{"id":"https://openalex.org/W4399769027","doi":"https://doi.org/10.1109/icara60736.2024.10553173","title":"Zero-shot Object Navigation with Vision-Language Foundation Models Reasoning","display_name":"Zero-shot Object Navigation with Vision-Language Foundation Models Reasoning","publication_year":2024,"publication_date":"2024-02-22","ids":{"openalex":"https://openalex.org/W4399769027","doi":"https://doi.org/10.1109/icara60736.2024.10553173"},"language":"en","primary_location":{"id":"doi:10.1109/icara60736.2024.10553173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icara60736.2024.10553173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 10th International Conference on Automation, Robotics and Applications (ICARA)","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/A5041372265","display_name":"Shuaihang Yuan","orcid":"https://orcid.org/0000-0002-7092-7966"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"Shuaihang Yuan","raw_affiliation_strings":["NYUAD Center for Artificial Intelligence and Robotics (CAIR),Abu Dhabi,UAE","NYUAD Center for Artificial Intelligence and Robotics (CAIR), Abu Dhabi, UAE","New York University Abu Dhabi, UAE","New York University, US"],"affiliations":[{"raw_affiliation_string":"NYUAD Center for Artificial Intelligence and Robotics (CAIR),Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210121405"]},{"raw_affiliation_string":"NYUAD Center for Artificial Intelligence and Robotics (CAIR), Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210121405"]},{"raw_affiliation_string":"New York University Abu Dhabi, UAE","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"New York University, US","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005190949","display_name":"Muhammad Shafique","orcid":"https://orcid.org/0000-0002-2607-8135"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]},{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Muhammad Shafique","raw_affiliation_strings":["NYUAD Center for Artificial Intelligence and Robotics (CAIR),Abu Dhabi,UAE","New York University, US","New York University Abu Dhabi, UAE","NYUAD Center for Artificial Intelligence and Robotics (CAIR), Abu Dhabi, UAE"],"affiliations":[{"raw_affiliation_string":"NYUAD Center for Artificial Intelligence and Robotics (CAIR),Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210121405"]},{"raw_affiliation_string":"New York University, US","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"New York University Abu Dhabi, UAE","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"NYUAD Center for Artificial Intelligence and Robotics (CAIR), Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021014362","display_name":"Mohamed Baghdadi","orcid":"https://orcid.org/0000-0002-5707-273X"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Mohamed Riyadh Baghdadi","raw_affiliation_strings":["NYUAD Center for Artificial Intelligence and Robotics (CAIR),Abu Dhabi,UAE","New York University Abu Dhabi, UAE","NYUAD Center for Artificial Intelligence and Robotics (CAIR), Abu Dhabi, UAE","New York University, US"],"affiliations":[{"raw_affiliation_string":"NYUAD Center for Artificial Intelligence and Robotics (CAIR),Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210121405"]},{"raw_affiliation_string":"New York University Abu Dhabi, UAE","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"NYUAD Center for Artificial Intelligence and Robotics (CAIR), Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210121405"]},{"raw_affiliation_string":"New York University, US","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082413942","display_name":"Farshad Khorrami","orcid":"https://orcid.org/0000-0002-8418-004X"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Farshad Khorrami","raw_affiliation_strings":["NYUAD Center for Artificial Intelligence and Robotics (CAIR),Abu Dhabi,UAE","New York University, US","NYUAD Center for Artificial Intelligence and Robotics (CAIR), Abu Dhabi, UAE","New York University Abu Dhabi, UAE"],"affiliations":[{"raw_affiliation_string":"NYUAD Center for Artificial Intelligence and Robotics (CAIR),Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210121405"]},{"raw_affiliation_string":"New York University, US","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"NYUAD Center for Artificial Intelligence and Robotics (CAIR), Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210121405"]},{"raw_affiliation_string":"New York University Abu Dhabi, UAE","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048765370","display_name":"Anthony Tzes","orcid":"https://orcid.org/0000-0003-3709-2810"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Anthony Tzes","raw_affiliation_strings":["NYUAD Center for Artificial Intelligence and Robotics (CAIR),Abu Dhabi,UAE","NYUAD Center for Artificial Intelligence and Robotics (CAIR), Abu Dhabi, UAE","New York University, US","New York University Abu Dhabi, UAE"],"affiliations":[{"raw_affiliation_string":"NYUAD Center for Artificial Intelligence and Robotics (CAIR),Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210121405"]},{"raw_affiliation_string":"NYUAD Center for Artificial Intelligence and Robotics (CAIR), Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210121405"]},{"raw_affiliation_string":"New York University, US","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"New York University Abu Dhabi, UAE","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083935587","display_name":"Yi Fang","orcid":"https://orcid.org/0000-0001-9427-3883"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Yi Fang","raw_affiliation_strings":["NYUAD Center for Artificial Intelligence and Robotics (CAIR),Abu Dhabi,UAE","NYUAD Center for Artificial Intelligence and Robotics (CAIR), Abu Dhabi, UAE","New York University Abu Dhabi, UAE","New York University, US"],"affiliations":[{"raw_affiliation_string":"NYUAD Center