Design and Evaluation of a Factorization-Based Grasp Myoelectric Control Founded on Synergies

Abstract

In this article we present a factorization-based myoelectric proportional control that uses surface skin electromyographic (sEMG) measurements to estimate the hand closure level of a user for telemanipulation purposes. The sEMG-based proportional control design is presented and the results of an experimental session are reported. In particular, involving one healthy subject, four different factorization algorithms are tested (Factor Analysis, Fast Independent Component Analysis, Non-negative Matrix Factorization and Principal Component Analysis) and quantitative evaluated along four different daily session using four different error metrics (Root-Mean-Square Error, Normalized Root-Mean-Square Error, cross-correlation coefficient and Dynamic Time Warping measurement). The metrics are computed comparing the sEMG-based estimation of the hand closure level with a ground-truth signal obtained through a motion tracking system. The results report for better performances of the Non-negative Matrix Factorization algorithm, that can be used for controlling robotic hands in a real telemanipulation scenario. Therefore, the proposed myoelectric proportional control was finally tested in a simple validation grasping scenario using a real robotic hand, reporting for user's simplicity and intuitiveness in regulating the grasp closure in accordance with different objects.