Learning References with Gaussian Processes in Model Predictive Control applied to Robot Assisted Surgery

TL;DR

This paper introduces a method using Gaussian processes to learn reference signals for model predictive control, enhancing proactive control in robot-assisted surgery where external references are uncertain.

Contribution

The paper proposes a novel approach to incorporate Gaussian process-based reference learning into model predictive control for improved robotic surgery performance.

Findings

Effective learning of reference signals with Gaussian processes

Improved tracking accuracy in robot-assisted surgery

Enhanced predictive control under uncertain external references

Abstract

One of the key benefits of model predictive control is the capability of controlling a system proactively in the sense of taking the future system evolution into account. However, often external disturbances or references are not a priori known, which renders the predictive controllers shortsighted or uninformed. Adaptive prediction models can be used to overcome this issue and provide predictions of these signals to the controller. In this work we propose to learn references via Gaussian processes for model predictive controllers. To illustrate the approach, we consider robot assisted surgery, where a robotic manipulator needs to follow a learned reference position based on optical tracking measurements.