We present a fully programmable ultra-low-power embedded platform that hosts an "electronic skin" (E-skin) arrays of tactile sensors with up to 64 channels, ECG/EMG sensors up to 8 channels, inertial sensors, and a Bluetooth Low Energy 5.0 module. The platform's compute engine is a heterogeneous multi-core parallel ultra-low power (PULP) processor based on RISC-V, capable of delivering up to 2.5 GOPS, within a 55 mW power consumption envelope, which makes the platform ideal for battery-powered always-on operation. Experimental results show a peak of 38.3x energy efficiency increase (0.7 V, 85 MHz) compared to ARM-Cortex-M microcontrollers with similar power budgets.
Eggimann M., Mach S., Magno M., Benini L. (2019). A RISC-V Based Open Hardware Platform for Always-On Wearable Smart Sensing. Institute of Electrical and Electronics Engineers Inc. [10.1109/IWASI.2019.8791364].
A RISC-V Based Open Hardware Platform for Always-On Wearable Smart Sensing
Mach S.;Benini L.
2019
Abstract
We present a fully programmable ultra-low-power embedded platform that hosts an "electronic skin" (E-skin) arrays of tactile sensors with up to 64 channels, ECG/EMG sensors up to 8 channels, inertial sensors, and a Bluetooth Low Energy 5.0 module. The platform's compute engine is a heterogeneous multi-core parallel ultra-low power (PULP) processor based on RISC-V, capable of delivering up to 2.5 GOPS, within a 55 mW power consumption envelope, which makes the platform ideal for battery-powered always-on operation. Experimental results show a peak of 38.3x energy efficiency increase (0.7 V, 85 MHz) compared to ARM-Cortex-M microcontrollers with similar power budgets.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
