Mobile robot localization using fuzzy neural network based extended kalman filter

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

Authors

  • Nguyen Thi Thanh Van University of Engineering and Technology, Vietnam National University, Hanoi 144 Xuan Thuy, Cau Giay, Hanoi, Vietnam
  • Phung Manh Duong University of Engineering and Technology, Vietnam National University, Hanoi 144 Xuan Thuy, Cau Giay, Hanoi, Vietnam
  • Tran Thuan Hoang University of Engineering and Technology, Vietnam National University, Hanoi 144 Xuan Thuy, Cau Giay, Hanoi, Vietnam
  • Tran Quang Vinh University of Engineering and Technology, Vietnam National University, Hanoi 144 Xuan Thuy, Cau Giay, Hanoi, Vietnam

DOI:

https://doi.org/10.15625/1813-9663/29/2/2348

Keywords:

fuzzy logic, extended kalman filter, localization, mobile robot

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.

Metrics

Metrics Loading ...

Published

01-04-2013

How to Cite

[1]
N. T. Thanh Van, P. M. Duong, T. T. Hoang, and T. Q. Vinh, “Mobile robot localization using fuzzy neural network based extended kalman filter”, JCC, vol. 29, no. 2, pp. 116–126, Apr. 2013.

Issue

Section

Cybernetics