{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T19:56:56Z","timestamp":1790884616198,"version":"4.1.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"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 Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1109\/lra.2026.3729462","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T19:12:56Z","timestamp":1788203576000},"page":"13071-13078","source":"Crossref","is-referenced-by-count":0,"title":["PROSPECT: Unified Streaming Vision-Language Navigation via Semantic\u2013Spatial Fusion and Latent Predictive Representation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1727-8308","authenticated-orcid":false,"given":"Zehua","family":"Fan","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8173-0141","authenticated-orcid":false,"given":"Wenqi","family":"Lyu","sequence":"additional","affiliation":[{"name":"University of Adelaide","place":["Adelaide, SA, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxuan","family":"Song","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou)","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3181-4349","authenticated-orcid":false,"given":"Linge","family":"Zhao","sequence":"additional","affiliation":[{"name":"Wuhan University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5821-5893","authenticated-orcid":false,"given":"Yifei","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing Jiao Tong University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5217-6704","authenticated-orcid":false,"given":"Xi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University AIR Wuxi Innovation Center","place":["Wuxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"He","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou)","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2663-6221","authenticated-orcid":false,"given":"Lida","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0570-2447","authenticated-orcid":false,"given":"Haiyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Lenovo","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7727-0657","authenticated-orcid":false,"given":"Bingchuan","family":"Sun","sequence":"additional","affiliation":[{"name":"Lenovo","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8299-4980","authenticated-orcid":false,"given":"Guangjun","family":"Bao","sequence":"additional","affiliation":[{"name":"Lenovo","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3297-3243","authenticated-orcid":false,"given":"Xuanyao","family":"Mao","sequence":"additional","affiliation":[{"name":"Lenovo","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8999-8510","authenticated-orcid":false,"given":"Liang","family":"Xu","sequence":"additional","affiliation":[{"name":"Lenovo","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5341-6040","authenticated-orcid":false,"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5358-719X","authenticated-orcid":false,"given":"Feng","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.079"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57385.2026.11696190"},{"key":"ref5","article-title":"V-JEPA 2: Self-supervised video models enable understanding, prediction and planning","author":"Assran","year":"2025"},{"key":"ref6","article-title":"WAN: Open and advanced large-scale video generative models","author":"Wan","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01472"},{"key":"ref8","article-title":"RynnVLA-002: A unified vision-language-action and world model","author":"Cen","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/085713-0818"},{"key":"ref10","article-title":"Motus: A unified latent action world model","author":"Bi","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00525"},{"key":"ref12","article-title":"NavForesee: A unified vision-language world model for hierarchical planning and dual-horizon navigation prediction","author":"Liu","year":"2025"},{"key":"ref13","article-title":"SigLIP 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"ref15","article-title":"Streaming 4D visual geometry transformer","author":"Zhuo","year":"2025"},{"key":"ref16","article-title":"InfiniteVGGT: Visual geometry grounded transformer for endless streams","author":"Yuan","year":"2026"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/085713-0457"},{"key":"ref19","first-page":"31054","article-title":"VLM-3R: Vision-language models augmented with instruction-aligned 3D reconstruction","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Fan","year":"2026"},{"key":"ref20","article-title":"JanusVLN: Decoupling semantics and spatiality with dual implicit memory for vision-language navigation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zeng","year":"2026"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01488"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_34"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"ref27","first-page":"2982","article-title":"Sim-to-real transfer via 3D feature fields for vision-and-language navigation","volume-title":"Proc. Conf. Robot Learn., Proc. Mach. Learn. Res.","volume":"270","author":"Wang","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.073"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3542323"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02582"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i5.37347"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"ref33","article-title":"Qwen 2.5: A comprehensive review of the leading resource-efficient LLM with potentioal to surpass all competitors","author":"Ahmed","year":"2025","journal-title":"TechRxiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref37","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statistics. JMLR Workshop Conf. Proc.","author":"Ross","year":"2011"},{"key":"ref38","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","author":"Ramakrishnan","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref40","article-title":"Video instruction tuning with synthetic data, 2024","author":"Zhang","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.328"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2764"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11690866\/11673313.pdf?arnumber=11673313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T19:15:00Z","timestamp":1790882100000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11673313\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":45,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3729462","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,11]]}}}