Event-Based Estimation of Hand Forces From High-Density Surface EMG on a Parallel Ultralow-Power Microcontroller

Modeling hand kinematics and dynamics is a key goal for research on human-machine interfaces (HMIs), with surface electromyography (sEMG) being the most commonly used sensing modality. Though under-researched, sEMG regression-based modeling of hand movements and forces is promising for finer control than allowed by mapping to fixed gestures. We present an event-based sEMG encoding for multifinger force estimation implemented on a microcontroller unit (MCU). We are the first to target the High-densitY Surface Electromyogram Recording (HYSER) high-density (HD)-sEMG dataset in multiday conditions closest to a real scenario without a fixed force pattern. Our mean absolute error (MAE) of (8.4 ± 2.8)% of the maximum voluntary contraction (MVC) is on par with the state-of-the-art (SoA) works on easier settings such as within-day, single-finger, or fixed-exercise. We deploy our solution for HYSER’s hardest task on a parallel ultralow-power MCU, getting an energy consumption below $6.5~\mu \text{J}$ per sample, $2.8\times $ to $11\times $ more energy-efficient than SoA single-core solutions, and a latency below 280 $\mu \text{s}$ per sample, shorter than HYSER’s HD-sEMG sampling period, thus compatible with real-time operation on embedded devices.