Toward Deep Generalization of Peripheral EMG-Based Human-Robot Interfacing: A Hybrid Explainable Solution for NeuroRobotic Systems

This letter investigates the feasibility of a generalizable solution for human-robot interfaces through peripheral multichannel Electromyography (EMG) recording. We propose a tangential approach in comparison to the literature to minimize the need for (re)calibration of the system for new users. The proposed algorithm decodes the signal space and detects the common underlying global neurophysiological components, which can be detected robustly across various users, minimizing the need for retraining and (re)calibration. The research question is how to go beyond techniques that detect a high number of gestures for a given individual (which requires extensive calibration) and achieve an algorithm that can detect a lower number of classes but without the need for (re)calibration. The outcomes of this letter address a challenge affecting the usability and acceptance of advanced myoelectric prostheses. For this, the paper proposes an explainable generalizable hybrid deep learning architecture that incorporates CNN and LSTM. We also utilize the GradCAM analysis to explain and optimize the structure of the generalized model, securing higher computational performance whiles proposing a shallower design.