arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.06546math.OC
收藏

具有神经网络控制器的分段仿射系统的李雅普诺夫函数学习

Learning Lyapunov Functions for Piecewise Affine Systems with Neural Network Controllers

Shaoru Chen, Mahyar Fazlyab, Manfred Morari, George J. Pappas, Victor M. Preciado

摘要:

提出了一种基于学习的分段仿射动力系统反馈控制器的李雅普诺夫稳定性分析方法。所提出的方法包括一个学习者和一个验证者之间的迭代交互,在每次迭代中,学习者使用的闭环系统的样本的集合,提出一个李雅普诺夫函数候选作为凸规划的解决方案。然后,学习者查询验证器,验证器求解混合整数规划以验证所提出的李雅普诺夫函数候选者或用反例拒绝它,即,稳定性条件失效的状态。然后,将该反例添加到学习器的样本集,以细化李雅普诺夫函数候选集。基于解析中心割平面法设计了学习器和验证器,验证器作为割平面预言机对候选李雅普诺夫函数集进行精化。我们表明,当一组李雅普诺夫函数是全维的参数空间,整个过程中发现一个李雅普诺夫函数在有限数量的迭代。我们证明了该方法在寻找二次和分段二次李雅普诺夫函数的效用。

英文摘要:

We propose a learning-based method for Lyapunov stability analysis of piecewise affine dynamical systems in feedback with piecewise affine neural network controllers. The proposed method consists of an iterative interaction between a learner and a verifier, where in each iteration, the learner uses a collection of samples of the closed-loop system to propose a Lyapunov function candidate as the solution to a convex program. The learner then queries the verifier, which solves a mixed-integer program to either validate the proposed Lyapunov function candidate or reject it with a counterexample, i.e., a state where the stability condition fails. This counterexample is then added to the sample set of the learner to refine the set of Lyapunov function candidates. We design the learner and the verifier based on the analytic center cutting-plane method, in which the verifier acts as the cutting-plane oracle to refine the set of Lyapunov function candidates. We show that when the set of Lyapunov functions is full-dimensional in the parameter space, the overall procedure finds a Lyapunov function in a finite number of iterations. We demonstrate the utility of the proposed method in searching for quadratic and piecewise quadratic Lyapunov functions.

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。

↑