Title :
SLAM based on intelligent unscented Kalman filter
Author :
Havangi, R. ; Nekoui, M.A. ; Taghirad, H.D. ; Teshnehlab, M.
Abstract :
The performance of SLAM based on unscented Kalman filter (UKF-SLAM) and thus the quality of the estimation depends on the correct a priori knowledge of process and measurement noise. Imprecise knowledge of these statistics can cause significant degradation in performance. In this paper, the adaptive Neuro-Fuzzy has been implemented to adapt the matrix covariance process of UKF-SLAM in order to improve its performance.
Keywords :
Kalman filters; SLAM (robots); covariance matrices; fuzzy neural nets; mobile robots; nonlinear filters; statistical analysis; UKF-SLAM; adaptive neuro-fuzzy; intelligent unscented Kalman filter; matrix covariance process; measurement noise; performance degradation; performance improvement; simultaneous localization and mapping; statistical analysis; Covariance matrix; Kalman filters; Noise; Noise measurement; Simultaneous localization and mapping; Vehicles;
Conference_Titel :
Control, Instrumentation and Automation (ICCIA), 2011 2nd International Conference on
Conference_Location :
Shiraz
Print_ISBN :
978-1-4673-1689-7
DOI :
10.1109/ICCIAutom.2011.6356777
