Flexible, Self-Adaptive Sense-and-Compress SoC for Sub-microWatt Always-On Sensory Recording

Abstract

We present a 5-sensor, fully integrated sensing system with interchangeable sensors and programmable configuration to create a sub-microWatt multisensor node that can tackle a wide range of sensing applications. Furthermore, the sensor node is capable of autonomously adapting its configuration to the application requirements hence minimizing system power. Such self-reconfiguration is enabled at low overhead by developing an automated offline optimization strategy, in combination with an autonomous embedded configuration controller, using the concept of behavioral trees (BTs). The resulting fully integrated platform consumes a maximum of 321 nW when sampling at 500 Hz and 3025 nW at 8 kHz. Furthermore, we demonstrate the end-to-end autonomous optimization flow for two different applications exploiting different sensors: 1) human activity recognition using accelerometers and 2) machine listening using a microphone. Both use cases demonstrate that the introduced system and methodology reduces the power by more than a factor 2 without losing significant application detection accuracy.