Control of Mechanical Systems via Feedback Linearization Based on Black-Box Gaussian Process Models

TL;DR

This paper explores feedback linearization control of mechanical systems using black-box Gaussian process models, comparing two strategies and analyzing the impact of kernel choices on robustness and performance.

Contribution

It introduces two novel GP-based feedback linearization strategies for mechanical systems and evaluates their robustness and effectiveness with different kernel functions.

Findings

Second strategy is more robust to kernel choice and model inaccuracies.

Structured kernels like polynomial improve performance across strategies.

Using GP models with structured kernels enhances trajectory tracking control.

Abstract

In this paper, we consider the use of black-box Gaussian process (GP) models for trajectory tracking control based on feedback linearization, in the context of mechanical systems. We considered two strategies. The first computes the control input directly by using the GP model, whereas the second computes the input after estimating the individual components of the dynamics. We tested the two strategies on a simulated manipulator with seven degrees of freedom, also varying the GP kernel choice. Results show that the second implementation is more robust w.r.t. the kernel choice and model inaccuracies. Moreover, as regards the choice of kernel, the obtained performance shows that the use of a structured kernel, such as a polynomial kernel, is advantageous, because of its effectiveness with both strategies.