{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:41:02Z","timestamp":1766061662293,"version":"3.48.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246938","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"17170-17177","source":"Crossref","is-referenced-by-count":0,"title":["LGNav: Zero-Shot Object Navigation Driven by Language and Pointing Gesture Using Large Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Weiyi","family":"Zhu","sequence":"first","affiliation":[{"name":"Southeast University,Nanjing,China,210096"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Liu","sequence":"additional","affiliation":[{"name":"Samsung Electronics (China) R&D,Nanjing,China,210018"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinde","family":"Li","sequence":"additional","affiliation":[{"name":"Southeast University,Nanjing,China,210096"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwei","family":"Lv","sequence":"additional","affiliation":[{"name":"Southeast University,Nanjing,China,210096"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhehan","family":"Yang","sequence":"additional","affiliation":[{"name":"Southeast University,Nanjing,China,210096"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Objectnav revisited: On evaluation of embodied agents navigating to objects","year":"2020","author":"Batra","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/568513.568514"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.dr.2010.10.001"},{"key":"ref4","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume":"33","author":"Chaplot","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","first-page":"32340","article-title":"Zson: Zero-shot object-goal navigation using multimodal goal embeddings","volume":"35","author":"Majumdar","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref7","first-page":"42829","article-title":"Esc: Exploration with soft commonsense constraints for zero-shot object navigation","volume-title":"International Conference on Machine Learning","author":"Zhou"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01716"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"article-title":"Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai","year":"2021","author":"Ramakrishnan","key":"ref13"},{"article-title":"On the opportunities and risks of foundation models","year":"2021","author":"Bommasani","key":"ref14"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3346800"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.24"},{"issue":"1","key":"ref19","first-page":"1","article-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision)","volume":"9","author":"Yang","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636208"},{"article-title":"Sharing cognition: Human gesture and natural language grounding based planning and navigation for indoor robots","year":"2021","author":"Kumar","key":"ref22"},{"article-title":"Mediapipe: A framework for building perception pipelines","year":"2019","author":"Lugaresi","key":"ref23"},{"article-title":"Simple stupid funnel algorithm","year":"2010","author":"Mononen","key":"ref24"},{"issue":"12","key":"ref25","first-page":"48","article-title":"An overview of pathfinding in navigation mesh","volume":"12","author":"Cui","year":"2012","journal-title":"International Journal of Computer Science and Network Security"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"article-title":"On evaluation of embodied navigation agents","year":"2018","author":"Anderson","key":"ref27"},{"article-title":"Habitat 3.0: A co-habitat for humans, avatars and robots","year":"2023","author":"Puig","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00323"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"article-title":"Sam 2: Segment anything in images and videos","year":"2024","author":"Ravi","key":"ref32"},{"key":"ref33","article-title":"Doubao foundation models"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246938.pdf?arnumber=11246938","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:37:27Z","timestamp":1766061447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246938\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246938","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}