{"id":"https://openalex.org/W4401417061","doi":"https://doi.org/10.1109/icra57147.2024.10610712","title":"VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation","display_name":"VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401417061","doi":"https://doi.org/10.1109/icra57147.2024.10610712"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610712","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/A5103004161","display_name":"Naoki Yokoyama","orcid":"https://orcid.org/0009-0002-2919-936X"},"institutions":[{"id":"https://openalex.org/I4210143335","display_name":"Boston Dynamics (United States)","ror":"https://ror.org/0488ezv32","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143335"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naoki Yokoyama","raw_affiliation_strings":["Boston Dynamics AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston Dynamics AI Institute","institution_ids":["https://openalex.org/I4210143335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064581452","display_name":"Sehoon Ha","orcid":"https://orcid.org/0000-0002-1972-328X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sehoon Ha","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070032468","display_name":"Dhruv Batra","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Batra","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076469070","display_name":"Jiuguang Wang","orcid":"https://orcid.org/0000-0001-6881-9918"},"institutions":[{"id":"https://openalex.org/I4210143335","display_name":"Boston Dynamics (United States)","ror":"https://ror.org/0488ezv32","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143335"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiuguang Wang","raw_affiliation_strings":["Boston Dynamics AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston Dynamics AI Institute","institution_ids":["https://openalex.org/I4210143335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071943173","display_name":"Bernadette Bucher","orcid":"https://orcid.org/0000-0003-1396-4872"},"institutions":[{"id":"https://openalex.org/I4210143335","display_name":"Boston Dynamics (United States)","ror":"https://ror.org/0488ezv32","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143335"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bernadette Bucher","raw_affiliation_strings":["Boston Dynamics AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston Dynamics AI Institute","institution_ids":["https://openalex.org/I4210143335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9923999905586243,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9537000060081482,"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":0.6997311115264893},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6546815037727356},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6337330341339111},{"id":"https://openalex.org/keywords/frontier","display_name":"Frontier","score":0.6303505301475525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5060760378837585},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44536370038986206},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4165840744972229},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3204795718193054},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12478294968605042},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10673168301582336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6997311115264893},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6546815037727356},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6337330341339111},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.6303505301475525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5060760378837585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44536370038986206},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4165840744972229},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3204795718193054},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12478294968605042},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10673168301582336},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610712","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334879","display_name":"Korea Evaluation Institute of Industrial