Spike-based Beamforming using pMUT Arrays for Ultra-Low Power Gesture Recognition

Sensor arrays constrain the power budget of battery-powered smart sensor as the analogue front-end (AFE), analogue-to-digital conversion (ADC) and digital signal processing is duplicated for each channel. By converting and processing the relevant information in the spiking domain, the energy consumption can be reduced by several orders of magnitude. We propose the first end-to-end ultra-low power Gesture Recognition (GR) system comprising an array of emitting and receiving piezoelectric micromachined ultrasonic transducers (pMUT), driving/sensing electronics, a novel spike-based beamforming strategy to extract the distance and angle information from incoming echoes without conventional ADCs and a Spiking Recurrent Neural Network (SRNN) for the GR. We experimentally demonstrate a classification accuracy of 86.0% on a dataset of five 3D gestures collected on our experimental setup.