Towards enhanced control of upper prosthetic limbs: A force-myographic approach

Abstract

Reliable decoding of a user's intention is a key step to control prosthetic devices. Force myography (FMG) is often used to assess topographic force patterns resulting from volumetric changes of activated muscles. However, during limb position changes this approach may give deteriorating performance over time. To address this limitation, we developed a position-aware platform that integrates an inertial measurement unit (IMU) and a force sensing array (FSA) with an advanced signal processing module. The module analyzes data using an artificial neural network (ANN) to predict an intended hand movement. Our results demonstrate that by utilizing multi-sensory information this decoding strategy provides a 90% accuracy.