Home → News → Reinforcement Learning Expedites 'Tuning' of Robotic... → Full Text

Reinforcement Learning Expedites 'Tuning' of Robotic Prosthetics

By North Carolina State ­niversity

January 24, 2019

[article image]

Researchers at North Carolina State University, the University of North Carolina, and Arizona State University (ASU) have developed an intelligence system for "tuning" powered prosthetic knees, a breakthrough allowing patients to walk comfortably with the prosthetic device in a matter of minutes.

The system is the first to rely solely on reinforcement learning to tune the prosthesis.

The new tuning system can alter 12 different control parameters and address prosthesis dynamics, such as joint stiffness, throughout the entire gait cycle.

The system relies on a computer program that utilizes reinforcement learning to modify all 12 parameters.

Said ASU's Jennie Si, "We are thrilled to find out that our reinforcement learning control algorithm actually did learn to make the prosthetic device work as part of a human body in such an exciting applications setting."

From North Carolina State University
View Full Article


Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA


No entries found