Section: New Results
Applications in Robotic myoelectric prostheses
Participants : Pierre-Yves Oudeyer [correspondant] , Aymar de Rugy, Daniel Cattaert, Mick Sebastien.
Together with the Hybrid team at INCIA, CNRS (Sébastien Mick, Daniel Cattaert, Florent Paclet, Aymar de Rugy) and Pollen Robotics (Matthieu Lapeyre, Pierre Rouanet), the Flowers team continued to work on a 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.
Reachy, a 3D-printed Human-like Robotic Arm as a Test Bed for Prosthesis Control Strategies
To this day, despite the increasing motor capability of robotic prostheses, elaborating efficient control strategies is still a key challenge for their design. To provide an amputee with efficient ways to drive a prosthesis, this task requires thorough testing prior to integration into finished products. To preserve consistency with prosthetic applications, employing an actual robot for such testing requires it to show human-like features. To fulfill this need for a biomimetic test platform, we developed the Reachy robotic platform, a seven-joint human-like robotic arm that can emulate a prosthesis. Although it does not include an articulated hand and is therefore more suitable for studying reaching than manipulation, a robotic hand from available research prototypes could be integrated to Reachy. Its 3D-printed structure and off-the-shelf actuators make it inexpensive relatively to the price of a genuine prosthesis. Using an open-source architecture, its design makes it broadly connectable and customizable, so it can be integrated into many applications. To illustrate how Reachy can connect to external devices, we developed several proofs of concept where it is operated with various control strategies, such as tele- operation or vision-driven control. In this way, Reachy can help researchers to develop and test innovative control strategies on a human-like robot.
Ship Motion estimation from sea wave vision
Participants : David Filliat [correspondant] , Natalia Díaz Rodríguez, Zhi Zhou, Manuel Cortés-Batet, Nazar-Mykola Kaminskyi.
Together with Naval Group, ENSTA Paris has been working on a set of software tools for simulating sea waves and motion estimation from images. The objective is predicting variables of interest in order to compensate the position and inclination of large boats at deep sea, seconds ahead of time to preserve stability. Work being currently done in partnership with Abo Akademi University (Turku, Finland) will validate the soon to be published Blender wave generator and machine learning algorithms, with real data gathered from the Baltic Sea archipelago.