Differential Evolution and Bayesian Optimisation for Hyper-Parameter Selection in Mixed-Signal Neuromorphic Circuits Applied to UAV Obstacle Avoidance
This work addresses obstacle avoidance for UAVs using neuromorphic circuits, but it is incremental as it applies existing optimization methods to a specific model.
The authors tackled hyper-parameter optimization for a neuromorphic spiking neural network model of the Lobula Giant Movement Detector applied to UAV obstacle avoidance, using Differential Evolution and Self-Adaptive Differential Evolution, and showed that these methods outperform state-of-the-art Bayesian optimization.
The Lobula Giant Movement Detector (LGMD) is a an identified neuron of the locust that detects looming objects and triggers its escape responses. Understanding the neural principles and networks that lead to these fast and robust responses can lead to the design of efficient facilitate obstacle avoidance strategies in robotic applications. Here we present a neuromorphic spiking neural network model of the LGMD driven by the output of a neuromorphic Dynamic Vision Sensor (DVS), which has been optimised to produce robust and reliable responses in the face of the constraints and variability of its mixed signal analogue-digital circuits. As this LGMD model has many parameters, we use the Differential Evolution (DE) algorithm to optimise its parameter space. We also investigate the use of Self-Adaptive Differential Evolution (SADE) which has been shown to ameliorate the difficulties of finding appropriate input parameters for DE. We explore the use of two biological mechanisms: synaptic plasticity and membrane adaptivity in the LGMD. We apply DE and SADE to find parameters best suited for an obstacle avoidance system on an unmanned aerial vehicle (UAV), and show how it outperforms state-of-the-art Bayesian optimisation used for comparison.