|Title||A Myoelectric Control Interface for Upper-Limb Robotic Rehabilitation Following Spinal Cord Injury|
|Publication Type||Journal Article|
|Year of Publication||2020|
|Authors||McDonald, CG, Sullivan, JL, Dennis, TA, O’Malley, MK|
|Journal||IEEE Transactions on Neural Systems and Rehabilitation Engineering|
|Keywords||Electromyography; injuries; Muscles; myoelectric control; pattern recognition; Rehabilitation robotics; Robot kinematics; Robot sensing systems; spinal cord injury; Wrist|
Spinal cord injury (SCI) is a widespread, life-altering injury leading to impairment of sensorimotor function that, while once thought to be permanent, is now being treated with the hope of one day being able to restore function. Surface electromyography (EMG) presents an opportunity to examine and promote human engagement at the neuromuscular level, enabling new protocols for intervention that could be combined with robotic rehabilitation, particularly when robot motion or force sensing may be unusable due to the user’s impairment. In this paper, a myoelectric control interface to an exoskeleton for the elbow and wrist was evaluated on a population of ten able-bodied participants and four individuals with cervical-level SCI. The ability of an EMG classifier to discern intended direction of motion in single-degree-of-freedom (DoF) and multi-DoF control modes was assessed for usability in a therapy-like setting. The classifier demonstrated high accuracy for able-bodied participants (averages over 99% for single-DoF and near 90% for multi-DoF), and performance in the SCI group was promising, warranting further study (averages ranging from 85% to 95% for single-DoF, and variable multi-DoF performance averaging around 60%). These results are encouraging for the future use of myoelectric interfaces in robotic rehabilitation for SCI.