Graphics Processing Unit Implementation of the Particle Filter

Modern graphics cards for computers, and especially their graphics processing units (GPUs), are designed for fast rendering of graphics. In order to achieve this GPUs are equipped with a parallel architecture which can be exploited for general-purpose computing on GPU (GPGPU) as a complement to the central processing unit (CPU). In this paper GPGPU techniques are used to make a parallel GPU implementation of state-of-the-art recursive Bayesian estimation using particle filters (PF). The modifications made to obtain a parallel particle filter, especially for the resampling step, are discussed and the performance of the resulting GPU implementation is compared to one achieved with a traditional CPU implementation. The resulting GPU filter is faster with the same accuracy as the CPU filter for many particles, and it shows how the particle filter can be parallelized