{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T20:51:32Z","timestamp":1774558292057,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tce.2025.3638139","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:57:50Z","timestamp":1764269870000},"page":"1171-1182","source":"Crossref","is-referenced-by-count":0,"title":["VLONS: A Vision-and-Language On-Device Navigation System With Multimodal Fusion and Modular Framework"],"prefix":"10.1109","volume":"72","author":[{"given":"Jianyang","family":"Shi","sequence":"first","affiliation":[{"name":"Department of Computer Science, Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1648-0227","authenticated-orcid":false,"given":"Haijun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sybmbiosis-X Technology Inc., Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6363-1446","authenticated-orcid":false,"given":"Tin Lun","family":"Lam","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sybmbiosis-X Technology Inc., Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hu","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BoT-SORT: Robust associations multi-pedestrian tracking","author":"Aharon","year":"2022","journal-title":"arXiv:2206.14651"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref3","article-title":"ReMEmbR: Building and reasoning over long-horizon spatio-temporal memory for robot navigation","author":"Anwar","year":"2024","journal-title":"arXiv:2409.13682"},{"key":"ref4","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.338"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.073"},{"key":"ref7","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chaplot"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967704"},{"key":"ref9","article-title":"Mobility VLA: Multimodal instruction navigation with long-context VLMs and topological graphs","author":"Lewis Chiang","year":"2024","journal-title":"arXiv:2407.07775"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"ref12","article-title":"CLIP-Nav: Using CLIP for zero-shot vision-and-language navigation","author":"Sashank Dorbala","year":"2022","journal-title":"arXiv:2211.16649"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3355061"},{"key":"ref14","first-page":"15220","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Eysenbach"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3257541"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref18","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910388963"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980074"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref22","first-page":"1585","article-title":"Embodied semantic scene graph generation","volume-title":"Proc. Conf. robot Learn.","author":"Li"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref24","first-page":"1084","article-title":"Grounding complex natural language commands for temporal tasks in unseen environments","volume-title":"Proc. Conf. Robot Learn.","author":"Liu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref26","article-title":"CognitiveDrone: A VLA model and evaluation benchmark for real-time cognitive task solving and reasoning in UAVs","author":"Lykov","year":"2025","journal-title":"arXiv:2503.01378"},{"key":"ref27","first-page":"32340","article-title":"ZSON: Zero-shot object-goal navigation using multimodal goal embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Majumdar"},{"key":"ref28","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"arXiv:2203.02155"},{"key":"ref29","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref30","article-title":"TRAVEL: Training-free retrieval and alignment for vision-and-language navigation","author":"Rajabi","year":"2025","journal-title":"arXiv:2502.07306"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00511"},{"key":"ref32","article-title":"SAM2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref33","first-page":"29441","article-title":"Hiera: A hierarchical vision transformer without the bells-and-whistles","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Ryali"},{"key":"ref34","article-title":"Semi-parametric topological memory for navigation","author":"Savinov","year":"2018","journal-title":"arXiv:1803.00653"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR65884.2025.11163198"},{"key":"ref36","first-page":"2683","article-title":"Navigation with large language models: Semantic guesswork as a heuristic for planning","volume-title":"Proc. Conf. Robot Learn.","author":"Shah"},{"key":"ref37","first-page":"492","article-title":"LM-Nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proc. Conf. Robot Learn.","author":"Shah"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561371"},{"key":"ref40","first-page":"51","article-title":"Cognitive maps in rats and men","author":"Stea","year":"2017","journal-title":"Psychol. Rev."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref42","article-title":"TrackVLA: Embodied visual tracking in the wild","author":"Wang","year":"2025","journal-title":"arXiv:2505.23189"},{"key":"ref43","article-title":"Florence-2: Advancing a unified representation for a variety of vision tasks","author":"Xiao","year":"2023","journal-title":"arXiv:2311.06242"},{"key":"ref44","article-title":"Embodied-RAG: General non-parametric embodied memory for retrieval and generation","author":"Xie","year":"2024","journal-title":"arXiv:2409.18313"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3378509"},{"key":"ref46","article-title":"Qwen3 technical report","volume-title":"arXiv:2505.09388","author":"Yang","year":"2025"},{"key":"ref47","article-title":"ByteTrack: Multi-object tracking by associating every detection box","author":"Zhang","year":"2021","journal-title":"arXiv:2110.06864"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981107"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/11456295\/11270935.pdf?arnumber=11270935","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:50:03Z","timestamp":1774554603000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11270935\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":48,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tce.2025.3638139","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"value":"0098-3063","type":"print"},{"value":"1558-4127","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}