arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.04243eess.SYcs.SY
收藏

分段仿射动力系统不变集估计:基于分段仿射障碍函数的方法

Invariant Set Estimation for Piecewise Affine Dynamical Systems Using Piecewise Affine Barrier Function

Pouya Samanipour, Hasan A. Poonawala

AI总结:

本文提出一种基于分段仿射障碍函数和线性优化的方法,用于估计由ReLU网络或PWA函数辨识的闭环动力系统的不变集,并通过域细化策略提升灵活性,实验验证了其有效性和高效性。

摘要:

本文提出了一种算法,用于近似闭环受控动力系统的不变集,该系统通过ReLU神经网络或分段仿射(PWA)函数进行辨识,特别针对安全关键应用中常用的ReLU网络提供安全保证这一挑战。PWA动力系统的不变集通过ReLU网络或其等效PWA函数进行估计。该方法将障碍函数构造为PWA函数,并利用顶点将搜索过程转化为线性优化问题。我们引入了一种域细化策略,以在优化未能找到有效障碍函数时增加灵活性。此外,优化的目标是在当前划分基础上最大化不变集。我们的实验结果表明了该方法的有效性和高效性,展示了其在确保PWA动力系统安全方面的潜力。

英文摘要:

This paper introduces an algorithm for approximating the invariant set of closed-loop controlled dynamical systems identified using ReLU neural networks or piecewise affine PWA functions, particularly addressing the challenge of providing safety guarantees for ReLU networks commonly used in safety-critical applications. The invariant set of PWA dynamical system is estimated using ReLU networks or its equivalent PWA function. This method entails formulating the barrier function as a PWA function and converting the search process into a linear optimization problem using vertices. We incorporate a domain refinement strategy to increase flexibility in case the optimization does not find a valid barrier function. Moreover, the objective of optimization is to maximize the invariant set based on the current partition. Our experimental results demonstrate the effectiveness and efficiency of our approach, demonstrating its potential for ensuring the safety of PWA dynamical systems.

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。

↑