{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T04:27:37Z","timestamp":1769747257517,"version":"3.49.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T00:00:00Z","timestamp":1737417600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T00:00:00Z","timestamp":1737417600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,1,21]]},"DOI":"10.1109\/sii59315.2025.10870978","type":"proceedings-article","created":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T18:17:07Z","timestamp":1739384227000},"page":"1274-1279","source":"Crossref","is-referenced-by-count":2,"title":["LLM-Guided Zero-Shot Visual Object Navigation with Building Semantic Map"],"prefix":"10.1109","author":[{"given":"Jin","family":"Shi","sequence":"first","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan,606-8501"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Yagi","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan,606-8501"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Yamamori","sequence":"additional","affiliation":[{"name":"ATR,Computational Neuroscience Labs,Department of Brain Robot Interface,Japan,619-0237"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Morimoto","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan,606-8501"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00645"},{"key":"ref3","article-title":"Objectnav revisited: On evaluation of embodied agents navigating to objects","author":"Batra","year":"2020"},{"key":"ref4","article-title":"Learning exploration policies for navigation","volume-title":"7th International Conference on Learning Representations","author":"Chen"},{"key":"ref5","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01716"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610117"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref9","first-page":"32 340","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3346800"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981646"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref16","article-title":"Habitat-matterport 3d dataset (HM3D): 1000 large-scale 3d environments for embodied AI","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1","author":"Ramakrishnan"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"ref18","article-title":"DD-PPO: learning near-perfect pointgoal navigators from 2.5 billion frames","volume-title":"8th International Conference on Learning Representations","author":"Wijmans"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161059"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802670"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref22","first-page":"19 730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref24","article-title":"Advances in embodied navigation using large language models: A survey","author":"Lin","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"ref27","volume-title":"Artificial Intelligence Applications and Innovations: 20th IFIP WG 12.5 International Conference, AIAI 2024, Corfu, Greece, June 27-30, 2024, Proceedings, Part IV","volume":"714","author":"Maglogiannis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref30","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","first-page":"666","article-title":"Last-mile embodied visual navigation","volume-title":"Conference on Robot Learning","author":"Wasserman"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2013.2248309"},{"key":"ref33","first-page":"7727","article-title":"VER: Scaling on-policy rl leads to the emergence of navigation in embodied rearrangement","volume":"35","author":"Wijmans","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref36","article-title":"Leveraging large (visual) language models for robot 3d scene understanding","author":"Chen","year":"2023"}],"event":{"name":"2025 IEEE\/SICE International Symposium on System Integration (SII)","location":"Munich, Germany","start":{"date-parts":[[2025,1,21]]},"end":{"date-parts":[[2025,1,24]]}},"container-title":["2025 IEEE\/SICE International Symposium on System Integration (SII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10870372\/10870581\/10870978.pdf?arnumber=10870978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T19:50:04Z","timestamp":1740081004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10870978\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,21]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/sii59315.2025.10870978","relation":{},"subject":[],"published":{"date-parts":[[2025,1,21]]}}}