待翻譯：NavWM: A Unified Navigation World Model for Foresight-Driven Planning
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2606.24101v1 Announce Type: new Abstract: Conventional visual navigation policies often struggle with myopic decision-making and mode collapse in complex environments. While world models offer a promising alternative, existing paradigms typically isolate perception, generation, and control, failing to capture their shared spatio-temporal dynamics. In this paper, we propose NavWM, a unified navigation world model that seamlessly integrates latent world reasoning, multimodal action prediction, and controllable visual generation. At its core, NavWM leverages latent world tokens to distill geometric and semantic priors, endowing the agent with robust structural understanding. To overcome the limitations of deterministic policies, we introduce an anchor-based multimodal trajectory forecasting framework that generates a diverse action space. This inherent diversity explicitly empowers the generative world model to act as a robust closed-loop planner, utilizing visual foresight to evaluate and select the optimal path. Extensive experiments across diverse robotics datasets demonstrate that NavWM significantly advances the state-of-the-art, delivering remarkable improvements in both high-fidelity future state generation and zero-shot navigation success.
AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。
[2606.24101] NavWM: A Unified Navigation World Model for Foresight-Driven Planning [Submitted on 23 Jun 2026] Title:NavWM: A Unified Navigation World Model for Foresight-Driven Planning View a PDF of the paper titled NavWM: A Unified Navigation World Model for Foresight-Driven Planning, by Yanghong Mei and 5 other authors View PDF HTML (experimental) Abstract:Conventional visual navigation policies often struggle with myopic decision-making and mode collapse in complex environments. While world models offer a promising alternative, existing paradigms typically isolate perception, generation, and control, failing to capture their shared spatio-temporal dynamics. In this paper, we propose NavWM, a unified navigation world model that seamlessly integrates latent world reasoning, multimodal action prediction, and controllable visual generation. At its core, NavWM leverages latent world tokens to distill geometric and semantic priors, endowing the agent with robust structural understanding. To overcome the limitations of deterministic policies, we introduce an anchor-based multimodal trajectory forecasting framework that generates a diverse action space. This inherent diversity explicitly empowers the generative world model to act as a robust closed-loop planner, utilizing visual foresight to evaluate and select the optimal path. Extensive experiments across diverse robotics datasets demonstrate that NavWM significantly advances the state-of-the-art, delivering remarkable improvements in both high-fidelity future state generation and zero-shot navigation success. Comments: 13 pages, 5 figures, accepted to ECCV 2026 Subjects: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2606.24101 [cs.RO] (or arXiv:2606.24101v1 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2606.24101 arXiv-issued DOI via DataCite (pending registration) Submission history From: Yanghong Mei [view email] [v1] Tue, 23 Jun 2026 03:30:20 UTC (1,181 KB) Full-text links: Access Paper: View a PDF of the paper titled NavWM: A Unified Navigation World Model for Foresight-Driven Planning, by Yanghong Mei and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.RO new | recent | 2026-06 Change to browse by: cs cs.CV References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)