Mobile robot localization using fuzzy neural network based extended kalman filter

Nguyen Thi Thanh Van, Phung Manh Duong, Tran Thuan Hoang, Tran Quang Vinh

Abstract


This paper proposes an approach to improve the performance of the extended Kalmanfilter (EKF) for the problem of mobile robot localization. A fuzzy logic systemis employed to continuously 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 theaccuracy and avoid the divergence of the EKF when the noise covariance matricesare fixed or incorrectly determined. Simulations and experiments are given. The results show thatthe proposed filter is better than the EKF in localizing the mobile robot.

Keywords


fuzzy logic, extended kalman filter, localization, mobile robot

Full Text: PDF

Refbacks

  • There are currently no refbacks.


Journal of Computer Science and Cybernetics ISSN: 1813-9663

Published by Vietnam Academy of Science and Technology