Co-Integrated Neuromorphic Devices for Bio-Inspired Compliance Control

Abstract

Mutual interactions between humans and devices are being widely adopted, including wearable electromechanical devices known as robotic exoskeletons. Among various modules used to control the human-robot interactions, compliance control (CC) is needed to ensure human safety and avoid abnormal operations. Here we propose a novel CC system with co-integrated neuromorphic devices composed of a pre-synapse, an interneuron, and a post-synapse. These devices are the same homotypic MOSFET with a SONOS configuration, despite having different functions. For proof-of-concept, semi-empirical simulations were conducted with the aid of an LTspice simulator, by reflecting measured neuron and synapse characteristics from the fabricated tri-gate FinFETs. The extremely low-power consumption of 0.2 mW, which is 55-fold smaller than other conventional approaches, was achieved. A high response rate of up to 3 ms was attained as well. Moreover, by automatically adjusting output signal frequency and amplitude, the micro-sized neuromorphic CC system can avoid excess actuator motion in human-robot interactions.