Online Learning Robust Control of Nonlinear Dynamical Systems

TL;DR

This paper develops an online robust control method for nonlinear dynamical systems under adversarial disturbances, providing guarantees on performance and attenuation levels for both known and unknown systems.

Contribution

It introduces an online controller with performance guarantees for nonlinear systems, addressing both known and unknown cases with disturbance and cost function preview capabilities.

Findings

Achieves bounded deviation in known systems with preview when attenuation exceeds a threshold.

Provides performance bounds for unknown systems incorporating estimation accuracy and prediction horizon.

Characterizes the minimum prediction horizon needed for guaranteed performance.

Abstract

In this work we address the problem of the online robust control of nonlinear dynamical systems perturbed by disturbance. We study the problem of attenuation of the total cost over a duration $T$ in response to the disturbances. We consider the setting where the cost function (at a particular time) is a general continuous function and adversarial, the disturbance is adversarial and bounded at any point of time. Our goal is to design a controller that can learn and adapt to achieve a certain level of attenuation. We analyse two cases (i) when the system is known and (ii) when the system is unknown. We measure the performance of the controller by the deviation of the controller's cost for a sequence of cost functions with respect to an attenuation $\gamma$, $R^p_t$. We propose an online controller and present guarantees for the metric $R^p_t$ when the maximum possible attenuation is given by $\overline{\gamma}$, which is a system constant. We show that when the controller has preview of the cost functions and the disturbances for a short duration of time and the system is known $R^p_T(\gamma) = O(1)$ when $\gamma \geq \gamma_c$, where $\gamma_c = \mathcal{O}(\overline{\gamma})$. We then show that when the system is unknown the proposed controller with a preview of the cost functions and the disturbances for a short horizon achieves $R^p_T(\gamma) = \mathcal{O}(N) + \mathcal{O}(1) + \mathcal{O}((T-N)g(N))$, when $\gamma \geq \gamma_c$, where $g(N)$ is the accuracy of a given nonlinear estimator and $N$ is the duration of the initial estimation period. We also characterize the lower bound on the required prediction horizon for these guarantees to hold in terms of the system constants.