Stable Gaussian Process based Tracking Control of Euler-Lagrange Systems

by   Thomas Beckers, et al.

Perfect tracking control for real-world Euler-Lagrange systems is challenging due to uncertainties in the system model and external disturbances. The magnitude of the tracking error can be reduced either by increasing the feedback gains or improving the model of the system. The latter is clearly preferable as it allows to maintain good tracking performance at low feedback gains. However, accurate models are often difficult to obtain. In this article, we address the problem of high-performance tracking control for unknown Euler-Lagrange systems. In particular, we employ Gaussian Process Regression (GPR) to obtain a data-driven model that is used for the feed-forward compensation of unknown dynamics of the system. Beneficially, GPR provides not only an estimate of the uncertainties, but naturally provides a measure of model confidence depending on the distance to training points. Accordingly, the feedback gain is adapted based on the model fidelity allowing low feedback gains in state space regions of high model confidence. Additionally, we study the stability of GP-based tracking control for Euler-Lagrange systems. The proposed confidence-adaptive feedback control law guarantees a globally bounded tracking error with a specific probability. Simulation studies illustrate the results and demonstrate the superiority over state of the art tracking control approaches.



There are no comments yet.


page 1

page 2

page 3

page 4


Keep soft robots soft -- a data-driven based trade-off between feed-forward and feedback control

Tracking control for soft robots is challenging due to uncertainties in ...

Online Gaussian Process learning-based Model Predictive Control with Stability Guarantees

Model predictive control provides high performance and safety in the for...

Robust tracking of an unknown trajectory with a multi-rotor UAV: A high-gain observer approach

We study a trajectory tracking problem for a multi-rotor in the presence...

Learning dynamics for improving control of overactuated flying systems

Overactuated omnidirectional flying vehicles are capable of generating f...

How Training Data Impacts Performance in Learning-based Control

When first principle models cannot be derived due to the complexity of t...

Concurrent Learning Based Tracking Control of Nonlinear Systems using Gaussian Process

This paper demonstrates the applicability of the combination of concurre...

Differential Flatness of Quadrotor Dynamics Subject to Rotor Drag for Accurate Tracking of High-Speed Trajectories

In this paper, we prove that the dynamical model of a quadrotor subject ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.