Gaussian Mixture Fitting Filter for Non-Gaussian Measurement Environment

In this paper, a novel Gaussian mixture fitting filter (GMFF) is proposed to copy with the nonlinear state estimation problem with non-Gaussian measurement environment. The core of GMFF is to use Gaussian mixture regression model to model the unknown measurement likelihood probability, which represents the combination of Gaussian mixture model and linear regression process. In the variational inference framework, through iteratively and alternatively achieving the fitting of the measurement model and the compensation of linear regression error, the estimation accuracy and adaptiveness can be enhanced gradually. The superior performance of GMFF is demonstrated in the simulations.