Abstract
We present a new method for learning control law that stabilizes an unknown nonlinear dynamical system at an equilibrium point. We formulate a system identification task in a self-supervised learning setting that jointly learns a controller and corresponding stable closed-loop dynamics hypothesis. The open-loop input-output behavior of the underlying dynamical system is used as the supervising signal to train the neural network-based system model and controller. The method relies on the Lyapunov stability theory to generate a stable closed-loop dynamics hypothesis and corresponding control law. We demonstrate our method on various nonlinear control problems such as n-Link pendulum balancing, pendulum on cart balancing, and wheeled vehicle path following.
Abstract (translated)
URL
https://arxiv.org/abs/2009.11782
