Electromyography (EMG) signals are widely used as control inputs for myoelectric exoskeletons. However, muscle fatigue, which can result from prolonged use or heavy loads, significantly affects muscle activation patterns, leading to reduced estimation accuracy. To address this challenge, we propose an adversarial learning framework to enhance grip force estimation under fatigue conditions. The framework consists of three key components: a domain-invariant feature extractor to mitigate domain shifts between non-fatigue and fatigue states, a force estimator to predict grip forces from these domain-invariant features, and a domain discriminator to distinguish between the two domains. The proposed method was evaluated on a dataset collected from eight participants performing gripping tasks under both non-fatigue and fatigue conditions, during which high-density EMG signals and grip forces were recorded simultaneously. Experimental results demonstrated that our method significantly reduced the root mean square error (RMSE) from 0.264 to 0.127, outperforming a baseline model consisting of only the feature extractor and force estimator$(p < 0.01)$. Additionally, the proposed approach exhibited consistent performance across all participants, highlighting its robustness and generalizability. These findings suggest that the proposed adversarial learning framework effectively enhances grip force estimation accuracy under muscle fatigue, offering a promising solution for improving the reliability and usability of myoelectric exoskeletons.

High-density electromyography (EMG) decomposition technology enables the myoelectric control on the level of individual motor units (MUs). Compared to traditional EMG-based control schemes, the MU-based control strategy exhibits enhanced reliability and superiority in the decoding of continuous motion and real-time control. Current MU-based control schemes are usually limited to one or two degrees of freedom (DoFs), reducing intuitiveness. In this work, we use a graph-based clustering method to associate MUs with multiple wrist/hand movements, realizing three-DoF simultaneous and proportional control (SPC) based on motor unit action potential train (MUAPT) decomposed from high-density EMG signals. The cumulative discharges of MUs within each group were extracted and mapped into multi-DoF motion activations with a multiple linear regression model. The performance of the proposed control scheme was tested on twelve subjects. Each subject controlled a virtual arrow to finish real-time control tasks with both position and velocity-based approaches. The results were promising: the task completion rate reached 89.2% in velocity control mode, and 70% in position control mode, which requires simultaneous activation of multiple DoFs. This study demonstrates the feasibility of three-DoF real-time myoelectric control based on MUAPTs, demonstrating the potential of MUs in creating more intuitive human-machine interfaces.

Estimating cumulative spike train (CST) of motor units (MUs) from surface electromyography (sEMG) is essential for the effective control of neural interfaces. However, the limited accuracy of existing estimation methods greatly hinders the further development of neural interface. This paper proposes a simple but effective approach for identifying CST based on spatial spike detection from high-density sEMG. Specifically, we use a spatial sliding window to detect spikes according to the spatial propagation characteristics of the motor unit action potential, focusing on the spikes of activated MUs in a local area rather than those of a specific MU. We validated the effectiveness of our proposed method through an experiment involving wrist flexion/extension and pronation/supination, comparing it with a recognized CST estimation method and an MU decomposition based method. The results demonstrated that the proposed method obtained higher accuracy on multi-DoF wrist torque estimation leveraging the estimated CST compared to the other three methods. On average, the correlation coefficient (R) and the normalized root mean square error (nRMSE) between the estimation results and recorded force were 0.96 ± 0.03 and 10.1% ± 3.7%, respectively. Moreover, there was an extremely high interpretive extent between the CSTs of proposed method and the MU decomposition method. The outcomes reveal the superiority of the proposed method in identifying CSTs and can provide promising driven signals for neural interface.

Surface electromyography (EMG) signals have shown promising applications in human-machine interfacing (HMI) systems such as orthotics, prosthetics, and exoskeletons. Nevertheless, existing myoelectric control methods, generally based on time-domain or frequency-domain features, could not directly interpret neural commands. EMG decomposition techniques have become a prevailing solution to decode the motor neuron discharges from the spinal cord, whereas only single degree-of-freedom (DoF) movements are primarily involved in the current neural-based interfaces, resulting in limited intuitiveness and functionality. Here, we propose a non-invasive framework to analyze motor unit activities and estimate wrist torques during simultaneous contractions of multiple DoFs. Motor unit discharges were decoded from surface EMG signals and pooled into groups during sequential wrist movements. Then three neural features were extracted and linearly projected to the torques of multi-DoF tasks. On average, there were 44 ±13 motor units identified for each motion with a PNR value of 25.8 ±2.9 dB. The neural features outperformed the classic EMG feature on the estimation accuracy with higher correlation coefficients and smoothness. These results demonstrate the feasibility and superiority of the proposed framework in kinetics estimation of simultaneous movements, extending the potential applications of surface EMG decomposition in human-machine interfaces.

Neural interface using decomposed motor units (MUs) from surface electromyography (sEMG) has allowed non-invasive access to the neural control signals, and provided a novel approach for intuitive human-machine interaction. However, most of the existing methods based on decomposed MUs merely adopted the discharge rate (DR) as the feature representations, which may lack local information around the discharge instant and ignore the subtle interactions of different MUs. In this study, we proposed an MU-specific image-based scheme for wrist torque estimation. Specifically, the high-density sEMG signals were decoded into motor unit spike trains (MUSTs), and then MU-specific images were reconstructed with MUSTs and corresponding motor unit action potential (MUAP). A convolutional neural network was used to learn representative features from MU-specific images automatically, and further to estimate wrist torques. The results demonstrated that the proposed method outperformed three conventional and a deep-learning regression approaches using DR features, with the estimation accuracy R2of 0.82 ± 0.09, 0.89 ± 0.06, and nRMSE of 12.6 ± 2.5%, 11.0 ± 3.1% for pronation/supination and flexion/extension, respectively. Further, the analysis of the extracted features from MU-specific images showed a higher correlation than DR for recorded torques, indicating the effectiveness of the proposed method. The outcomes of this study provide a novel and promising perspective for the intuitive control of neural interfacing.

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 R2equal 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.