Differential evolution tuned fuzzy supervisor adapted extended Kalman filtering for SLAM problems in mobile robots

The present paper proposes a successful application of differential evolution (DE) optimized fuzzy logic supervisors (FLS) to improve the quality of solutions that extended Kalman filters (EKFs) can offer to solve simultaneous localization and mapping (SLAM) problems for mobile robots and autonomous vehicles. The utility of the proposed system can be readily appreciated in those situations where an incorrect knowledge of Q and R matrices of EKF can significantly degrade the SLAM performance. A fuzzy supervisor has been implemented to adapt the R matrix of the EKF online, in order to improve its performance. The free parameters of the fuzzy supervisor are suitably optimized by employing the DE algorithm, a comparatively recent method, popularly employed now-a-days for high-dimensional parallel direct search problems. The utility of the proposed system is aptly demonstrated by solving the SLAM problem for a mobile robot with several landmarks and with wrong knowledge of sensor statistics. The system could successfully demonstrate enhanced performance in comparison with usual EKF-based solutions for identical environment situations.

[1]  Maurice Clerc,et al.  The particle swarm - explosion, stability, and convergence in a multidimensional complex space , 2002, IEEE Trans. Evol. Comput..

[2]  David W. Murray,et al.  Simultaneous Localization and Map-Building Using Active Vision , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Kazuyuki Kobayashi,et al.  Accurate differential global positioning system via fuzzy logic Kalman filter sensor fusion technique , 1998, IEEE Trans. Ind. Electron..

[4]  Hugh F. Durrant-Whyte,et al.  A solution to the simultaneous localization and map building (SLAM) problem , 2001, IEEE Trans. Robotics Autom..

[5]  R. Storn,et al.  On the usage of differential evolution for function optimization , 1996, Proceedings of North American Fuzzy Information Processing.

[6]  Man Systems,et al.  1996 Biennial Conference of the North American Fuzzy Information Processing Society - NAFIPS , 1996 .

[7]  R. Fitzgerald.  Divergence of the Kalman filter , 1971 .

[8]  R. Mehra.  On the identification of variances and adaptive Kalman filtering , 1970 .

[9]  Eduardo Mario Nebot,et al.  Optimization of the simultaneous localization and map-building algorithm for real-time implementation , 2001, IEEE Trans. Robotics Autom..

[10]  Rainer Storn,et al.  Minimizing the real functions of the ICEC'96 contest by differential evolution , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[11]  R. Eberhart,et al.  Empirical study of particle swarm optimization , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[12]  Peter Cheeseman,et al.  On the Representation and Estimation of Spatial Uncertainty , 1986 .

[13]  Sebastian Thrun,et al.  FastSLAM 2.0: An Improved Particle Filtering Algorithm for Simultaneous Localization and Mapping that Provably Converges , 2003, IJCAI.

[14]  Robert Sutton,et al.  Adaptive tuning of a Kalman filter via fuzzy logic for an intelligent AUV navigation system , 2004 .