论文标题
具有信心保证的机器人控制器全球动态的数据有效表征
Data-Efficient Characterization of the Global Dynamics of Robot Controllers with Confidence Guarantees
论文作者
论文摘要
本文提出了替代建模和拓扑结合的整合，以显着减少描述机器人控制器（包括封闭盒）的基本全局动态所需的数据量。高斯工艺（GP），在状态空间上用随机短轨迹训练，是基础动力学系统的替代模型。然后，建立并用于描述有向无环图的形式的组合表示形式，称为{\ it Morse Graph}。莫尔斯图能够描述系统的吸引子及其相应的吸引力区域（\ roa）。此外，还提供了整个状态空间的全局动力学估计的点置信度。与替代方案相反，该框架不需要估算Lyapunov功能，从而减轻了GP高预测准确性的需求。该框架适用于只要满足Lipschitz-continuition的数据驱动的控制器，这些控制器不揭示分析模型。将该方法与已建立的分析和最新的机器学习替代方法进行了比较，以估算\ roA，在不牺牲准确性的情况下优于数据效率。链接到代码：https：//go.rutgers.edu/49hy35en
This paper proposes an integration of surrogate modeling and topology to significantly reduce the amount of data required to describe the underlying global dynamics of robot controllers, including closed-box ones. A Gaussian Process (GP), trained with randomized short trajectories over the state-space, acts as a surrogate model for the underlying dynamical system. Then, a combinatorial representation is built and used to describe the dynamics in the form of a directed acyclic graph, known as {\it Morse graph}. The Morse graph is able to describe the system's attractors and their corresponding regions of attraction (\roa). Furthermore, a pointwise confidence level of the global dynamics estimation over the entire state space is provided. In contrast to alternatives, the framework does not require estimation of Lyapunov functions, alleviating the need for high prediction accuracy of the GP. The framework is suitable for data-driven controllers that do not expose an analytical model as long as Lipschitz-continuity is satisfied. The method is compared against established analytical and recent machine learning alternatives for estimating \roa s, outperforming them in data efficiency without sacrificing accuracy. Link to code: https://go.rutgers.edu/49hy35en
