":[63],"drawing":[64],"inspiration":[65],"from":[66],"expert":[68],"consultation":[69],"meeting,":[70],"we":[71,129],"introduce":[72],"novel":[74],"zero-shot":[75,168],"framework.":[77],"Within":[78],"framework,":[80],"models":[82],"possessing":[83],"distinct":[84],"abilities":[85],"are":[86],"served":[87],"as":[88],"domain":[89,134],"experts.":[90],"Our":[91,191],"proposed":[92],"agent,":[94],"namely":[95],"DiscussNav,":[96],"can":[97,136,194],"actively":[98],"discuss":[99],"these":[101],"experts":[102,135],"collect":[104],"essential":[105],"information":[106],"before":[107],"moving":[108],"at":[109,197],"every":[110],"step.":[111],"These":[112],"discussions":[113,132],"cover":[114],"critical":[115],"subtasks":[117],"like":[118],"instruction":[119],"environment":[121],"completion":[124],"estimation.":[125],"Through":[126],"comprehensive":[127],"experiments,":[128],"demonstrate":[130],"that":[131,162],"effectively":[137],"facilitate":[138],"perceiving":[141],"instruction-relevant":[142],"information,":[143],"correcting":[144],"inadvertent":[145],"errors,":[146],"sifting":[148],"through":[149],"in-consistent":[150],"movement":[151],"decisions.":[152],"The":[153],"performances":[154],"representative":[157],"R2R":[160],"show":[161],"our":[163,186],"method":[164,187],"surpasses":[165],"leading":[167],"margin":[174],"all":[176],"metrics.":[177],"Additionally,":[178],"real-robot":[179],"experiments":[180],"display":[181],"obvious":[183],"advantages":[184],"over":[188],"project":[192],"web":[193],"be":[195],"seen":[196],"https://sites.google.com/view/discussnav.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}