for Artificial Intelligence and Robotics (CAIR),Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210121405"]},{"raw_affiliation_string":"NYUAD Center for Artificial Intelligence and Robotics (CAIR), Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210121405"]},{"raw_affiliation_string":"New York University Abu Dhabi, UAE","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"New York University, US","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5041372265"],"corresponding_institution_ids":["https://openalex.org/I4210121405","https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.5248,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63465969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"501","last_page":"505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9986000061035156,"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":0.996399998664856,"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/zero","display_name":"Zero (linguistics)","score":0.6770792007446289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6595723628997803},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5233418345451355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5029858946800232},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47129762172698975},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.45111727714538574},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4215432107448578},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08918049931526184},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08549222350120544}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6770792007446289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6595723628997803},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5233418345451355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5029858946800232},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47129762172698975},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.45111727714538574},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4215432107448578},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08918049931526184},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08549222350120544},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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/icara60736.2024.10553173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icara60736.2024.10553173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 10th International Conference on Automation, Robotics and Applications (ICARA)","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":50,"referenced_works":["https://openalex.org/W2107667896","https://openalex.org/W2314286347","https://openalex.org/W2321229037","https://openalex.org/W2884565639","https://openalex.org/W2896457183","https://openalex.org/W2953127211","https://openalex.org/W3009928773","https://openalex.org/W3011144238","https://openalex.org/W3034201026","https://openalex.org/W3040041096","https://openalex.org/W3109001458","https://openalex.org/W3109097593","https://openalex.org/W3126672009","https://openalex.org/W3201759799","https://openalex.org/W3206376852","https://openalex.org/W3210395242","https://openalex.org/W3211686893","https://openalex.org/W4293566037","https://openalex.org/W4294010056","https://openalex.org/W4304195432","https://openalex.org/W4306705228","https://openalex.org/W4312956471","https://openalex.org/W4313180266","https://openalex.org/W4318718936","https://openalex.org/W4318719538","https://openalex.org/W4322718191","https://openalex.org/W4366330503","https://openalex.org/W4385416186","https://openalex.org/W4386083015","https://openalex.org/W4386907141","https://openalex.org/W4390204337","https://openalex.org/W4391759936","https://openalex.org/W4393154152","https://openalex.org/W6747106673","https://openalex.org/W6753516098","https://openalex.org/W6755207826","https://openalex.org/W6774815639","https://openalex.org/W6780443396","https://openalex.org/W6791353385","https://openalex.org/W6803557570","https://openalex.org/W6811013733","https://openalex.org/W6839459284","https://openalex.org/W6842667729","https://openalex.org/W6846113813","https://openalex.org/W6846254642","https://openalex.org/W6849177959","https://openalex.org/W6849793301","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6857217666"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"This":[0],"research":[1],"introduces":[2],"a":[3,62,70,97],"novel":[4],"method":[5],"for":[6,36,65],"zero-shot":[7],"object":[8,66],"navigation,":[9],"enabling":[10],"agents":[11,47],"to":[12,29,45,68,78,112],"navigate":[13],"unexplored":[14],"environments.":[15],"Our":[16,87],"approach":[17],"differs":[18],"from":[19],"traditional":[20],"methods,":[21],"which":[22],"often":[23],"fail":[24],"in":[25,100],"new":[26],"settings":[27],"due":[28],"their":[30],"dependence":[31],"on":[32,89],"large":[33],"navigation":[34],"datasets":[35],"training.":[37],"We":[38],"use":[39],"Large":[40],"Vision":[41],"Language":[42],"Models":[43],"(LVLMs)":[44],"help":[46],"understand":[48],"and":[49,104],"move":[50],"through":[51],"unfamiliar":[52],"visual":[53],"environments":[54],"without":[55],"prior":[56],"experience.":[57],"The":[58],"process":[59],"involves":[60],"using":[61],"pretrained":[63],"LVLM":[64,76],"detection":[67],"create":[69],"semantic":[71],"map,":[72],"followed":[73],"by":[74,107],"employing":[75],"again":[77],"predict":[79],"the":[80,84,90,113],"likely":[81],"location":[82],"of":[83],"target":[85],"object.":[86],"experiments":[88],"RoboTHOR":[91],"benchmark":[92],"show":[93],"improved":[94],"performance,":[95],"with":[96],"1.8%":[98],"increase":[99],"both":[101],"Success":[102,105],"Rate":[103],"Weighted":[106],"Path":[108],"Length":[109],"(SPL)":[110],"compared":[111],"existing":[114],"best":[115],"method,":[116],"ESC.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}