Learning Region of Attraction for Nonlinear Systems

Abstract

Estimating the region of attraction (ROA) of general nonlinear autonomous systems remains a challenging problem and requires a case-by-case analysis. Leveraging the universal approximation property of neural networks, in this paper, we propose a counterexample-guided method to estimate the ROA of general nonlinear dynamical systems provided that they can be approximated by piecewise linear neural networks and that the approximation error can be bounded. Specifically, our method searches for robust Lyapunov functions using counterexamples, i.e., the states at which the Lyapunov conditions fail. We generate the counterexamples using Mixed-Integer Quadratic Programming. Our method is guaranteed to find a robust Lyapunov function in the parameterized function class, if exists, after collecting a finite number of counterexamples. We illustrate our method through numerical examples.

Accepted to Conference on Decision and Control 2021

References in corpus (8)

• Provable defenses against adversarial examples via the convex outer adversarial polytope
• Evaluating Robustness of Neural Networks with Mixed Integer Programming
• Neural Lyapunov Control
• Formal Synthesis of Lyapunov Neural Networks
• Nonlinear Systems Identification Using Deep Dynamic Neural Networks
• The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systems
• Automated and Sound Synthesis of Lyapunov Functions with SMT Solvers
• Stability Analysis using Quadratic Constraints for Systems with Neural Network Controllers