Neural Network Strategy for Sampling of Particle Filters on the Tracking Problem

Abstract

Sequential Monte Carlo methods, namely particle filters, are popular statistic techniques for sampling sequentially from a complex probability distribution. Sampling is a key step for particle filters and has vital effects on simulation results. Since degeneracy of particles in samples sometimes is very severe, there exist only a few particles with significant weights. Thus the sample diversity is reduced significantly so that only a few particles are used to represent the corresponding probability distribution. Therefore, resampling has to be used very often during the whole procedure. This paper addresses a new method which can avoid the phenomenon of particle degeneracy. A backpropagation neural network is used to adjust low weight particles in order to increase their weights and particles with high weights may be split into two small ones if needed. Our simulation results on a typical tracking problem show that not only the phenomenon of particle degeneracy is effectively avoided but also tracking results are much better than those of the traditional particle filter.