{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T14:20:05Z","timestamp":1769955605230,"version":"3.49.0"},"reference-count":40,"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\/501100010256","name":"Guangzhou Municipal Science and Technology Project","doi-asserted-by":"publisher","award":["2024A03J0619"],"award-info":[{"award-number":["2024A03J0619"]}],"id":[{"id":"10.13039\/501100010256","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.2026.3655265","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:56:21Z","timestamp":1768856181000},"page":"2943-2950","source":"Crossref","is-referenced-by-count":0,"title":["Stairway to Success: An Online Floor-Aware Zero-Shot Object-Goal Navigation Framework via LLM-Driven Coarse-to-Fine Exploration"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9591-5358","authenticated-orcid":false,"given":"Zeying","family":"Gong","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"given":"Rong","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3439-5197","authenticated-orcid":false,"given":"Tianshuai","family":"Hu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, SAR, China"}]},{"given":"Ronghe","family":"Qiu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3884-2185","authenticated-orcid":false,"given":"Lingdong","family":"Kong","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0696-4363","authenticated-orcid":false,"given":"Lingfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5916-7505","authenticated-orcid":false,"given":"Guoyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"given":"Yiyi","family":"Ding","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2219-5569","authenticated-orcid":false,"given":"Junwei","family":"Liang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Habitat-MatterPort 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","author":"Ramakrishnan","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3457373"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341827"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01716"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610117"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3380948"},{"key":"ref8","first-page":"32340","article-title":"ZSON: Zero-shot object-goal navigation using multimodal goal embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Majumdar","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610499"},{"key":"ref12","first-page":"2049","article-title":"InstructNav: Zero-shot system for generic instruction navigation in unexplored environment","volume-title":"Proc. Conf. Robot Learn.","author":"Long","year":"2025"},{"key":"ref13","first-page":"5285","article-title":"SG-Nav: Online 3D scene graph prompting for LLM-based zero-shot object navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Yin","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128607"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3418269"},{"key":"ref17","article-title":"STRIVE: Structured representation integrating VLM reasoning for efficient object navigation","author":"Zhu","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.24"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3606388"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3381489"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.077"},{"key":"ref22","article-title":"Habitat challenge 2022","author":"Yadav","year":"2022"},{"key":"ref23","article-title":"ObjectNav revisited: On evaluation of embodied agents navigating to objects","author":"Batra","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref25","article-title":"D-Fine: Redefine regression task in detrs as fine-grained distribution refinement","author":"Peng","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref27","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023"},{"key":"ref28","article-title":"RedNet: Residual encoder-decoder network for indoor RGB-D semantic segmentation","author":"Jiang","year":"2018"},{"key":"ref29","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref32","article-title":"Qwen2.5 technical report","author":"Yang","year":"2024"},{"key":"ref33","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref34","article-title":"LLaMA-Adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023"},{"key":"ref35","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref36","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2023"},{"key":"ref37","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Hamilton","year":"2017"},{"key":"ref38","article-title":"DeepSeek-V3 technical report","author":"Liu","year":"2024"},{"key":"ref39","article-title":"Qwen-Vl: A versatile vision-language model for understanding, localization","author":"Bai","year":"2023"},{"key":"ref40","article-title":"Qwen2 technical report","author":"Team","year":"2024"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11359420\/11358651.pdf?arnumber=11358651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T07:53:21Z","timestamp":1769500401000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11358651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":40,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3655265","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}