{"id":"https://openalex.org/W7165010589","doi":"https://doi.org/10.1109/access.2026.3704550","title":"VOCA: A VLM-Optimized Call Approach for Zero-Shot Navigation Using Target-Context Cues","display_name":"VOCA: A VLM-Optimized Call Approach for Zero-Shot Navigation Using Target-Context Cues","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7165010589","doi":"https://doi.org/10.1109/access.2026.3704550"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3704550","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3704550","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3704550","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138770803","display_name":"Gunmin Yoo","orcid":"https://orcid.org/0009-0001-6453-8075"},"institutions":[{"id":"https://openalex.org/I113825674","display_name":"Handong Global University","ror":"https://ror.org/00txhkt32","country_code":"KR","type":"education","lineage":["https://openalex.org/I113825674"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gunmin Yoo","raw_affiliation_strings":["School of Computer Science and Electrical Engineering, Handong Global University, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0009-0001-6453-8075","affiliations":[{"raw_affiliation_string":"School of Computer Science and Electrical Engineering, Handong Global University, Pohang, South Korea","institution_ids":["https://openalex.org/I113825674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085032254","display_name":"Hyunwoo Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I113825674","display_name":"Handong Global University","ror":"https://ror.org/00txhkt32","country_code":"KR","type":"education","lineage":["https://openalex.org/I113825674"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunwoo Gu","raw_affiliation_strings":["School of Computer Science and Electrical Engineering, Handong Global University, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0009-0008-2779-648X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Electrical Engineering, Handong Global University, Pohang, South Korea","institution_ids":["https://openalex.org/I113825674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003984706","display_name":"Sung Soo Hwang","orcid":"https://orcid.org/0000-0002-0863-7503"},"institutions":[{"id":"https://openalex.org/I113825674","display_name":"Handong Global University","ror":"https://ror.org/00txhkt32","country_code":"KR","type":"education","lineage":["https://openalex.org/I113825674"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung Soo Hwang","raw_affiliation_strings":["School of Computer Science and Electrical Engineering, Handong Global University, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0863-7503","affiliations":[{"raw_affiliation_string":"School of Computer Science and Electrical Engineering, Handong Global University, Pohang, South Korea","institution_ids":["https://openalex.org/I113825674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I113825674"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79591568,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"95969","last_page":"95988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.1242000013589859,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.1242000013589859,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.10760000348091125,"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/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.10660000145435333,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/radar-tracker","display_name":"Radar tracker","score":0.25279998779296875},{"id":"https://openalex.org/keywords/global-positioning-system","display_name":"Global Positioning System","score":0.22290000319480896},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.21559999883174896},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2092999964952469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688999772071838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4661000072956085},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4458000063896179},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3043999969959259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25429999828338623},{"id":"https://openalex.org/C32283439","wikidata":"https://www.wikidata.org/wiki/Q1407014","display_name":"Radar tracker","level":3,"score":0.25279998779296875},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.22290000319480896},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.21559999883174896},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2092999964952469},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2045000046491623}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3704550","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3704550","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7a1384faeaee4cc28df2a0a61c3a2d92","is_oa":false,"landing_page_url":"https://doaj.org/article/7a1384faeaee4cc28df2a0a61c3a2d92","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 95969-95988 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3704550","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3704550","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"object":[1,17,164],"navigation":[2,42,65,168],"with":[3],"vision-language":[4,27,123,201],"models":[5,28,73],"(VLMs)":[6],"allows":[7],"robots":[8],"to":[9,25,91,185],"follow":[10],"natural":[11],"language":[12,72,86],"instructions":[13],"about":[14,205,213],"previously":[15],"unseen":[16],"categories":[18],"without":[19],"task-specific":[20],"training.":[21],"However,":[22],"frequent":[23,193],"calls":[24,62,203],"large":[26],"incur":[29],"high":[30],"computational":[31],"cost":[32],"and":[33,104,144,166,207,233,236],"long":[34],"inference":[35],"latency,":[36],"which":[37,108],"are":[38],"problematic":[39],"for":[40],"real-time":[41,163,240],"on":[43,161,175,192],"physical":[44],"robots.":[45],"This":[46],"paper":[47],"proposes":[48],"the":[49,58,69,78,152,171,176,198,208,234],"VLM-Optimized":[50],"Call":[51],"Approach":[52],"(VOCA),":[53],"a":[54,83,110,116,121,127,155,162,186,226],"framework":[55],"that":[56,159,189,223],"reduces":[57,197],"number":[59,129,199],"of":[60,71,80,130,200,239],"model":[61,87,124,194,202],"while":[63,215],"preserving":[64],"performance.":[66,219],"VOCA":[67,196,224],"separates":[68],"use":[70],"into":[74],"two":[75],"stages.":[76],"At":[77],"beginning":[79],"each":[81],"episode,":[82],"lightweight":[84],"text-only":[85],"is":[88],"called":[89],"once":[90],"generate":[92],"Target-Context":[93],"Cues,":[94],"such":[95,140],"as":[96,141],"likely":[97],"support":[98],"objects,":[99,102],"strong":[100,187],"co-occurring":[101],"<monospace>Gateways</monospace>,":[103],"visually":[105],"similar":[106],"distractors,":[107],"form":[109],"static":[111],"knowledge":[112],"base.":[113],"During":[114],"navigation,":[115],"call":[117],"policy":[118],"selectively":[119],"invokes":[120],"multimodal":[122],"only":[125],"at":[126],"small":[128],"key":[131],"moments,":[132],"including":[133],"initial":[134],"global":[135],"route":[136],"planning,":[137],"resolving":[138],"deadlocks":[139],"visual":[142],"loops,":[143],"verifying":[145],"final":[146],"target":[147],"candidates.":[148],"Between":[149],"these":[150],"calls,":[151,195],"agent":[153],"follows":[154],"VLM-free":[156],"control":[157],"loop":[158],"relies":[160,190],"detector":[165],"local":[167],"guided":[169],"by":[170,204,212],"precomputed":[172],"cues.":[173],"Experiments":[174],"large-scale":[177],"HM3D":[178],"ObjectNav":[179],"v2":[180],"benchmark":[181],"show":[182],"that,":[183],"compared":[184],"baseline":[188],"heavily":[191],"48%":[206],"average":[209],"episode":[210],"time":[211],"32%,":[214],"maintaining":[216],"comparable":[217],"success":[218],"These":[220],"results":[221],"demonstrate":[222],"provides":[225],"practical":[227],"balance":[228],"between":[229],"high-level":[230],"semantic":[231],"reasoning":[232],"latency":[235],"efficiency":[237],"requirements":[238],"robotic":[241],"navigation.":[242]},"counts_by_year":[],"updated_date":"2026-06-30T06:16:30.551410","created_date":"2026-06-18T00:00:00"}
