arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.01292cs.RO
收藏

具有置信度保证的机器人控制器全局动态特性的数据有效表征

Data-Efficient Characterization of the Global Dynamics of Robot Controllers with Confidence Guarantees

IME, Universidade Federal de Goiás(戈亚斯联邦大学数学与统计研究所);ICMC, Universidade de São Paulo(圣保罗大学数学与计算机科学研究所)

Ewerton R. Vieira, Aravind Sivaramakrishnan, Yao Song, Edgar Granados, Marcio Gameiro, Konstantin Mischaikow, Ying Hung, Kostas E. Bekris

摘要:

本文提出了一种集成的代理建模和拓扑结构,以显着减少所需的数据量来描述底层的全局动态的机器人控制器,包括闭盒的。高斯过程(GP),在状态空间上的随机短轨迹训练,作为一个代理模型的基础动力系统。然后,建立一个组合表示,并用于描述的动力学的形式的有向无环图,称为{ \it莫尔斯图}。Morse图能够描述系统的吸引子及其相应的吸引区域(\roa)。此外,在整个状态空间上的全局动态估计的逐点置信水平提供。与替代方案相比,该框架不需要估计李雅普诺夫函数,从而减轻了对GP的高预测精度的需求。该框架适用于数据驱动的控制器,只要满足Lipschitz连续性,就不暴露分析模型。该方法与建立的分析和最近的机器学习替代估计\roa s相比,在不牺牲准确性的情况下,在数据效率方面优于它们。代码链接:https://go.rutgers.edu/49hy35en

英文摘要:

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

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。

↑