Safety Verification of Neural Feedback Systems Based on Constrained Zonotopes
Safety Verification of Neural Feedback Systems Based on Constrained Zonotopes
复制标题
DOI：
10.1109/cdc51059.2022.9992655
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
Yuhao Zhang;Xiangru Xu
中科院分区：
文献类型：
--
作者：
Yuhao Zhang;Xiangru Xu
最近在许多反馈控制系统中使用了人工神经网络，并引入了有关此类系统安全的新挑战。本文通过使用基于限制的扎根方法的方法来考虑具有给定馈电神经网络的动力学系统的安全验证问题作为反馈控制器。提出了一种基于集合的新方法，以计算具有线性模型的神经反馈系统的精确和过度评估的可触及式集合，并提供了基于线性程序的足够条件，以验证该系统的轨迹是否可以避免不安全区域表示为表示不安全的区域限制的分子型。结果还扩展到具有非线性模型的神经反馈系统。提出方法的计算效率和准确性通过两个数值示例证明，其中还提供了与最新方法的比较。
Artificial neural networks have recently been utilized in many feedback control systems and introduced new challenges regarding the safety of such systems. This paper considers the safe verification problem for a dynamical system with a given feedforward neural network as the feedback controller by using a constrained zonotope-based approach. A novel set-based method is proposed to compute both exact and over-approximated reachable sets for neural feedback systems with linear models, and linear program-based sufficient conditions are presented to verify whether the trajectories of such a system can avoid unsafe regions represented as constrained zonotopes. The results are also extended to neural feedback systems with nonlinear models. The computational efficiency and accuracy of the proposed method are demonstrated by two numerical examples where a comparison with state-of-the-art methods is also provided.