Random Weighting-Based Nonlinear Gaussian Filtering

Zhaohui Gao,Yongmin Zhong,Jiahui Yang,Shesheng Gao,Chengfan Gu

doi:10.1109/access.2020.2968363

Abstract

The Gaussian filtering is a commonly used method for nonlinear system state estimation. However, this method requires both system process noise and measurement noise to be white noise sequences with known statistical characteristics. However, it is difficult to satisfy this condition in engineering practice, making the Gaussian filtering solution deviated or diverged. This paper adopts the random weighting concept to address the limitation of the nonlinear Gaussian filtering. It establishes the random weighting estimations of system noise characteristics on the basis of the maximum a-posterior theory, and further develops a new Gaussian filtering method based on the random weighting estimations to restrain system noise influences on system state estimation by adaptively adjusting the random weights of system noise characteristics. Simulation, experimental and comparison analyses prove that the proposed method overcomes the limitation of the traditional Gaussian filtering in requirement of system noise characteristics, leading to improved estimation accuracy.

Highlights

Nonlinear system state estimation is an important research topic in many science and engineering fields, such as vehicle navigation and guidance systems, robotic control, target recognition, radar tracking, information fusion, spacecraft orbit determination, and signal processing [5], [21]
This paper proposes a novel Gaussian filtering method based on random weighting to overcome the shortcoming of the traditional Gaussian filtering for nonlinear system state estimation by adaptively estimating system noise characteristics
This paper proposes a new random weighting-based Gaussian filtering (RWGF) for estimation of nonlinear system state

Summary

INTRODUCTION

Nonlinear system state estimation is an important research topic in many science and engineering fields, such as vehicle navigation and guidance systems, robotic control, target recognition, radar tracking, information fusion, spacecraft orbit determination, and signal processing [5], [21]. EKF approximates the nonlinear system model by the first-order Taylor expansion [17], and conducts nonlinear state estimation based on the linear structure of the traditional Kalman filter. This paper proposes a novel Gaussian filtering method based on random weighting to overcome the shortcoming of the traditional Gaussian filtering for nonlinear system state estimation by adaptively estimating system noise characteristics. This method establishes random weighting theories to online estimate the means and covariance of both system process and measurement noises based on the MAP principle. Simulations and experiments as well as comparison analysis with the traditional Gaussian filtering were conducted to comprehensively evaluate the performance of the proposed method

PRINCIPLE OF RANDOM WEIGHTING

ANALYSIS OF TRADITIONAL GAUSSIAN FILTERING

RANDOM WEIGHTING MAP ESTIMATION

CONCLUSION