{"id":"https://openalex.org/W4416749005","doi":"https://doi.org/10.1109/iros60139.2025.11246938","title":"LGNav: Zero-Shot Object Navigation Driven by Language and Pointing Gesture Using Large Vision-Language Models","display_name":"LGNav: Zero-Shot Object Navigation Driven by Language and Pointing Gesture Using Large Vision-Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749005","doi":"https://doi.org/10.1109/iros60139.2025.11246938"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5050208967","display_name":"Weiyi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiyi Zhu","raw_affiliation_strings":["Southeast University,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446292","display_name":"Juan Liu","orcid":"https://orcid.org/0009-0008-3916-4754"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juan Liu","raw_affiliation_strings":["Samsung Electronics (China) R&D,Nanjing,China,210018"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics (China) R&D,Nanjing,China,210018","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010863275","display_name":"Xinde Li","orcid":"https://orcid.org/0000-0002-1529-4537"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinde Li","raw_affiliation_strings":["Southeast University,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102026886","display_name":"Zhiwei Lv","orcid":"https://orcid.org/0000-0001-8424-4747"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Lv","raw_affiliation_strings":["Southeast University,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047173176","display_name":"Zhehan Yang","orcid":"https://orcid.org/0000-0001-6249-0170"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhehan Yang","raw_affiliation_strings":["Southeast University,Nanjing,China,210096"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42414242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17170","last_page":"17177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.44440001249313354,"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":0.44440001249313354,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.4020000100135803,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.022600000724196434,"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/gesture","display_name":"Gesture","score":0.8435999751091003},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7821999788284302},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4936999976634979},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4569999873638153},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.45649999380111694},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.439300000667572},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.39160001277923584}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8435999751091003},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7821999788284302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657999992370605},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7139999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6881999969482422},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4569999873638153},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3580000102519989},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.2784000039100647},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":18,"referenced_works":["https://openalex.org/W1989386832","https://openalex.org/W2007336324","https://openalex.org/W2169528473","https://openalex.org/W2953127211","https://openalex.org/W2964339842","https://openalex.org/W3034201026","https://openalex.org/W3188422869","https://openalex.org/W4312956471","https://openalex.org/W4313180266","https://openalex.org/W4386075839","https://openalex.org/W4386083015","https://openalex.org/W4389666115","https://openalex.org/W4390204337","https://openalex.org/W4401042437","https://openalex.org/W4401417061","https://openalex.org/W4402716047","https://openalex.org/W4402753977","https://openalex.org/W4404612908"],"related_works":[],"abstract_inverted_index":{"In":[0],"human":[1,87],"communication,":[2],"referring":[3],"to":[4,19,59,98,113,153],"a":[5,16,100,129,148,204],"specific":[6],"object":[7,35,47,111,158,194],"within":[8],"an":[9,74],"environment":[10],"often":[11],"involves":[12],"the":[13,21,45,81,120,125,134,139,160,168,177,183,198],"combination":[14],"of":[15,170,185,206],"pointing":[17,53,82,186],"gesture":[18,54,83],"indicate":[20],"object\u2019s":[22],"direction":[23,84],"and":[24,30,52,90,146,200],"linguistic":[25],"descriptions":[26],"specifying":[27],"its":[28,173],"name":[29],"attributes,":[31],"thereby":[32],"enabling":[33],"precise":[34],"identification.":[36],"Inspired":[37],"by":[38,50,85,128],"this":[39,69,92],"natural":[40],"multimodal":[41],"interaction,":[42],"we":[43,71],"formalize":[44],"zero-shot":[46],"navigation":[48,77,162,195],"driven":[49],"language":[51],"(LGZSON)":[55],"task,":[56,70],"which":[57],"aims":[58],"more":[60],"closely":[61],"approximate":[62],"real-world":[63],"human-agent":[64],"communication":[65],"scenarios.":[66],"To":[67],"address":[68],"propose":[72],"LGNav,":[73,171],"open-set,":[75],"training-free":[76],"framework.":[78],"LGNav":[79,136,188],"estimates":[80],"extracting":[86],"body":[88],"landmarks":[89],"integrates":[91],"directional":[93],"information":[94],"with":[95],"depth":[96],"images":[97],"initialize":[99],"versatile":[101],"candidate":[102,117,144,157],"position":[103],"map":[104],"(VCPM).":[105],"The":[106],"framework":[107],"further":[108],"employs":[109],"open-vocabulary":[110],"detection":[112],"identify":[114],"all":[115],"potential":[116],"objects":[118],"in":[119,176,182],"environment,":[121,141],"projecting":[122],"them":[123],"onto":[124],"VCPM.":[126],"Guided":[127],"motion":[130],"policy":[131],"derived":[132],"from":[133],"VCPM,":[135],"continuously":[137],"explores":[138],"unknown":[140],"sequentially":[142],"visits":[143],"objects,":[145],"utilizes":[147],"large":[149],"vision-language":[150],"model":[151],"(LVLM)":[152],"verify":[154],"whether":[155],"each":[156],"satisfies":[159],"given":[161],"instruction.":[163],"Extensive":[164],"experimental":[165],"results":[166,191],"validate":[167],"effectiveness":[169],"demonstrating":[172],"strong":[174,207],"performance":[175],"LG-ZSON":[178],"task.":[179],"Furthermore,":[180],"even":[181],"absence":[184],"gestures,":[187],"achieves":[189],"competitive":[190],"on":[192],"standard":[193],"benchmarks,":[196],"including":[197],"Gibson":[199],"HM3D":[201],"datasets,":[202],"outperforming":[203],"range":[205],"baseline":[208],"methods.":[209]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}