Learning Stabilizable Deep Dynamics Models
This work addresses stability guarantees in neural network-based dynamics modeling for control systems, which is an incremental improvement over existing methods for autonomous systems.
The authors tackled the problem of learning dynamics models for input-affine control systems while ensuring stability, resulting in a method that also provides a stabilizing controller and control Lyapunov function, with usefulness demonstrated through numerical examples.
When neural networks are used to model dynamics, properties such as stability of the dynamics are generally not guaranteed. In contrast, there is a recent method for learning the dynamics of autonomous systems that guarantees global exponential stability using neural networks. In this paper, we propose a new method for learning the dynamics of input-affine control systems. An important feature is that a stabilizing controller and control Lyapunov function of the learned model are obtained as well. Moreover, the proposed method can also be applied to solving Hamilton-Jacobi inequalities. The usefulness of the proposed method is examined through numerical examples.