Learning Koopman-based Stability Certificates for Unknown Nonlinear Systems

📅 2024-12-03
🏛️ arXiv.org
📈 Citations: 0
Influential: 0
📄 PDF

career value

182K/year
🤖 AI Summary
Existing Koopman-based methods struggle to simultaneously learn continuous-time dynamics and guarantee stability for unknown nonlinear systems under low-frequency sampling. Method: This paper proposes a novel framework that jointly learns the Koopman generator and a Lyapunov function, tightly integrating high-accuracy Koopman generator estimation with physics-informed neural networks (PINNs) and embedding Lyapunov stability constraints. Attractor domain verification is performed formally using an SMT solver. Contribution/Results: The approach significantly expands the verifiable region of the estimated region of attraction while reducing conservatism. It provides mathematically certified stability guarantees for dynamical systems under sparse observations—overcoming a key limitation of current Koopman methods, which lack rigorous stability certification under low-sampling-rate conditions.

Technology Category

Application Category

📝 Abstract
Koopman operator theory has gained significant attention in recent years for identifying discrete-time nonlinear systems by embedding them into an infinite-dimensional linear vector space. However, providing stability guarantees while learning the continuous-time dynamics, especially under conditions of relatively low observation frequency, remains a challenge within the existing Koopman-based learning frameworks. To address this challenge, we propose an algorithmic framework to simultaneously learn the vector field and Lyapunov functions for unknown nonlinear systems, using a limited amount of data sampled across the state space and along the trajectories at a relatively low sampling frequency. The proposed framework builds upon recently developed high-accuracy Koopman generator learning for capturing transient system transitions and physics-informed neural networks for training Lyapunov functions. We show that the learned Lyapunov functions can be formally verified using a satisfiability modulo theories (SMT) solver and provide less conservative estimates of the region of attraction compared to existing methods.
Problem

Research questions and friction points this paper is trying to address.

Learning stability certificates for unknown nonlinear systems
Addressing low observation frequency in Koopman-based learning
Formally verifying Lyapunov functions with SMT solvers
Innovation

Methods, ideas, or system contributions that make the work stand out.

Learning Koopman generator for transient transitions
Physics-informed neural networks for Lyapunov functions
SMT solver for formal verification of stability
R
Rui Zhou
Department of Applied Mathematics, University of Waterloo, Waterloo, Ontario N2L 3G1, Canada.
Y
Yiming Meng
Coordinated Science Laboratory, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA.
Z
Zhexuan Zeng
Department of Automatic Control, Huazhong University of Science and Technology, Wuhan, China.
J
Jun Liu
Department of Applied Mathematics, University of Waterloo, Waterloo, Ontario N2L 3G1, Canada.