{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:23:05Z","timestamp":1778257385118,"version":"3.51.4"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021ZD0110700"],"award-info":[{"award-number":["2021ZD0110700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373315"],"award-info":[{"award-number":["62373315"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tcsvt.2025.3531410","type":"journal-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T19:07:34Z","timestamp":1737400054000},"page":"6231-6244","source":"Crossref","is-referenced-by-count":7,"title":["E\u00b2BA: Environment Exploration and Backtracking Agent for Visual Language Object Navigation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4065-6659","authenticated-orcid":false,"given":"Yuhong","family":"Shi","sequence":"first","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0321-4955","authenticated-orcid":false,"given":"Jianyi","family":"Liu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihang","family":"Sun","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9898-5543","authenticated-orcid":false,"given":"Xinhu","family":"Zheng","sequence":"additional","affiliation":[{"name":"Intelligent Transportation Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","volume-title":"arXiv:2109.08238","author":"Ramakrishnan","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10341563"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00511"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icra46639.2022.9812337"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2972281"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161059"},{"key":"ref8","article-title":"OVRL-v2: A simple state-of-art baseline for ImageNav and ObjectNav","volume-title":"arXiv:2303.07798","author":"Yadav","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.075"},{"key":"ref10","article-title":"Learning transferable visual models from natural language supervision","volume-title":"arXiv:2103.00020","author":"Radford","year":"2021"},{"key":"ref11","first-page":"1","article-title":"SayPlan: Grounding large language models using 3D scene graphs for scalable robot task planning","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Rana"},{"key":"ref12","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst. (NIPS)","volume":"33","author":"Chaplot"},{"key":"ref13","first-page":"1","article-title":"Demonstrating large language models on robots","volume-title":"Proc. Robotics: Sci. Syst. (RSS)","author":"Zeng"},{"key":"ref14","first-page":"1","article-title":"ViNT: A foundation model for visual navigation","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Shah"},{"key":"ref15","first-page":"3554","article-title":"L3MVN: Leveraging large language models for visual target navigation","volume-title":"Proc. IEEE\/RSJ Int. Conf. Intell. Robots Syst. (IROS)","author":"Yu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63223-5_28"},{"key":"ref17","first-page":"146","article-title":"A frontier-based approach for autonomous exploration","volume-title":"Proc. Int. Symp. Comput. Intell. Robot. Automat. (CIRA)","author":"Yamauchi"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068923"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3363531"},{"key":"ref20","first-page":"3889","article-title":"Frontier-based exploration planning for amphibious robot with Gaussian process occupancy map","volume-title":"Proc. 42nd Chin. Control Conf. (CCC)","author":"Li"},{"key":"ref21","first-page":"11182","article-title":"Real-time robot path planning using rapid visible tree","volume-title":"Proc. IEEE Int. Conf. Robot. Autom. (ICRA)","author":"Xing"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3422052"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3203762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3034800"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3236573"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233554"},{"key":"ref28","article-title":"Navi2Gaze: Leveraging foundation models for navigation and target gazing","volume-title":"arXiv:2407.09053","author":"Zhu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/93"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_15"},{"key":"ref32","article-title":"VoroNav: Voronoi-based zero-shot object navigation with large language model","volume-title":"arXiv:2401.02695","author":"Wu","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.60"},{"key":"ref34","article-title":"BEVBert: Multimodal map pre-training for language-guided navigation","volume-title":"arXiv:2212.04385","author":"An","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.529"},{"issue":"5","key":"ref36","first-page":"4269","article-title":"Augmented commonsense knowledge for remote object grounding","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"38","author":"Mohammadi"},{"key":"ref37","article-title":"OVExp: Open vocabulary exploration for object-oriented navigation","volume-title":"arXiv:2407.09016","author":"Wei","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3407759"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01444"},{"key":"ref41","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611736"},{"key":"ref44","article-title":"RoboPoint: A vision-language model for spatial affordance prediction for robotics","volume-title":"arXiv:2406.10721","author":"Yuan","year":"2024"},{"key":"ref45","article-title":"A3 VLM: Actionable articulation-aware vision language model","volume-title":"arXiv:2406.07549","author":"Huang","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161317"},{"key":"ref47","first-page":"1","article-title":"Bootstrap your own skills: Learning to solve new tasks with large language model guidance","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Zhang"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref49","article-title":"NavCoT: Boosting LLM-based vision-and-language navigation via learning disentangled reasoning","volume-title":"arXiv:2403.07376","author":"Lin","year":"2024"},{"key":"ref50","article-title":"Navigation with large language models: Semantic guesswork as a heuristic for planning","volume-title":"arXiv:2310.10103","author":"Shah","year":"2023"},{"key":"ref51","article-title":"Co-NavGPT: Multi-robot cooperative visual semantic navigation using large language models","volume-title":"arXiv:2310.07937","author":"Yu","year":"2023"},{"key":"ref52","article-title":"ESC: Exploration with soft commonsense constraints for zero-shot object navigation","volume-title":"arXiv:2301.13166","author":"Zhou","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01538"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref55","article-title":"Embodied task planning with large language models","volume-title":"arXiv:2307.01848","author":"Wu","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3346800"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref58","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"35","author":"Lee"},{"key":"ref59","first-page":"1","article-title":"Robots that ask for help: Uncertainty alignment for large language model planners","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Ren"},{"key":"ref60","first-page":"584","article-title":"The unscented particle filter","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Merwe"},{"key":"ref61","article-title":"Attention is all you need","volume-title":"arXiv:1706.03762","author":"Vaswani","year":"2017"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.93.4.1591"},{"key":"ref63","article-title":"Leveraging large (visual) language models for robot 3D scene understanding","volume-title":"arXiv:2209.05629","author":"Chen","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref65","article-title":"RedNet: Residual encoder\u2013decoder network for indoor RGB-D semantic segmentation","volume-title":"arXiv:1806.01054","author":"Jiang","year":"2018"},{"key":"ref66","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv:1810.04805","author":"Devlin","year":"2018"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref68","volume-title":"Language Models Are Unsupervised Multitask Learners","author":"Radford","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"ref70","article-title":"The llama 3 herd of models","volume-title":"arXiv:2407.21783","author":"Grattafiori","year":"2024"},{"key":"ref71","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","volume-title":"arXiv:2403.05530","author":"Team","year":"2024"},{"key":"ref72","volume-title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","year":"2025"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01411"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11071401\/10845850.pdf?arnumber=10845850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T04:30:51Z","timestamp":1751689851000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10845850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":73,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3531410","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}