This paper presents a Bayesian optimization framework for the automatic tuning of shared controllers which are defined as a Model Predictive Control (MPC) problem. The proposed framework includes the design of performance metrics as well as the representation of user inputs for simulation-based optimization. The framework is applied to the optimization of a shared controller for an Image Guided Therapy robot. VR-based user experiments confirm the increase in performance of the automatically tuned MPC shared controller with respect to a hand-tuned baseline version as well as its generalization ability.
@article{arxiv.2311.01133,
title = {A Bayesian optimization framework for the automatic tuning of MPC-based shared controllers},
author = {Anne van der Horst and Bas Meere and Dinesh Krishnamoorthy and Saray Bakker and Bram van de Vrande and Henry Stoutjesdijk and Marco Alonso and Elena Torta},
journal= {arXiv preprint arXiv:2311.01133},
year = {2023}
}