skip to main content

Title: Wearer-Prosthesis Interaction for Symmetrical Gait: A Study Enabled by Reinforcement Learning Prosthesis Control
; ; ;
Award ID(s):
1808898 1563454 1563921 1808752
Publication Date:
Journal Name:
IEEE Transactions on Neural Systems and Rehabilitation Engineering
Page Range or eLocation-ID:
904 to 913
Sponsoring Org:
National Science Foundation
More Like this
  1. Prosthetic devices have significantly improved mobility and quality of life for amputees. Significant engineering advancements have been made in artificial limb biomechanics, joint control systems, and light-weight materials. Amputees report that the primary problem they face with their artificial limbs is a poor fitting socket. In this paper, we propose a smart prosthesis system, in which we measure the real-time force distributions within a prothetic socket and dynamically visualize the results in a mobile application. A major part of the overall proposed system, a wireless pressure sensing system and a force visualization method, are evaluated at current stage. Finally, corresponding works for fully completing this smart prosthesis system are discussed as well.
  2. Human-in-the-loop optimization allows for individualized device control based on measured human performance. This technique has been used to produce large reductions in energy expenditure during walking with exoskeletons but has not yet been applied to prosthetic devices. In this series of case studies, we applied human-in-the-loop optimization to the control of an active ankle-foot prosthesis used by participants with unilateral transtibial amputation. We optimized the parameters of five control architectures that captured aspects of successful exoskeletons and commercial prostheses, but none resulted in significantly lower metabolic rate than generic control. In one control architecture, we increased the exposure time per condition by a factor of five, but the optimized controller still resulted in higher metabolic rate. Finally, we optimized for self-reported comfort instead of metabolic rate, but the resulting controller was not preferred. There are several reasons why human-in-the-loop optimization may have failed for people with amputation. Control architecture is an unlikely cause given the variety of controllers tested. The lack of effect likely relates to changes in motor adaptation, learning, or objectives in people with amputation. Future work should investigate these potential causes to determine whether human-in-the-loop optimization for prostheses could be successful.