发表机构
Technical University of Munich; German Aerospace Center (DLR); University of Leeds（慕尼黑工业大学; 德国航空航天中心; 利兹大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种利用几何先验的非参数异方差模仿学习方法，在数据稀缺下实现快速适应，支持流形输入输出，更新快于3毫秒，并在真实机器人任务中验证。
AI 中文摘要
当从人类示范中学习概率策略时，数据高效的学习和对新场景的快速适应是关键要求。实现直观且可靠适应的一种流行方式是通过非参数方法，通常是基于核的方法。然而，现有解决方案要么未能考虑机器人学中常见的流形几何，从而限制了数据效率，要么在几何感知时提供不可靠的不确定性估计或需要重新训练以适应。我们提出了一种非参数方法，在数据稀缺和异方差不确定性的场景中利用几何先验进行概率建模。我们利用该方法基于时间或机器人状态制定策略，其中不可分离的对角核允许在相同大小的输入和输出中捕获自由度之间的不确定性关系。通过优化公式，快速更新成为可能，对于涉及位置和方向的轨迹，更新所需时间少于3毫秒。我们的方法支持流形值输入和流形值输出，并处理大的方向变化。利用任务参数化，可以轻松适应不同的物体姿态。我们在玩具示例集和真实机器人操作任务上评估了该方法，包括自主执行和共享控制场景。
英文摘要
When learning probabilistic policies from human demonstrations, data-efficient learning and fast adaptations to new scenarios are key requirements. One popular way to achieve intuitive and reliable adaptations is through non-parametric, typically kernel-based, methods. However, existing solutions either fail to account for the geometry of manifolds common in robotics, limiting data efficiency, or, when geometry-aware, provide unreliable uncertainty estimates or require retraining to adapt. We propose a non-parametric approach leveraging geometric priors in scenarios of data scarcity and heteroscedastic uncertainties for probabilistic modeling. We utilize the method to formulate policies based on time or robot state, where non-separable diagonal kernels allow capturing uncertainty relations between degrees of freedom for same-sized in- and outputs. Fast updates, requiring less than 3 ms for a trajectory involving both position and orientation are possible through an optimized formulation. Our approach supports both manifold-valued input and manifold-valued output with large orientation changes. Using task parameterization, adaptation to different object poses is easily possible. We evaluate the approach on a set of toy examples and on real robot manipulation tasks both in autonomous execution and in shared control scenarios.
