Shortcomings of human-in-the-loop optimization of an ankle-foot prosthesis emulator: a case series

Abstract

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.

Human-prosthesis cooperation: combining adaptive prosthesis control with visual feedback guided gait

“…Our observation in this study may explain why previous studies on human-in-the-loop optimization (HILO) of prosthesis control did not always show significant gait performance improvement for individuals with an amputation [8,11]. For example, one study unsuccessfully used HILO to attempt to optimize prosthesis ankle control torque to minimize the metabolic cost (as the cost function) [8].…”

“…Further, the tuning procedure can become impractical with the increased number of control parameters needed to be tuned. Research groups have created and investigated their own automatic prosthesis tuning algorithms that adjust the control parameters (either joint impedance or torque profiles) of the prosthesis as the user is walking to achieve a pre-determined goal [10][11][12][13]. Focusing on transfemoral prostheses, our group designed modelfree reinforcement learning (RL) algorithms to automatically tune 12 prosthesis control parameters to achieve normative knee motion in walking [12,13], which has been a common tuning goal for research and commercial robotic prostheses [4,5].…”

The split-belt rimless wheel

“…Models of human walking with powered assistive devices suggest that the addition of sufficient mechanical power could reduce human metabolic cost to negligible levels (Franks et al, 2020;Handford and Srinivasan, 2016;Uchida et al, 2016). However, in many experiments with powered prosthetic limbs (Quesada et al, 2016;Welker et al, 2021) and exoskeletons (Galle et al, 2017;Jackson and Collins, 2015;Van Dijk et al, 2017) human metabolic rate is reduced much less than expected, or not at all, while increased device work can actually increase human metabolic rate. Our study mirrors these findings; simple dynamical models of split-belt treadmill walking demonstrate a mechanism for energy-free gait that is apparently unavailable to humans, outweighed by other factors.…”

Human-Prosthesis Cooperation: Combining Adaptive Prosthesis Control with Visual Feedback Guided Gait

“…Further, the tuning procedure can become impractical with the increased number of control parameters needed to be tuned. Research groups have created and investigated their own automatic prosthesis tuning algorithms that adjust the control parameters (either joint impedance or torque pro les) of the prosthesis as the user is walking to achieve a pre-determined goal (8)(9)(10)(11). Focusing on transfemoral prostheses, our group designed model-free reinforcement learning (RL) algorithms to automatically tune 12 prosthesis control parameters to achieve normative knee motion in walking (10,11), which has been a common tuning goal for research and commercial robotic prostheses (4,5).…”