Communications of the ACM
Reinforcement Learning Expedites 'Tuning' of Robotic Prosthetics
Researchers from North Carolina State University, the University of North Carolina and Arizona State University have developed an intelligent system for tuning powered prosthetic knees that relies solely on reinforcement learning.
Credit: NC State University News
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