Event-based Low-Power and Low-Latency Regression Method for Hand Kinematics from Surface EMG

Human-Machine Interfaces (HMIs) are a rapidly progressing field, and gesture recognition is a promising method in industrial, consumer, and health use cases. Surface electromyography (sEMG) is a State-of-the-Art (SoA) pathway for humanto-machine communication. Currently, the research goal is a more intuitive and fluid control, moving from signal classification of discrete positions to continuous control based on regression. The sEMG-based regression is still scarcely explored in research since most approaches have addressed classification. In this work, we propose the first event-based EMG encoding applied to the regression of hand kinematics suitable for working in streaming on a low-power microcontroller (STM32 F401, mounting ARM Cortex-M4). The motivation for event-based encoding is to exploit upcoming neuromorphic hardware to benefit from reduced latency and power consumption. We achieve a Mean Absolute Error of 8.8 +/- 2.3 degrees on 5 degrees of actuation on the public dataset NinaPro DB8, comparable with the SoA Deep Neural Network (DNN). We use 9x less memory and 13x less energy per inference, with 10x shorter latency per inference compared to the SoA deep net, proving suitable for resource-constrained embedded platforms.