AUTHOR=Langlois Kevin , Geeroms Joost , Van De Velde Gabriel , Rodriguez-Guerrero Carlos , Verstraten Tom , Vanderborght Bram , Lefeber Dirk 

TITLE=Improved Motion Classification With an Integrated Multimodal Exoskeleton Interface

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 15 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2021.693110

DOI=10.3389/fnbot.2021.693110

ISSN=1662-5218

ABSTRACT=Human motion intention detection is an essential part of the control of upper-body exoskeletons.
While surface electromyography (sEMG)-based systems may be able to provide anticipatory control, they typically require exact placement of the electrodes on the muscle bodies which limits the practical use and donning of the technology. In this study, we propose a K-Nearest Neighbours classifier to detect reaching movements and lifting tasks that represent daily activities of industrial workers. The classifier uses  multimodal measurements obtained from 3D-printed sEMG- and pressure-sensors made of flexible, conductive materials, fully integrated in a 3D-printed physical interface for the upper arm. The performance of the classifier is validated through repeated experiments and compared to a unimodal EMG-based classifier. The results indicate that excellent prediction performance can be obtained, even with a minimal amount of sEMG electrodes and without specific placement of the electrode.