Robust Stability of Neural Network-controlled Nonlinear Systems with Parametric Variability
This addresses safety and robustness concerns for dynamical systems with machine-learned components, but it appears incremental as it builds on existing Lyapunov methods.
The paper tackled the problem of ensuring stability and safety in neural network-controlled nonlinear systems with parametric variations by proposing a Lyapunov-based stability certificate and a stability-guaranteed training algorithm, validated through an illustrative example.
Stability certification and identifying a safe and stabilizing initial set are two important concerns in ensuring operational safety, stability, and robustness of dynamical systems. With the advent of machine-learning tools, these issues need to be addressed for the systems with machine-learned components in the feedback loop. To develop a general theory for stability and stabilizability of a neural network (NN)-controlled nonlinear system subject to bounded parametric variation, a Lyapunov-based stability certificate is proposed and is further used to devise a maximal Lipschitz bound for the NN controller, and also a corresponding maximal region-of-attraction (RoA) inside a given safe operating domain. To compute such a robustly stabilizing NN controller that also maximizes the system's long-run utility, a stability-guaranteed training (SGT) algorithm is proposed. The effectiveness of the proposed framework is validated through an illustrative example.