{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T15:01:35Z","timestamp":1784041295364,"version":"3.55.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003662","name":"Korea Evaluation Institute of Industrial Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003662","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610712","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"42-48","source":"Crossref","is-referenced-by-count":129,"title":["VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation"],"prefix":"10.1109","author":[{"given":"Naoki","family":"Yokoyama","sequence":"first","affiliation":[{"name":"Boston Dynamics AI Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sehoon","family":"Ha","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhruv","family":"Batra","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiuguang","family":"Wang","sequence":"additional","affiliation":[{"name":"Boston Dynamics AI Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernadette","family":"Bucher","sequence":"additional","affiliation":[{"name":"Boston Dynamics AI Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref2","article-title":"ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation","author":"Zhou","year":"2023"},{"key":"ref3","article-title":"How To Not Train Your Dragon: Training-free Embodied Object Navigation with Semantic Frontiers","author":"Chen","year":"2023","journal-title":"RSS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3346800"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref8","article-title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Ramakrishnan"},{"key":"ref9","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":"NeurIPS"},{"key":"ref10","article-title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","author":"Batra","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01581"},{"key":"ref12","article-title":"Semantic Visual Navigation by Watching YouTube Videos","author":"Chang","year":"2020","journal-title":"NeurIPS"},{"key":"ref13","first-page":"5982","article-title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","volume":"35","author":"Deitke","year":"2022","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49997.2022.9926452"},{"key":"ref15","article-title":"Ovrl-v2: A simple state-of-art baseline for imagenav and objectnav","author":"Yadav","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01716"},{"key":"ref17","article-title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","author":"Chaplot","year":"2020","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01485"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981646"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00645"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341773"},{"key":"ref25","first-page":"8748","article-title":"Learning Transferable Visual Models from Natural Language Supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_9081"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref30","article-title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","author":"Liu","year":"2023"},{"key":"ref31","article-title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","author":"Zhang","year":"2023"},{"key":"ref32","article-title":"On Evaluation of Embodied Navigation Agents","author":"Anderson","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3336109"},{"key":"ref34","article-title":"Rethinking Sim2Real: Lower Fidelity Simulation Leads to Higher Sim2Real Transfer in Navigation","volume-title":"Conference on Robot Learning (CoRL)","author":"Truong"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01672"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636743"},{"key":"ref37","article-title":"ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings","author":"Majumdar","year":"2022","journal-title":"NeurIPS"},{"key":"ref38","article-title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","author":"Bhat","year":"2023"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610712.pdf?arnumber=10610712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:21:27Z","timestamp":1723267287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610712\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610712","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}