Improved FastSLAM2.0 using ANFIS and PSO

Abstract

Original scienti c paper FastSLAM2.0 is a framework for simultaneous localization of robot using a Rao-Blackwellized particle lter (RBPF). One of the problems of FastSLAM2.0 relates to the design of RBPF. The performance and quality of the estimation of RBPF depends heavily on the correct a priori knowledge of the process and measurement noise covariance matrices that are in most real-life applications unknown. On the other hand, an incorrect a priori knowledge may seriously degrade their performance. This paper presents an intelligent RBPF to solve this problem. In this method, two adaptive Neuro-Fuzzy inference systems (ANFIS) are used for tuning the process and measurement noise covariance matrices and for increasing acuuracy and consistency. In addition, we use particle swarm optimization (PSO) to optimize the performance of sampling. Experimental results demonstrate that the proposed algorithm is effective.

LSO-FastSLAM: A New Algorithm to Improve the Accuracy of Localization and Mapping for Rescue Robots

“…One of the problems is particle weight degradation and particle diversity loss. This problem is caused by the adoption of Rao-Blackwellized filter in the FastSLAM algorithm, which will decrease the accuracy of the FastSLAM algorithm [ 11 , 12 , 13 , 14 , 15 ]. Another problem of the FastSLAM algorithm is that it requires a large number of particles to maintain the accuracy of the algorithm in a complex environment, which will increase the running time of the algorithm and reduce the efficiency of the robot.…”