NavForesee：面向分层规划与双视野导航预测的统一视觉语言世界模型
NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction
将视觉语言模型同时作为高层规划器和生成式世界模型，通过预测短期环境动态与长期导航里程碑形成感知-规划-预测-动作的内部反馈闭环，为具身导航中的长程规划提供可复用的双视野预测框架。
原文依据 a novel Vision-Language Model (VLM) that unifies high-level language planning and predictive world model imagination within a single, unified framework
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在人工智能领域，由复杂自然语言指令引导的长时程具身导航仍然是一项艰巨挑战。现有智能体往往难以对未见环境进行鲁棒的长时程规划，导致较高的失败率。为解决这些局限，我们提出 NavForesee，一种新颖的视觉语言模型（VLM），在单一统一框架内融合高层语言规划与预测性世界模型想象。我们的方法使单个 VLM 能够同时执行规划与预测性预见。以完整指令和历史观测为条件，模型通过分解任务、跟踪进度并制定后续子目标来理解导航指令。同时，它作为生成式世界模型，通过预测短期环境动态和长期导航里程碑提供关键预见。VLM 的结构化规划指导其目标预测，而想象出的未来则为导航动作提供丰富上下文，形成感知-规划/预测-动作的强大内部反馈闭环。我们在 R2R-CE 和 RxR-CE 基准上进行大量实验，证明 NavForesee 在复杂场景中取得极具竞争力的性能。我们的工作凸显了融合显式语言规划与隐式时空预测的巨大潜力，为更智能、更强大的具身智能体铺平道路。
英文原文摘要 1528 字符
Embodied navigation for long-horizon tasks, guided by complex natural language instructions, remains a formidable challenge in artificial intelligence. Existing agents often struggle with robust long-term planning about unseen environments, leading to high failure rates. To address these limitations, we introduce NavForesee, a novel Vision-Language Model (VLM) that unifies high-level language planning and predictive world model imagination within a single, unified framework.Our approach empowers a single VLM to concurrently perform planning and predictive foresight. Conditioned on the full instruction and historical observations, the model is trained to understand the navigation instructions by decomposing the task, tracking its progress, and formulating the subsequent sub-goal. Simultaneously, it functions as a generative world model, providing crucial foresight by predicting short-term environmental dynamics and long-term navigation milestones. The VLM's structured plan guides its targeted prediction, while the imagined future provides rich context to inform the navigation actions, creating a powerful internal feedback loop of perception-planning/prediction-action. We demonstrate through extensive experiments on the R2R-CE and RxR-CE benchmark that NavForesee achieves highly competitive performance in complex scenarios. Our work highlights the immense potential of fusing explicit language planning with implicit spatiotemporal prediction, paving the way for more intelligent and capable embodied agents.