Adaptive Neuro-Fuzzy Extended Kaiman Filtering for robot localization
Authors:
- 1 September 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. T5-130-T5-135
Abstract
Extended Kalman Filter (EKF) has been a popular approach in localization of a mobile robot. However, the performance of the EKF and the quality of the estimation depends on the correct a priori knowledge of process and measurement noise covariance matrices (Qk and RK, respectively). Imprecise knowledge of these statistics can cause significant degradation in performance. In this paper, the Adaptive Neuro-Fuzzy Inference System (ANFIS) supervises the performance of the EKF with adjusting the matrix Qk and RK. The ANFIS is trained using the steepest gradient descent (SD) to minimize the differences between the outputs of ANFIS and desired outputs. The simulation results show the effectiveness of the proposed algorithm.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Fuzzy Adaptive Extended Kalman Filter for miniature Attitude and Heading Reference System2009
- Hybrid Extended Kalman Filter-based localization with a highly accurate odometry model of a mobile robot2008
- An accurate localization for mobile robot using extended Kalman filter and sensor fusion2008
- An Effective Kalman Filter Localization Method for Mobile Robots2006
- Mobile Robot Localization Based on Extended Kalman Filter2006
- Estimation with Applications to Tracking and Navigation2002
- Development and experimental validation of an adaptive extended Kalman filter for the localization of mobile robotsIEEE Transactions on Robotics and Automation, 1999
- Mobile robot localization using landmarksIEEE Transactions on Robotics and Automation, 1997
- Divergence of the Kalman filterIEEE Transactions on Automatic Control, 1971
- On the identification of variances and adaptive Kalman filteringIEEE Transactions on Automatic Control, 1970