DreamFlow：通过条件流匹配在潜在空间中超越观测的局部导航
DreamFlow: Local Navigation Beyond Observation via Conditional Flow Matching in the Latent Space
AI总结：
本文提出DreamFlow框架，通过条件流匹配扩展机器人感知范围，提升局部导航性能，实验显示其在仿真和现实环境中均优于现有方法。
摘要：
局部导航在复杂环境中常因密集障碍和频繁局部极小值而失败。传统局部规划器依赖启发式方法易失效，而基于深度强化学习（DRL）的方法虽具适应性，但受限于有限的 onboard 感知能力。本文提出DreamFlow，一种基于DRL的局部导航框架，通过条件流匹配（CFM）扩展机器人感知范围。CFM预测模块学习局部高度图潜在表示与更广泛空间表示之间的概率映射，条件于导航上下文。这使导航策略能够预测未观测的环境特征并主动避开潜在局部极小值。实验结果表明，DreamFlow在仿真中在潜在预测准确性和导航性能上优于现有方法。所提方法进一步在复杂现实环境中通过四足机器人验证。项目页面可在https://dreamflow-icra.github.io访问。
英文摘要：
Local navigation in cluttered environments often suffers from dense obstacles and frequent local minima. Conventional local planners rely on heuristics and are prone to failure, while deep reinforcement learning(DRL)based approaches provide adaptability but are constrained by limited onboard sensing. These limitations lead to navigation failures because the robot cannot perceive structures outside its field of view. In this paper, we propose DreamFlow, a DRL-based local navigation framework that extends the robot's perceptual horizon through conditional flow matching(CFM). The proposed CFM based prediction module learns probabilistic mapping between local height map latent representation and broader spatial representation conditioned on navigation context. This enables the navigation policy to predict unobserved environmental features and proactively avoid potential local minima. Experimental results demonstrate that DreamFlow outperforms existing methods in terms of latent prediction accuracy and navigation performance in simulation. The proposed method was further validated in cluttered real world environments with a quadrupedal robot. The project page is available at https://dreamflow-icra.github.io.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
