Using spiking neural networks for light spot tracking

Abstract

This paper introduces a new method for automatically compensating the light spot displacement from the normal position in laser spot trackers. The method is based on hardware implementation of the spiking neural networks which provides fast response due to real time operation and ability to learn unsupervised when they are stimulated by concurrent events. To validate this method we implemented in hardware a spiking neural network structure able to process the input from a photodiode array and to control a positioning system. The performance of the neural network that is based on an electronic neuron of biological inspiration was tested using the output of the photodiode array placed in strait line. The results show that the rapport between the energy consumed by the spiking neural network and the accuracy in compensating the spot moving on horizontal or vertical directions is significantly better than the rapport which is obtainable when programmable computing devices solve the same task. These results are encouraging to develop low power spot tracking system for enhancing the receiving accuracy in free space optics or for enhancing the efficacy of the photovoltaic systems.