Learning-Based Repetitive Precision Motion Control with Mismatch Compensation

TL;DR

This paper introduces a learning-based iterative control method that uses Gaussian Process Regression to adaptively compensate for model mismatch in repetitive precision motion tasks, enhancing tracking accuracy.

Contribution

It presents a novel iterative control approach combining nominal models with GPR for mismatch learning, specifically designed for repetitive precision motion control.

Findings

Improved tracking accuracy demonstrated in simulations.

Experimental results confirm effectiveness of mismatch compensation.

Convergence analysis supports method stability.

Abstract

Learning-based control methods utilize run-time data from the underlying process to improve the controller performance under model mismatch and unmodeled disturbances. This is beneficial for optimizing industrial processes, where the dynamics are difficult to model, and the repetitive nature of the process can be exploited. In this work, we develop an iterative approach for repetitive precision motion control problems where the objective is to follow a reference geometry with minimal tracking error. Our method utilizes a nominal model of the process and learns the mismatch using Gaussian Process Regression (GPR). The control input and the GPR data are updated after each iteration to improve the performance in a run-to-run fashion. We provide a preliminary convergence analysis, implementation details of the proposed controller for minimizing different error types, and a case study where we demonstrate improved tracking performance with simulation and experimental results.