{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T08:57:17Z","timestamp":1769677037213,"version":"3.49.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206167"],"award-info":[{"award-number":["62206167"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/lra.2026.3655277","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:56:21Z","timestamp":1768856181000},"page":"2818-2824","source":"Crossref","is-referenced-by-count":0,"title":["Curiosity-Driven Zero-Shot Object Navigation With Vision-Language Models"],"prefix":"10.1109","volume":"11","author":[{"given":"Zhengyi","family":"Gu","sequence":"first","affiliation":[{"name":"School of Computer Engineering and Science, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuquan","family":"Xue","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7552-0796","authenticated-orcid":false,"given":"Hanzhang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Engineering and Science, Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"42829","article-title":"ESC: Exploration with soft commonsense constraints for zero-shot object navigation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou","year":"2023"},{"key":"ref2","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref4","first-page":"21918","article-title":"Habitat-matterport 3D dataset (hm3d): 1000 large-scale 3D environments for embodied ai","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ramakrishnan","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_30"},{"key":"ref8","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"33","author":"Chaplot","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref10","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref11","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2024"},{"key":"ref12","article-title":"End-to-end navigation with vision language models: Transforming spatial reasoning into question-answering","author":"Goetting","year":"2024"},{"key":"ref13","first-page":"16301","article-title":"Instructnav: Zero-shot system for generic instruction navigation in unexplored environment","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Long","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. learn.","author":"Radford","year":"2021"},{"key":"ref16","first-page":"12336","article-title":"Clip on wheels: Zero-shot object navigation as object localization and exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Gadre","year":"2022"},{"key":"ref17","first-page":"32340","article-title":"Zson: Zero-shot object-goal navigation using multimodal goal embeddings","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"35","author":"Majumdar","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610499"},{"key":"ref19","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron"},{"key":"ref20","article-title":"The dawn of LMMs: Preliminary explorations with gpt-4v (ision)","author":"Yang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref22","first-page":"287","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Proc. Conf. Robot Learn.","author":"Brohan","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3387941"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.089"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-6495-6_36"},{"key":"ref27","first-page":"2683","article-title":"Navigation with large language models: Semantic guesswork as a heuristic for planning","volume-title":"Proc. Conf. Robot Learn.","author":"Shah","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref31","article-title":"Prismatic VLMs: Investigating the design space of visually-conditioned language models","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Karamcheti","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.24"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802670"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11359420\/11359082.pdf?arnumber=11359082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:00:58Z","timestamp":1769634058000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11359082\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":35,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3655277","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}