.png){kind=icon}
返回
Reliably-Stabilizing Piecewise-Affine Neural Network Controllers
.png){kind=icon}
OA
AI
DOI：10.1109/TAC.2022.3216978.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
A common problem affecting neural network (NN) approximations of model predictive control (MPC) policies is the lack of analytical tools to assess the stability of the closed-loop system under the action of the NN-based controller. We present a general procedure to quantify the performance of such a controller, or to design minimum complexity NNs with rectified linear units (ReLUs) that preserve the desirable properties of a given MPC scheme. By quantifying the approximation error between NN-based and MPC-based state-to-input mappings, we first establish suitable conditions involving two key quantities, the worst-case error and the Lipschitz constant, guaranteeing the stability of the closed-loop system. We then develop an offline, mixed-integer optimization-based method to compute those quantities exactly. Together these techniques provide conditions sufficient to certify the stability and performance of an ReLU-based approximation of an MPC control law.
Keyword:
Mixed-integer (MI) linear optimization
model predictive control (MPC)
neural networks (NNs)
期刊
IF:
7
论文数:
1.3W
被引数:
6.7W
机构
引用论文
.png){kind=icon}
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Preliminary Study on the Antigen-Removal from Extracellular Matrix via Different Decellularization
PREAI
分享收藏
查看更多内容