Simultaneous localization and mapping with neuro-fuzzy assisted extended Kalman filtering

This paper present the development of neuro-fuzzy based adaptive EKF for the SLAM problem with the aim of estimating the proper values for the elements of R matrix at each running step. The adaptive neuro fuzzy EKF (ANFEKF) is designed to reduce the mismatch between the theoretical and actual covariance of the innovation consequence. The particle swarm optimization (PSO) is then employed to train the free parameters of ANFEKF offline. By employing PSO we can exploit the advantages of the high-dimensional search space algorithm for more effective training of ANFEKF. The performance of the proposed approach is evaluated by experiments on the mobile robot platform under two benchmark of environment situation with a number of landmarks. The results has shown that the improvement of the proposed ANFEKF method in terms of computational cost, performance efficiency and real time implementation.