Mobile Robot Localization Using Fuzzy Neural Network Based Extended Kalman Filter

TL;DR

This paper introduces a fuzzy neural network-enhanced extended Kalman filter that adaptively adjusts noise covariance matrices, significantly improving mobile robot localization accuracy and stability over traditional EKF methods.

Contribution

It presents a novel fuzzy neural network approach to dynamically tune EKF parameters, reducing divergence and enhancing localization performance.

Findings

Proposed filter outperforms standard EKF in simulations and experiments

Adaptive adjustment of noise covariance improves localization accuracy

Method prevents divergence of the Kalman filter in noisy environments

Abstract

This paper proposes a novel approach to improve the performance of the extended Kalman filter (EKF) for the problem of mobile robot localization. A fuzzy logic system is employed to continuous-ly adjust the noise covariance matrices of the filter. A neural network is implemented to regulate the membership functions of the antecedent and consequent parts of the fuzzy rules. The aim is to gain the accuracy and avoid the divergence of the EKF when the noise covariance matrices are fixed or wrongly determined. Simulations and experiments have been conducted. The results show that the proposed filter is better than the EKF in localizing the mobile robot.