Stability Margins of Neural Network Controllers
2024-09-13Code Available0· sign in to hype
Neelay Junnarkar, Murat Arcak, Peter Seiler
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/neelayjunnarkar/nn-stability-marginsOfficialIn paperpytorch★ 2
Abstract
We present a method to train neural network controllers with guaranteed stability margins. The method is applicable to linear time-invariant plants interconnected with uncertainties and nonlinearities that are described by integral quadratic constraints. The type of stability margin we consider is the disk margin. Our training method alternates between a training step to maximize reward and a stability margin-enforcing step. In the stability margin enforcing-step, we solve a semidefinite program to project the controller into the set of controllers for which we can certify the desired disk margin.