Technology","ror":"https://ror.org/03z9cwa38"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2107667896","https://openalex.org/W2136980446","https://openalex.org/W2884565639","https://openalex.org/W2953127211","https://openalex.org/W2964339842","https://openalex.org/W3009928773","https://openalex.org/W3036497058","https://openalex.org/W3036498537","https://openalex.org/W3040041096","https://openalex.org/W3138508885","https://openalex.org/W3166396011","https://openalex.org/W3201759799","https://openalex.org/W4214643368","https://openalex.org/W4221163448","https://openalex.org/W4254415482","https://openalex.org/W4282981845","https://openalex.org/W4283640928","https://openalex.org/W4305009099","https://openalex.org/W4312360147","https://openalex.org/W4312396969","https://openalex.org/W4313180266","https://openalex.org/W4318719538","https://openalex.org/W4322616103","https://openalex.org/W4327525106","https://openalex.org/W4382322597","https://openalex.org/W4386075839","https://openalex.org/W4386076325","https://openalex.org/W4386083015","https://openalex.org/W4386083032","https://openalex.org/W4388936652","https://openalex.org/W4389667118","https://openalex.org/W4390204337","https://openalex.org/W4404612908","https://openalex.org/W6753516098","https://openalex.org/W6779913221","https://openalex.org/W6780167394","https://openalex.org/W6780443396","https://openalex.org/W6791353385","https://openalex.org/W6800673378","https://openalex.org/W6839650396","https://openalex.org/W6840041517","https://openalex.org/W6841586102","https://openalex.org/W6845716266","https://openalex.org/W6849793301","https://openalex.org/W6850481810","https://openalex.org/W6850630192","https://openalex.org/W6850787431","https://openalex.org/W6854362512"],"related_works":["https://openalex.org/W2347401120","https://openalex.org/W2041961361","https://openalex.org/W2310010941","https://openalex.org/W1988132375","https://openalex.org/W2334292868","https://openalex.org/W579144800","https://openalex.org/W2147233680","https://openalex.org/W2069525434","https://openalex.org/W2046798653","https://openalex.org/W2021057137"],"abstract_inverted_index":{"Understanding":[0],"how":[1],"humans":[2],"leverage":[3],"semantic":[4,48,217],"knowledge":[5,197],"to":[6,13,44,60,72,83,89,155,180,183],"navigate":[7,45,182],"unfamiliar":[8],"environments":[9,106],"and":[10,42,63,67,113,176],"decide":[11],"where":[12],"explore":[14,90],"next":[15],"is":[16,37],"pivotal":[17],"for":[18,91,140],"developing":[19],"robots":[20,161],"capable":[21],"of":[22,95,198,203,209,216,220],"human-like":[23],"search":[24],"behaviors.":[25],"We":[26,101,171],"introduce":[27],"a":[28,68,74,96],"zero-shot":[29,151],"navigation":[30],"approach,":[31],"Vision-Language":[32],"Frontier":[33],"Maps":[34],"(VLFM),":[35],"which":[36],"inspired":[38],"by":[39,133,136],"human":[40],"reasoning":[41],"designed":[43],"towards":[46],"unseen":[47],"objects":[49,185],"in":[50,104,190,212],"novel":[51],"environments.":[52],"VLFM":[53,78,103,123,173,204],"builds":[54],"occupancy":[55],"maps":[56],"from":[57,107],"depth":[58],"observations":[59,66],"identify":[61,84],"frontiers,":[62],"leverages":[64],"RGB":[65],"pre-trained":[69],"vision-language":[70,210],"model":[71],"generate":[73],"language-grounded":[75],"value":[76],"map.":[77],"then":[79],"uses":[80],"this":[81],"map":[82],"the":[85,108,119,141,164,191,199,206,214],"most":[86],"promising":[87,207],"frontier":[88],"finding":[92],"an":[93,187],"instance":[94],"given":[97],"target":[98,184],"object":[99],"category.":[100],"evaluate":[102],"photo-realistic":[105],"Gibson,":[109],"Habitat-Matterport":[110],"3D":[111,115],"(HM3D),":[112],"Matterport":[114],"(MP3D)":[116],"datasets":[117,130],"within":[118,186],"Habitat":[120],"simulator.":[121],"Remarkably,":[122],"achieves":[124],"state-of-the-art":[125],"results":[126],"on":[127,159,174],"all":[128],"three":[129],"as":[131,163],"measured":[132],"success":[134],"weighted":[135],"path":[137],"length":[138],"(SPL)":[139],"Object":[142],"Goal":[143],"Navigation":[144],"task.":[145],"Furthermore,":[146],"we":[147],"show":[148],"that":[149],"VLFM\u2019s":[150],"nature":[152],"enables":[153],"it":[154],"be":[156,225],"readily":[157],"deployed":[158],"real-world":[160],"such":[162],"Boston":[165],"Dynamics":[166],"Spot":[167,175],"mobile":[168],"manipulation":[169],"platform.":[170],"deploy":[172],"demonstrate":[177],"its":[178],"capability":[179],"efficiently":[181],"office":[188],"building":[189],"real":[192,221],"world,":[193],"without":[194],"any":[195],"prior":[196],"environment.":[200],"The":[201],"accomplishments":[202],"underscore":[205],"potential":[208],"models":[211],"advancing":[213],"field":[215],"navigation.":[218],"Videos":[219],"world":[222],"deployment":[223],"can":[224],"viewed":[226],"at":[227],"naoki.io/vlfm.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":73},{"year":2024,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}