Reliably-stabilizing piecewise-affine neural network controllers

Filippo Fabiani and Paul J. Goulart

November 2021.
BibTeX  URL 

  author = {Filippo Fabiani and Paul J. Goulart},
  title = {Reliably-stabilizing piecewise-affine neural network controllers},
  year = {2021},
  url = {}

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.