SaferPath: 基于学习引导和安全约束控制的分层视觉导航
SaferPath: Hierarchical Visual Navigation with Learned Guidance and Safety-Constrained Control
AI总结：
SaferPath通过结合学习引导和安全约束控制，提升移动机器人在复杂环境中的视觉导航能力，有效减少碰撞并提高成功率。
摘要：
视觉导航是移动机器人的一项核心能力，然而基于端到端学习的方法在面对未见过的拥挤、杂乱或狭窄环境时，往往在泛化能力和安全性方面存在困难。这些局限性在密集的室内环境中尤为明显，其中碰撞的可能性较高，而端到端模型经常失效。为此，我们提出了SaferPath，一种分层视觉导航框架，该框架利用现有端到端模型的学习引导，并通过安全约束优化控制模块进行优化。SaferPath将视觉观测转换为可通行区域地图，并利用模型预测Stein变分进化策略（MP-SVES）优化引导轨迹，高效地在几次迭代中生成安全轨迹。优化后的轨迹由MPC控制器跟踪，确保在复杂环境中实现稳健导航。在包含未见过的障碍物、密集无结构空间和狭窄走廊等场景的大量实验中，证明SaferPath在成功率和碰撞减少方面表现优异，优于ViNT和NoMaD等代表性基线方法，并在具有挑战性的现实环境中实现了安全导航。
英文摘要：
Visual navigation is a core capability for mobile robots, yet end-to-end learning-based methods often struggle with generalization and safety in unseen, cluttered, or narrow environments. These limitations are especially pronounced in dense indoor settings, where collisions are likely and end-to-end models frequently fail. To address this, we propose SaferPath, a hierarchical visual navigation framework that leverages learned guidance from existing end-to-end models and refines it through a safety-constrained optimization-control module. SaferPath transforms visual observations into a traversable-area map and refines guidance trajectories using Model Predictive Stein Variational Evolution Strategy (MP-SVES), efficiently generating safe trajectories in only a few iterations. The refined trajectories are tracked by an MPC controller, ensuring robust navigation in complex environments. Extensive experiments in scenarios with unseen obstacles, dense unstructured spaces, and narrow corridors demonstrate that SaferPath consistently improves success rates and reduces collisions, outperforming representative baselines such as ViNT and NoMaD, and enabling safe navigation in challenging real-world settings.
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。
