Fulltext

Movement Onset Detection and Target Estimation for Robot-Aided Arm Training = Bestimmung des Bewegungsbeginns und Bewegungsziels bei der roboterunterstützten Armrehabilitation

Riener, Robert ; Novak, Domen

In: at - Automatisierungstechnik, 2015, vol. 63, no. 4, p. 286-298

Aggiungi alla tua lista
    Titre
    • Movement Onset Detection and Target Estimation for Robot-Aided Arm Training
    Titre traduit ()
    • Bestimmung des Bewegungsbeginns und Bewegungsziels bei der roboterunterstützten Armrehabilitation
    Auteur
    • Riener, Robert. ETH Zurich, Zurich
    • Novak, Domen. University of Wyoming, USA
    Type de document
    • Postprint
    Langue
    • Tedesco
    Publié dans
    • at - Automatisierungstechnik, 2015, vol. 63, no. 4, p. 286-298. De Gruyter Oldenbourg
    Autre version électronique
    Identifiant OAI-PMH
    • oai:doc.rero.ch:325712
    Summary
    This paper presents a motion intention estimation algorithm that is based on the recordings of joint torques, joint positions, electromyography, eye tracking and contextual information. It is intended to be used to support a virtual-reality-based robotic arm rehabilitation training. The algorithm first detects the onset of a reaching motion using joint torques and electromyography. It then predicts the motion target using a combination of eye tracking and context, and activates robotic assistance toward the target. The algorithm was first validated offline with 12 healthy subjects, then in a real-time robot control setting with 3 healthy subjects. In offline crossvalidation, onset was detected using torques and electromyography 116 ms prior to detectable changes in joint positions. Furthermore, it was possible to successfully predict a majority of motion targets, with the accuracy increasing over the course of the motion. Results were slightly worse in online validation, but nonetheless show great potential for real-time use with stroke patients.