A Motor Unit-specific Images Based Scheme for Continuous Estimation of Wrist Torques - A Pilot Study

Neural interface using motor units (MUs) decomposed from surface electromyography (sEMG) has provided a novel approach for the intuitive human-robot interaction. However, existing feature extraction methods from decomposed MUs are simplex, ignoring the inherent spatial information and the subtle interactions between different MUs. In this study, we proposed a MU-specific images based scheme for extracting features from decomposed MUs and further estimating wrist torques continuously. Specifically, MU-specific images were reconstructed from decomposed MUs using sEMG and fed into a convolutional neural network for feature extraction and estimating wrist torques. The results demonstrated that the proposed scheme significantly outperformed three conventional regression methods using decomposed spike count features, with R ² equal to 0.86 ± 0.05 in pronation/supination and 0.90 ± 0.05 in flexion/extension. This study provides a novel scheme for estimation of continuous movement using decomposed MUs and potentially paves the way of neural interface.