Synergistic EMG control of FES elbow extension after spinal cord injury

Individuals with a C5/C6 spinal cord injury (SCI) have paralyzed elbow extensors, yet retain weak to strong voluntary control of elbow flexion and some shoulder movements. They lack elbow extension, which is critical during activities of daily living. This research focuses on development of a synergistic controller employing remaining voluntary elbow flexor and shoulder electromyography (EMG) to control elbow extension with functional electrical stimulation (FES). We hypothesized that the remaining voluntary upper extremity muscles of a C5/C6 SCI subject produce repeatable, recognizable patterns of EMG indicative of the required triceps stimulation level. EMG from voluntary elbow flexor and shoulder muscles were used as inputs to train and test an artificial neural network (ANN) to output triceps stimulation level. A biomechanical model of the arm was used to estimate the triceps stimulation levels required for a particular subject and endpoint force goal. EMG was collected from SCI subjects while they generated isometric force vectors of varying magnitude and direction using the predicted triceps stimulation levels. Once trained, the network controller yielded low error and generalized.