面向航空图像目标导航的不确定性感知世界模型

摘要

空中图像目标导航要求无人驾驶飞行器（UAV）到达由目标图像指定的目标位置。现有的基于世界模型的方法利用预测的未来状态对候选轨迹进行排序，但通常仅依赖一个或少数几个点预测，这对于具有显著未来状态不确定性的大规模户外环境而言是不足的。为解决此局限，我们提出了不确定性感知导航世界模型（UA-NWM），一种用于空中图像目标导航的高效潜在世界模型，它将轨迹评分形式化为条件分布外检测。UA-NWM 用不确定性子空间表示可能的未来状态，并将预测与目标间的差异分解为不确定性可解释成分与不可解释成分。仅利用不可解释的残差进行评分，从而无需多个未来样本即可实现稳健选择。大量实验表明，UA-NWM 在保持低推理延迟的同时，持续优于现有导航世界模型。真实世界的 UAV 实验进一步验证了其实际适用性。项目页面：https://duryi.github.io/UA-NWM-Project-Page

English

Aerial image-goal navigation requires an unmanned aerial vehicle (UAV) to reach a target location specified by a goal image. Existing world-model-based methods rank candidate trajectories using predicted futures, but typically rely on only one or a few point predictions, which is inadequate for large-scale outdoor environments with substantial future-state uncertainty. To address this limitation, we propose the Uncertainty-Aware Navigation World Model (UA-NWM), an efficient latent world model for aerial image-goal navigation, which formulates trajectory scoring as conditional out-of-distribution detection. UA-NWM represents plausible futures with an uncertainty subspace and decomposes the prediction--goal discrepancy into uncertainty-explainable and unexplainable components. Only the unexplainable residual is used for scoring, enabling robust selection without multiple future samples. Extensive experiments demonstrate that UA-NWM consistently outperforms existing navigation world models while maintaining low inference latency. Real-world UAV experiments further validate its practical applicability. Project page: https://duryi.github.io/UA-NWM-Project-Page