Learning nonlinear feedforward: a Gaussian Process Approach Applied to a Printer with Friction

TL;DR

This paper presents a Gaussian Process-based method for identifying inverse models of nonlinear systems, specifically applied to a printer with friction, resulting in improved tracking performance over linear feedforward methods.

Contribution

It introduces a novel Gaussian Process approach for modeling inverse nonlinear systems directly from input-output data, suitable for unknown system structures.

Findings

Enhanced tracking accuracy on a consumer printer with friction.

Gaussian Process inverse models outperform linear feedforward.

Method validated through experimental results.

Abstract

Feedforward control is essential to achieving good tracking performance in positioning systems. The aim of this paper is to develop an identification strategy for inverse models of systems with nonlinear dynamics of unknown structure using input-output data, which directly delivers feedforward signals for a-priori unknown tasks. To this end, inverse systems are regarded as noncausal nonlinear finite impulse response (NFIR) systems and modeled as a Gaussian Process with a stationary kernel function that imposes properties such as smoothness and periodicity. The approach is validated experimentally on a consumer printer with friction and shown to lead to improved tracking performance with respect to linear feedforward.