Learning Stabilizable Deep Dynamics Models
Machine Learning
2022-03-21 v1 Systems and Control
Systems and Control
Optimization and Control
Abstract
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.
Keywords
Cite
@article{arxiv.2203.09710,
title = {Learning Stabilizable Deep Dynamics Models},
author = {Kenji Kashima and Ryota Yoshiuchi and Yu Kawano},
journal= {arXiv preprint arXiv:2203.09710},
year = {2022}
}