Spiking neural network (SNN) control of a flapping insect-scale robot

Abstract

The flapping microrobot known as RoboBee is the first robot to demonstrate insect-scale flight, as well as the most capable flying robotic insect to date. Controlled hover, trajectory-following, and perching have been accomplished by means of onboard sensors and actuators fabricated with the robot using a “pop-up book MEMS” process based on smart composite microstructures. This paper presents a RoboBee bio-inspired controller that closes the loop between the onboard sensors and actuators by means of a leaky integrate-and-fire spiking neural network that adapts in flight using a reward-modulated Hebbian plasticity mechanism.