Automatic LQR tuning based on Gaussian process global optimization

This paper proposes an automatic controller tuning framework based on linear optimal control combined with Bayesian optimization. With this framework, an initial set of controller gains is automatically improved according to a pre-defined performance objective evaluated from experimental data. The underlying Bayesian optimization algorithm is Entropy Search, which represents the latent objective as a Gaussian process and constructs an explicit belief over the location of the objective minimum. This is used to maximize the information gain from each experimental evaluation. Thus, this framework shall yield improved controllers with fewer evaluations compared to alternative approaches. A seven-degree-of-freedom robot arm balancing an inverted pole is used as the experimental demonstrator. Results of two- and four-dimensional tuning problems highlight the method's potential for automatic controller tuning on robotic platforms.

I. Introduction

Robotic setups often need fine-tuned controller parameters both at low- and task-levels. Finding an appropriate set of parameters through simplistic protocols, such as manual tuning or grid search, can be highly time-consuming. We seek to automate the process of fine tuning a nominal controller based on performance observed in experiments on the physical plant. We aim for information-efficient approaches, where only few experiments are needed to obtain improved performance.