{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:44:29Z","timestamp":1782798269923,"version":"3.54.5"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Research Foundation of Korea (NRF) grant"},{"name":"Korean Government, Ministry of Science and ICT","award":["RS-2025-24683458"],"award-info":[{"award-number":["RS-2025-24683458"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3704550","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:39:49Z","timestamp":1781725189000},"page":"95969-95988","source":"Crossref","is-referenced-by-count":0,"title":["VOCA: A VLM-Optimized Call Approach for Zero-Shot Navigation Using Target-Context Cues"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6453-8075","authenticated-orcid":false,"given":"Gunmin","family":"Yoo","sequence":"first","affiliation":[{"name":"School of Computer Science and Electrical Engineering, Handong Global University, Pohang, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2779-648X","authenticated-orcid":false,"given":"Hyunwoo","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Electrical Engineering, Handong Global University, Pohang, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0863-7503","authenticated-orcid":false,"given":"Sung Soo","family":"Hwang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Electrical Engineering, Handong Global University, Pohang, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICARA60736.2024.10553173"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3594204"},{"key":"ref4","article-title":"DD-PPO: Learning near-perfect pointgoal navigators from 2.5 billion frames","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wijmans"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref6","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume":"33","author":"Chaplot","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref8","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Proc. Conf. Robot Learn. (CoRL)","volume":"205","author":"Ichter"},{"key":"ref9","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn. (CoRL)","volume":"229","author":"Zitkovich"},{"key":"ref10","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Driess"},{"key":"ref11","first-page":"22","article-title":"End-to-end navigation with vision-language models: Transforming spatial reasoning into question-answering","volume-title":"Proc. Int. Conf. Neuro-Symbolic Systems","volume":"288","author":"Goetting"},{"key":"ref12","first-page":"492","article-title":"LM-Nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proc. Conf. Robot Learn. (CoRL)","volume":"205","author":"Shah"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref14","first-page":"23","article-title":"SayPlan: Grounding large language models using 3D scene graphs for scalable robot task planning","volume-title":"Proc. Conf. Robot Learn. (CoRL)","volume":"229","author":"Rana"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.529"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610499"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02280"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref21","first-page":"53757","article-title":"VoroNav: Voronoi-based zero-shot object navigation with large language model","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"235","author":"Wu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_10"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1244"},{"key":"ref25","article-title":"Learning to explore using active neural SLAM","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chaplot"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.341"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP55912.2026.11463005"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01128"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Radford"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref32","article-title":"Habitat-Matterport 3D Dataset (HM3D): 1000 large-scale 3D environments for embodied AI","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks (NeurIPS Datasets Benchmarks)","author":"Ramakrishnan"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00477"},{"key":"ref34","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018","journal-title":"arXiv:1807.06757"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11569479.pdf?arnumber=11569479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:10:46Z","timestamp":1782796246000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11569479\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3704550","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}