{"id":"https://openalex.org/W7124886871","doi":"https://doi.org/10.1109/lra.2026.3655277","title":"Curiosity-Driven Zero-Shot Object Navigation With Vision-Language Models","display_name":"Curiosity-Driven Zero-Shot Object Navigation With Vision-Language Models","publication_year":2026,"publication_date":"2026-01-19","ids":{"openalex":"https://openalex.org/W7124886871","doi":"https://doi.org/10.1109/lra.2026.3655277"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2026.3655277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3655277","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5100531908","display_name":"Zhengyi Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyi Gu","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123418591","display_name":"Yuheng Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuheng Zhou","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077666374","display_name":"Yuquan Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuquan Xue","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123375683","display_name":"Hanzhang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanzhang Wang","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-7552-0796","affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]}],"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":0.07174189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"3","first_page":"2818","last_page":"2824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7670000195503235,"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":0.7670000195503235,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.03689999878406525,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.03610000014305115,"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/object","display_name":"Object (grammar)","score":0.6333000063896179},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.574400007724762},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.548799991607666},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4887000024318695},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.48649999499320984},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.46140000224113464},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.383899986743927},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.33160001039505005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247999906539917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6801000237464905},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6333000063896179},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.574400007724762},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.548799991607666},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4887000024318695},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.48649999499320984},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.46140000224113464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44209998846054077},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39910000562667847},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3066999912261963},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2026.3655277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3655277","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/211368","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/211368","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6361363801","display_name":null,"funder_award_id":"62206167","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":19,"referenced_works":["https://openalex.org/W1987648924","https://openalex.org/W2107667896","https://openalex.org/W2566265240","https://openalex.org/W2950697717","https://openalex.org/W2953127211","https://openalex.org/W2962887844","https://openalex.org/W3009928773","https://openalex.org/W3116623932","https://openalex.org/W4225672218","https://openalex.org/W4313180266","https://openalex.org/W4386083015","https://openalex.org/W4387652983","https://openalex.org/W4389666115","https://openalex.org/W4394828156","https://openalex.org/W4401042437","https://openalex.org/W4401417236","https://openalex.org/W4402353987","https://openalex.org/W4404612908","https://openalex.org/W4405786698"],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"object":[1],"navigation":[2],"(ZSON)":[3],"in":[4,129],"unseen":[5],"environments":[6],"poses":[7],"a":[8,43,76,125],"significant":[9],"challenge":[10],"due":[11],"to":[12,35,56,105,138,149],"the":[13,19,48,62,65,99,103,117,145],"absence":[14],"of":[15,52,68,90],"object-specific":[16],"priors":[17],"and":[18,32,84,152],"need":[20],"for":[21],"efficient":[22,151],"exploration.":[23,58,154],"Existing":[24],"approaches":[25],"often":[26],"struggle":[27],"with":[28],"ineffective":[29],"search":[30],"strategies":[31],"repeated":[33],"visits":[34],"irrelevant":[36],"areas.":[37],"In":[38],"this":[39,91],"paper,":[40],"we":[41],"introduce":[42],"curiosity-driven":[44],"framework":[45],"that":[46,80,121,144],"leverages":[47],"commonsense":[49],"reasoning":[50],"capabilities":[51],"vision-language":[53],"models":[54],"(VLMs)":[55],"guide":[57],"At":[59],"each":[60],"step,":[61],"agent":[63,104],"estimates":[64],"semantic":[66],"plausibility":[67],"regions":[69,83],"based":[70],"on":[71,116],"language-conditioned":[72],"visual":[73],"cues,":[74],"constructing":[75],"dynamic":[77],"value":[78],"map":[79],"promotes":[81],"informative":[82],"suppresses":[85],"redundancy.":[86],"The":[87],"core":[88],"contribution":[89],"work":[92],"is":[93],"integrating":[94],"VLM-based":[95],"scene":[96],"understanding":[97],"into":[98],"curiosity":[100],"mechanism,":[101],"enabling":[102],"make":[106],"human-like":[107],"judgments":[108],"about":[109],"environmental":[110],"relevance":[111],"during":[112],"navigation.":[113],"Extensive":[114],"experiments":[115],"HM3D":[118],"benchmark":[119],"show":[120],"our":[122],"method":[123],"achieves":[124],"12.1%":[126],"absolute":[127],"improvement":[128],"Success":[130],"Rate":[131],"(SR)":[132],"over":[133],"strong":[134],"baselines":[135],"(from":[136],"56.5%":[137],"68.6%).":[139],"Qualitative":[140],"analysis":[141],"further":[142],"confirms":[143],"proposed":[146],"strategy":[147],"leads":[148],"more":[150],"goal-directed":[153]},"counts_by_year":[],"updated_date":"2026-01-29T23:13:10.619473","created_date":"2026-01-21T00:00:00"}
