.png){kind=icon}
返回
Stability Verification of Neural Network Controllers Using Mixed-Integer Programming
.png){kind=icon}
OA
AI
DOI：10.1109/TAC.2023.3283213.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this article, we propose a framework for the stability verification of mixed-integer linear programming (MILP) representable control policies. This framework compares a fixed candidate policy, which admits an efficient parameterization and can be evaluated at a low computational cost, against a fixed baseline policy, which is known to be stable but expensive to evaluate. We provide sufficient conditions for the closed-loop stability of the candidate policy in terms of the worst-case approximation error with respect to the baseline policy, and we show that these conditions can be checked by solving a mixed-integer quadratic program. In addition, we demonstrate that an outer and inner approximation of the stability region of the candidate policy can be computed by solving an MILP. The proposed framework is sufficiently general to accommodate a broad range of candidate policies including ReLU neural networks (NNs), optimal solution maps of parametric quadratic programs, and model predictive control (MPC) policies. We also present an open-source toolbox in Python based on the proposed framework, which allows for the easy verification of custom NN architectures and MPC formulations. We showcase the flexibility and reliability of our framework in the context of a dc-dc power converter case study and investigate its computational complexity.
Keyword:
Mixed-integer programming
model predictive control
neural networks
stability guarantees
verification
期刊
IF:
7
论文数:
1.3W
被引数:
6.7W
机构
引用论文
Cleavage and release of a soluble form of the receptor tyrosine kinase ARK in vitro and in vivo.png)
IF0
PREAI
分享收藏Near-Optimal Rapid MPC Using Neural Networks: A Primal-Dual Policy Learning Framework使用神经网络的近似最优快速MPC: 原始对偶策略学习框架
OAAI
OAAI分享收藏Efficient Representation and Approximation of Model Predictive Control Laws via Deep Learning基于深度学习的模型预测控制律的有效表示和逼近OAAI
OAAI分享收藏Robust model predictive control of constrained linear systems with bounded disturbances有界扰动约束线性系统的鲁棒模型预测控制AUTOMATICAOAAI
AUTOMATICAIF5.9
OAAI分享收藏
查看更多内容