Safe and Efficient Model-free Adaptive Control via Bayesian Optimization

TL;DR

This paper introduces a novel, data-driven, model-free adaptive control method using safe Bayesian optimization, demonstrating improved safety and efficiency on rotational systems through simulations and experiments.

Contribution

It presents a new adaptive control approach based on safe Bayesian optimization, specifically tailored for practical use on rotational systems, with enhancements for safety and computational efficiency.

Findings

The method is sample-efficient in various disturbance scenarios.

It outperforms constrained Bayesian optimization in safety.

It achieves performance close to grid evaluation optima.

Abstract

Adaptive control approaches yield high-performance controllers when a precise system model or suitable parametrizations of the controller are available. Existing data-driven approaches for adaptive control mostly augment standard model-based methods with additional information about uncertainties in the dynamics or about disturbances. In this work, we propose a purely data-driven, model-free approach for adaptive control. Tuning low-level controllers based solely on system data raises concerns on the underlying algorithm safety and computational performance. Thus, our approach builds on GoOSE, an algorithm for safe and sample-efficient Bayesian optimization. We introduce several computational and algorithmic modifications in GoOSE that enable its practical use on a rotational motion system. We numerically demonstrate for several types of disturbances that our approach is sample efficient, outperforms constrained Bayesian optimization in terms of safety, and achieves the performance optima computed by grid evaluation. We further demonstrate the proposed adaptive control approach experimentally on a rotational motion system.