Effects of output speed threshold on real-time continuous emg human-machine interface control

Continuous EMG control of human-machine interfaces (HMIs) enables more direct and flexible control of output movements than discrete classification algorithms. However, EMG is a non-stationary signal and can add noise to continuous EMG control output. We studied the effect of an output speed threshold method to stabilize the movement prediction of a 2-DOF musculoskeletal model-based continuous EMG controller during a real-time virtual task. In each of several trials, three able-bodied subjects were instructed to move and align the palm and finger segments of a virtual hand with four different target postures on a computer screen. Three different thresholds on the model's predicted angular speed were applied in a randomized order across trials: no threshold, medium threshold (15 °/sec), and high threshold (30 °/sec); the virtual hand did not move if the predicted angular speed at the next timepoint did not exceed the threshold. We recorded completion time, overshoot, jerk, and number of failed trials to quantify task performance. In a separate block of trials, subjects reported their threshold preference following multiple pairwise comparisons. The number of overshoots decreased and jerk magnitude increased with higher threshold levels. The average completion time was lowest with the medium threshold for 2 subjects. All 3 subjects had lower failed trials with either the medium or high threshold. The subject preference score showed an inverse trend with the number of failed trials. In summary, the presented threshold method was successful in reducing overshoot and trial failures, and a threshold was preferred by all subjects over no threshold. Thus, an output speed threshold may improve the functional performance and user satisfaction of continuous EMG control for HMIs, such as powered upper limb prostheses.