While most wearable gesture recognition approaches focus on the forearm or fingers, the wrist may a more suitable location for practical use. We present the design and validation of a real-time gesture recognition wristband based on surface electromyography (sEMG) and inertial measurement unit (IMU) sensing fusion, which can recognize 8 air gestures and 4 surface gestures with 2 distinct force levels. Ten healthy subjects performed an initial gesture recognition experiment, followed by a second experiment 1 hour later and a third experiment 1 day later. Classification accuracies for the initial experiment were 92.6% and 88.8% for air and surface gestures, respectively, and there were no changes in accuracy results during testing 1 hour and 1 day later (p>0.05). These results demonstrate the feasibility of wrist-based gesture recognition paving the way for potential future integration in to a smart watch or other wrist-worn wearable for intuitive human computer interaction.

The research on muscular activity based human-machine interface (HMI) is of great significance, such as controlling prosthetic hand to improve the life quality of amputee patients. However, the HMI performance is limited by muscular fatigue due to frequent muscle contraction. To overcome the drawback, this paper presents a multi-modal sensing system that can collect surface electromyography (sEMG), near-infrared spectroscopy (NIRS) and mechanomyography (MMG) simultaneously. To evaluate the performance of the multi-modal signal acquisition system, incremental isometric voluntary contractions experiment is carried out. The experimental results show that the proposed system can reliably obtain three kinds of muscle contraction information from the perspective of electrophysiology, oxygen metabolism and low-frequency vibration of myofiber. Furthermore, muscle fatigue induced experiment imitating HMI usage is performed, and it convincingly demonstrates a significantly (p < 0.01) improved classification accuracy (CA) by using multi-modal features. The CA is compensated by 3.6% ~ 22.9% in the presence of muscular fatigue. These results suggest that multi-modal sensing can improve the HMI performance and robustness. The outcomes of this study have great potential to promote the biomedical and clinical applications of human-machine interaction.

It is vital to measure muscular fatigue for human–machine interaction (HMI) and avoiding muscle impairment. This article presents a novel approach to comprehensively evaluate muscle fatigue through the fusion of mini-grid surface electromyography (sEMG), mechanomyography (MMG), and near-infrared spectroscopy (NIRS). A hybrid mini-grid sEMG, MMG, and NIRS sensor system was developed, forming an instrument to measure motor unit action potential trains (MUAPts), low-frequency myofiber vibration, and oxygen metabolism. Muscle fatigue-induced experiment was performed via a sustained isometric contraction at 50% of maximal voluntary contraction (MVC) force with ten subjects. MUAPts were decomposed from the four-channel array of sEMG signals, and the firing rate (FR) of specific motor units (MUs) was calculated to measure fatigue process. Furthermore, root mean square (rms) and median frequency (MDF) of sEMG/MMG, blood volume (BV), and muscle oxygenation ( $\triangle $ HbO ₂ ) extracted from NIRS, were proposed as fatigue metrics. The variation and correlation analysis among fatigue metrics provided a detailed and reliable physiological assessment on muscle fatigue, gaining a synthetic understanding of muscle fatigue mechanisms. The outcomes of this study have great potential applications in sports, clinical diagnosis, and HMI.

Dexterous prosthetic hand is an essential rehabilitation assistant device to improve the life quality of amputee patients. Despite the continuous emergence of commercial prostheses and laboratory prototypes, the rejection rate remains high caused by the poor neural interaction performance and excessive cognitive burden, especially for the usage of upper-arm prostheses controlled by above-the-elbow amputation stump. The progress in artificial perception, bidirectional neural interface and share control indicates a great potential to improve the manipulation efficiency of upper-limb prostheses. In this review, a comprehensive analysis of human-in-the-loop shared control studies is presented to provide researchers with a systematic technical route in upper-limb prostheses control. The latest avenues of research concerning myoelectric control, sensory feedback, perception, autonomous motion planning of multiple degree of freedom elbow-wrist, and share control are overviewed and discussed. The comprehensive assessments show that there remains inadequate technologies to achieve an anthropomorphic and efficient unified elbow-wrist-hand prostheses manipulation. By delineating the current shortcomings, the outcomes of this work highlight future investigation in the field of intuitive motion control, feedback of proprioception/touch and the natural interaction between human intent and machine autonomy.

This letter introduces a variable admittance control approach aimed at enhancing intuitive human-robot interaction by considering both direct and indirect human intentions. The magnitude of force serves as a representation of direct intentions, delineating preferences for rapid or precise motions. Drawing from the movement sciences and motor control field, the minimum-jerk model is employed to mirror human motor system control policies and movement behaviors. From this model, velocity-curvature patterns are derived, enabling an intuitive estimation of indirect intentions indicating long-term objectives like trajectory and turning direction. We propose an innovative guidance method, rooted in the estimation of indirect human intentions, enabling the robot to concurrently follow and guide the operator. To assess the efficacy of this approach, both offline simulations and real-time human experiments are conducted on a six-DOF robot and a force/torque sensor. Our comprehensive experiments demonstrate substantial enhancements in both accuracy ( ${\geq\!\text{12.1}{\%}}$ ) and smoothness ( ${\geq\!\text{18.3}{\%}}$ ) over fixed admittance control and state-of-the-art variable admittance methods.

It is of great significance to recognize hand gestures via measuring biological signals from forearm muscles for portable human-machine interaction (HMI). Decreasing the number of sensor nodes is imperative for practical HMI applications. However, it would be an enormous challenge to maintain gesture recognition performance for traditional myoelectric interface with sparse-site sensing. To overcome this drawback, we present a novel HMI predicting more than ten hand and wrist motions relying on only two hybrid mini-grid surface electromyography (sEMG), mechanomyography (MMG) and near-infrared spectroscopy (NIRS) sensor nodes. Beyond the time domain (TD) features of sEMG, additional information containing movement intention is measured from motor unit action potential trains (MUAPt) according to the decomposition of four-channel arrayed sEMG. Furthermore, low-frequency myofiber vibration and haemodynamics are extracted from MMG and NIRS, respectively. Experiments are performed on thirteen healthy subjects to recognize 12 hand and wrist gestures. The results indicate that combining motor unit discharge feature yields consistently higher ( p <0.01) classification accuracy (91.6%) than traditional TD features of sEMG (87.8%) by using linear discrimination analysis classifier. Additionally, both MMG and NIRS features are demonstrated effective supplementary to distinguish muscular activation patterns, producing significantly enhanced (4.2%~11.2%, p <0.05) recognition performance with the fused information. The outcomes of this study are promising for the HMI applications such as controlling prosthetic hand and wearable device.