Particle Flow Gaussian Sum Particle Filter

TL;DR

This paper introduces a Gaussian sum particle filter that employs particle flow to better approximate complex distributions in challenging estimation problems, improving upon existing methods.

Contribution

It proposes a novel Gaussian sum particle filter using particle flow, enabling more accurate modeling of complex distributions compared to single Gaussian approaches.

Findings

Outperforms existing particle flow filters in simulations

Effectively models complex, multi-modal distributions

Demonstrates improved estimation accuracy in challenging scenarios

Abstract

Particle flow Gaussian particle flow (PFGPF) uses an invertible particle flow to generate a proposal density. It approximates the predictive and posterior distributions as Gaussian densities. In this paper, we use bank of PFGPF filters to construct a Particle flow Gaussian sum particle filter (PFGSPF), which approximates the predictive and posterior as Gaussian mixture model. This approximation is useful in complex estimation problems where a single Gaussian approximation is not sufficient. We compare the performance of this proposed filter with PFGPF and others in challenging numerical simulations.