Donning/Doffing and Arm Positioning Influence in Upper Limb Adaptive Prostheses Control

Abstract

New upper limb prostheses controllers are continuously being proposed in the literature. However, most of the prostheses commonly used in the real world are based on very old basic controllers. One reason to explain this reluctance to change is the lack of robustness. Traditional controllers have been validated by many users and years, so the introduction of a new controller paradigm requires a lot of strong evidence of a robust behavior. In this work, we approach the robustness against donning/doffing and arm position for recently proposed linear filter adaptive controllers based on myoelectric signals. The adaptive approach allows to introduce some feedback in a natural way in real time in the human-machine collaboration, so it is not so sensitive to input signals changes due to donning/doffing and arm movements. The average completion rate and path efficiency obtained for eight able-bodied subjects donning/doffing five times in four days is 95.83% and 84.19%, respectively, and for four participants using different arm positions is 93.84% and 88.77%, with no statistically significant difference in the results obtained for the different conditions. All these characteristics make the adaptive linear regression a potential candidate for future real world prostheses controllers.

An Interactive Training Model for Myoelectric Regression Control Based on Human–Machine Cooperative Performance

“…Compared with classification models, the continuous outputs of regression estimates may more naturally mimic human movement. In addition, regression models have been found to be more robust to some unpredictable small variations in EMG signals and may generate better performance during untrained conditions compared to classification models [32,35].…”

“…However, this experiment is independent of the muscles source, therefore reproducible with other EMG signals from different origins. Previous works [16,35] have used these specifications for the data acquisition protocol with successful results.…”

Simultaneous Three-Degrees-of-Freedom Prosthetic Control Based on Linear Regression and Closed-Loop Training Protocol

“…However, these metrics are not so useful in our case since they do not provide a description of the performance of the complete system in terms of real-time task accuracy and efficiency. Different from these typical error-based metrics, performance metrics measure the accuracy of the complete system in real time in different ways [27,28]. In spite of recent efforts [29] to value the offline evaluation, to measure the real-time performance is much more relevant [30].…”