A Feature Extraction Pipeline for Enhancing Lightweight Neural Networks in sEMG-based Joint Torque Estimation
This work addresses accurate torque estimation for personalized exoskeleton assistance in rehabilitation, but it is incremental as it focuses on feature extraction for lightweight models.
The paper tackled the problem of predicting joint torques for robot-assisted rehabilitation using sEMG signals, proposing a feature extraction pipeline that enabled a simple MLP to achieve mean RMSEs of 0.963 N m, 1.403 N m, and 1.434 N m for elbow and shoulder joints, comparable to a TCN.
Robot-assisted rehabilitation offers an effective approach, wherein exoskeletons adapt to users' needs and provide personalized assistance. However, to deliver such assistance, accurate prediction of the user's joint torques is essential. In this work, we propose a feature extraction pipeline using 8-channel surface electromyography (sEMG) signals to predict elbow and shoulder joint torques. For preliminary evaluation, this pipeline was integrated into two neural network models: the Multilayer Perceptron (MLP) and the Temporal Convolutional Network (TCN). Data were collected from a single subject performing elbow and shoulder movements under three load conditions (0 kg, 1.10 kg, and 1.85 kg) using three motion-capture cameras. Reference torques were estimated from center-of-mass kinematics under the assumption of static equilibrium. Our offline analyses showed that, with our feature extraction pipeline, MLP model achieved mean RMSE of 0.963 N m, 1.403 N m, and 1.434 N m (over five seeds) for elbow, front-shoulder, and side-shoulder joints, respectively, which were comparable to the TCN performance. These results demonstrate that the proposed feature extraction pipeline enables a simple MLP to achieve performance comparable to that of a network designed explicitly for temporal dependencies. This finding is particularly relevant for applications with limited training data, a common scenario patient care.