Reliably-Stabilizing Piecewise-Affine Neural Network Controllers
From MaRDI portal
Abstract: 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 a ReLU-based approximation of an MPC control law.
Cited in
(6)- Stabilization control of generalized type neural networks with piecewise constant argument
- Robust stabilization of polytopic systems via fast and reliable neural network-based approximations
- Ensemble neural network-based approximate model predictive control with strict guarantees
- A neural network-based approach to hybrid systems identification for control
- Robust stability of neural network control systems with interval matrix uncertainties
- Control Lyapunov function design via configuration-constrained polyhedral computing
This page was built for publication: Reliably-Stabilizing Piecewise-Affine Neural Network Controllers
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6047021)
