An Information-Rich and Highly Wearable Soft Sensor System Based on Displacement Myography for Practical Hand Gesture Interfaces

Wearable sensors for hand gesture recognition have demonstrated significant potential for creating non-invasive human-machine interfaces. Nonetheless, the trade-off between wearability, practicality and performance constrains their applicability in real-world scenarios. This paper introduces MyoLog, a wearable soft sensor system that utilises forearm muscle deformations for accurate hand gesture recognition. Muscle displacements are captured using an array of magnets and tri-axis magnetometers (displacement myography), integrated into soft and flexible structures that conform to and deform with the shape of forearm muscles. The high signal-to-noise ratio and sensitivity of the sensor modules in MyoLog produce information-rich signals, enabling the detection and differentiation of a wide spectrum of hand gestures. The study used the results of 9 participants performing 44 diverse gestures with MyoLog to investigate its performance in terms of number of gestures and achieved classification accuracy. The average performance achieved by participants was 97.7%, 91.5%, and 89.1% accuracy in executing 13, 22, and 28 gestures, respectively. To demonstrate the capabilities of MyoLog in practical settings, we explored two potential applications in virtual reality training for laparoscopic surgery and prosthetic hand control. The high wearability of MyoLog without compromising the performance paves the way for more practical human-machine interactions in diverse applications.