Improvement of hand functions of spinal cord injury patients with electromyography-driven hand exoskeleton: A feasibility study

Abstract

We have developed a one-of-a-kind hand exoskeleton, called Maestro, which can power finger movements of those surviving severe disabilities to complete daily tasks using compliant joints. In this paper, we present results from an electromyography (EMG) control strategy conducted with spinal cord injury (SCI) patients (C5, C6, and C7) in which the subjects completed daily tasks controlling Maestro with EMG signals from their forearm muscles. With its compliant actuation and its degrees of freedom that match the natural finger movements, Maestro is capable of helping the subjects grasp and manipulate a variety of daily objects (more than 15 from a standardized set). To generate control commands for Maestro, an artificial neural network algorithm was implemented along with a probabilistic control approach to classify and deliver four hand poses robustly with three EMG signals measured from the forearm and palm. Increase in the scores of a standardized test, called the Sollerman hand function test, and enhancement in different aspects of grasping such as strength shows feasibility that Maestro can be capable of improving the hand function of SCI subjects.

Challenges and solutions for application and wider adoption of wearable robots

“…intention to be detected and the wearable robot to be moved accordingly (Yun et al, 2020). Additionally, EMG can be used as an effectiveness measure of the wearable robot: since wearable robots are meant to support the wearer and reduce human workload, reductions in EMG level can be considered proportional to reductions in human muscle demand (Goršič et al, 2021;Kermavnar et al, 2021).…”

“…Existing algorithms range from simple thresholding (e.g., activate assistance if user bends forward) to more complex approaches based on classification and regression using machine learning (Novak and Riener, 2015;Tucker et al, 2015). For example, classifiers can learn to identify desired gestures from EMG-based on a training dataset of previously recorded and manually labeled EMG data (Yun et al, 2020); similarly, regression algorithms can learn to estimate desired robot torque from ground reaction force (Naseri et al, 2020) or EMG (Gui et al, 2019).…”

Evaluation of a machine-learning-driven active–passive upper-limb exoskeleton robot: Experimental human-in-the-loop study

“…The brain produces biological signals and sends them to muscles as action potentials, so that the body is moved and controlled. The most frequently applied physiological signals that are utilized to analyze human movement and rehabilitation are surface electromyography (sEMG; Yun et al, 2020 ; Nasr et al, 2021a ) signals. Biological signal interpretation or classification was successfully achieved using machine-learning methods (Nasr et al, 2021a ), primarily using offline analysis.…”

A Compact and Lightweight Rehabilitative Exoskeleton to Restore Grasping Functions for People with Hand Paralysis

“…Different robotic systems for the upper limb have been recently introduced especially to acute and chronic stroke survivors. By powering the hand movements to accomplish everyday activities, assistive exoskeletons have shown the ability to improve the quality of life in patients with cervical cord injury [ 8 ]. However, these robotic systems such as the Hand of Hope [ 9 ], FESTO (FESTO, Esslingen, Germany), Milebot (MileBot, Hand Rehabilitation Exoskeleton Robot, Shenzhen, China), Handy Rehab (HandyRehab, Hong Kong, China), etc.…”