中文标题#
FlowNav：结合流匹配和深度先验的高效导航
英文标题#
FlowNav: Combining Flow Matching and Depth Priors for Efficient Navigation
中文摘要#
在未见过的环境中实现有效的机器人导航是一项具有挑战性的任务，这需要在高频下进行精确的控制动作。 最近的进展将其视为一个图像目标条件控制问题，其中机器人使用正面 RGB 图像生成导航动作。 该领域的最新方法使用扩散策略来生成这些控制动作。 尽管它们的结果很有前景，但这些模型计算成本高且感知能力弱。 为了解决这些限制，我们提出了 FlowNav，这是一种新方法，它结合了来自现成基础模型的 CFM 和深度先验来学习机器人导航的动作策略。 FlowNav 在导航和探索方面比最新方法更准确、更快。 我们通过在多个环境中的真实机器人实验验证了我们的贡献，展示了改进的导航可靠性和准确性。 代码和训练好的模型是公开的。
英文摘要#
Effective robot navigation in unseen environments is a challenging task that requires precise control actions at high frequencies. Recent advances have framed it as an image-goal-conditioned control problem, where the robot generates navigation actions using frontal RGB images. Current state-of-the-art methods in this area use diffusion policies to generate these control actions. Despite their promising results, these models are computationally expensive and suffer from weak perception. To address these limitations, we present FlowNav, a novel approach that uses a combination of CFM and depth priors from off-the-shelf foundation models to learn action policies for robot navigation. FlowNav is significantly more accurate and faster at navigation and exploration than state-of-the-art methods. We validate our contributions using real robot experiments in multiple environments, demonstrating improved navigation reliability and accuracy. Code and trained models are publicly available.
PDF 获取#
抖音扫码查看更多精彩内容