Automatic LQR Tuning Based on Gaussian Process Global Optimization

TL;DR

This paper introduces an automatic controller tuning method using Bayesian optimization with Gaussian processes, significantly reducing the number of experiments needed to optimize control gains on robotic systems.

Contribution

It combines linear optimal control with Entropy Search Bayesian optimization for automatic, data-efficient controller tuning.

Findings

Effective tuning on a robotic arm balancing an inverted pole.

Fewer evaluations needed compared to traditional methods.

Potential for automatic tuning in complex robotic platforms.

Abstract

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 a two- and four-dimensional tuning problems highlight the method's potential for automatic controller tuning on robotic platforms.