{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T20:03:21Z","timestamp":1785182601233,"version":"3.55.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2023YFB4706600"],"award-info":[{"award-number":["2023YFB4706600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Zhejiang Provincial Science and Technology Plan Project","award":["2024C01170"],"award-info":[{"award-number":["2024C01170"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62322314"],"award-info":[{"award-number":["62322314"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/lra.2026.3713727","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T21:50:20Z","timestamp":1784238620000},"page":"10513-10520","source":"Crossref","is-referenced-by-count":0,"title":["NavDreamer: Video Models as Zero-Shot 3D Navigators"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1540-4410","authenticated-orcid":false,"given":"Xijie","family":"Huang","sequence":"first","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4200-4304","authenticated-orcid":false,"given":"Weiqi","family":"Gai","sequence":"additional","affiliation":[{"name":"Differential Robotics","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyue","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7332-5802","authenticated-orcid":false,"given":"Congyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9184-3999","authenticated-orcid":false,"given":"Qiaoyu","family":"Zheng","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Differential Robotics","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5484-205X","authenticated-orcid":false,"given":"Xin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Differential Robotics","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8894-5118","authenticated-orcid":false,"given":"Yuze","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6513-374X","authenticated-orcid":false,"given":"Fei","family":"Gao","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. Mach. Learn. Res.","volume":"270","author":"Kim","year":"2024"},{"issue":"2","key":"ref2","first-page":"17","article-title":"$\\pi _{0.5}$: A vision-language-action model with open-world generalization","volume-title":"Proc. 9th Annu. Conf. Robot Learn.","volume":"1","author":"Black","year":"2025"},{"key":"ref3","article-title":"VLA-AN: An efficient and onboard vision-language-action framework for aerial navigation in complex environments","author":"Wu","year":"2025"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref5","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref6","article-title":"UAV-Flow colosseo: A real-world benchmark for flying-on-a-word UAV imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"38","author":"Wang","year":"2025"},{"key":"ref7","article-title":"Gen-0: Embodied foundation models that scale with physical interaction","year":"2025","journal-title":"Generalist AI Blog"},{"key":"ref8","article-title":"Cosmos policy: Fine-tuning video models for visuomotor control and planning","author":"Kim","year":"2026"},{"key":"ref9","first-page":"56465","article-title":"Position: Video as the new language for real-world decision making","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2024"},{"key":"ref10","article-title":"WAN: Open and advanced large-scale video generative models","author":"Wan","year":"2025"},{"key":"ref11","article-title":"HunyuanVideo 1.5 technical report","author":"Wu","year":"2025"},{"key":"ref12","article-title":"World simulation with video foundation models for physical AI","author":"Ali","year":"2025"},{"key":"ref13","article-title":"Video models are zero-shot learners and reasoners","author":"Wiedemer","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0403"},{"key":"ref15","article-title":"DreamZero: World action models are zero-shot policies","author":"GEAR","year":"2026"},{"key":"ref16","article-title":"mimic-video: Video-action models for generalizable robot control beyond VLAs","author":"Pai","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.ads5033"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01472"},{"key":"ref20","first-page":"82155","article-title":"Improving video generation with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"38","author":"Liu","year":"2025"},{"key":"ref21","article-title":"$\\pi ^{3}$: Permutation-equivariant visual geometry learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2026"},{"key":"ref22","first-page":"35928","article-title":"MoGe-2: Accurate monocular geometry with metric scale and sharp details","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3047728"},{"key":"ref24","first-page":"5170","article-title":"DreamGen: Unlocking generalization in robot learning through video world models","volume-title":"Proc. Conf. Robot Learn.","volume":"295","author":"Jang","year":"2025"},{"key":"ref25","article-title":"WorldVLA: Towards autoregressive action world model","author":"Cen","year":"2025"},{"key":"ref26","first-page":"95597","article-title":"VideoVLA: Video generators can be generalizable robot manipulators","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"38","author":"Shen","year":"2025"},{"key":"ref27","article-title":"Large video planner enables generalizable robot control","author":"Chen","year":"2025"},{"key":"ref28","article-title":"Sparse video generation propels real-world beyond-the-view vision-language navigation","author":"Zhang","year":"2026"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3606383"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aeb0180"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01411"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00559"},{"key":"ref34","first-page":"4697","article-title":"See, point, fly: A learning-free VLM framework for universal unmanned aerial navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Hu","year":"2025"},{"key":"ref35","article-title":"Aerial world model for long-horizon visual generation and navigation in 3D space","author":"Zhang","year":"2025"},{"key":"ref36","article-title":"Qwen3-VL technical report","author":"Bai","year":"2025"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3511409"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1163\/1574-9347_dnp_e506570"},{"key":"ref39","first-page":"621","article-title":"AirSim: High-fidelity visual and physical simulation for autonomous vehicles","volume-title":"Proc. Field Service Robot., Results 11th Int. Conf.","author":"Shah","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3141876"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00524"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1505"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11606541\/11611635.pdf?arnumber=11611635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T19:10:10Z","timestamp":1785179410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11611635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":42,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3713727","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}