EN FR
EN FR


Section: New Results

Applications for Robotic myoelectric prostheses: co-adaptation algorithms and design of a 3D printed robotic arm prosthesis

Participants : Pierre-Yves Oudeyer [correspondant] , Manuel Lopes, Mathilde Couraud, Sebastien Mick, Aymar de Rugy, Daniel Cattaert, Florent Paclet.

Together with the Hybrid team at INCIA, CNRS, the Flowers team continued to work on establishing the foundations of a long-term project related to the design and study of myoelectric robotic prosthesis. The ultimate goal of this project is to enable an amputee to produce natural movements with a robotic prosthetic arm (open-source, cheap, easily reconfigurable, and that can learn the particularities/preferences of each user). This will be achieved by 1) using the natural mapping between neural (muscle) activity and limb movements in healthy users, 2) developing a low-cost, modular robotic prosthetic arm and 3) enabling the user and the prosthesis to co-adapt to each other, using machine learning and error signals from the brain, with incremental learning algorithms inspired from the field of developmental and human-robot interaction. In particular, in 2016 two lines of work were achieved, concerning two important scientific challenges, and in the context of one PEPS CNRS projects:

First, a new version of the experimental setup was designed to allow fast prototyping of 3D printed robotic prostheses. This work was based on the use of the Poppy open-source modular platform, and resulted in a functional prototype. A video demonstrations is available at: https://github.com/s-mick

Second, we have designed various control models allowing to transform signals coming from the human arm (either measured through EMGs or direct force sensors) and we have studied the influence of control modes on usability in the operation of a robotic arm prosthesis. In this context, we designed an experimental framework centered on a target-reaching task, and carried out tests with healthy subjects. The usability assessment relies on performance metrics on one hand, and a post-experiment questionnaire on another hand, in order to explore the multiple dimensions of the system's usability rather than focus only on measurements evaluating skills and performances. The code associated to this experimental setup is open-source and available at https://github.com/s-mick.