Ramazan HAVANGI, Mohammad Ali NEKOUI, Mohammad TESHNEHLAB

An improved FastSLAM framework using soft computing

FastSLAM is a framework for simultaneous localization and mapping (SLAM) using a Rao-Blackwellized particle filter. However, FastSLAM degenerates over time. This degeneracy is due to the fact that a particle set estimating the pose of the robot loses its diversity. One of the main reasons for losing particle diversity in FastSLAM is sample impoverishment. In this case, most of the particle weights are insignificant. Another problem of FastSLAM relates to the design of an extended Kalman filter (EKF) for the landmark position's estimation. The performance of the EKF and the quality of the estimation depend heavily on correct a priori knowledge of the process and measurement noise covariance matrices (Qt and Rt ), which are, in most applications, unknown. Incorrect a priori knowledge of Qt and Rt may seriously degrade the performance of the Kalman filter. This paper presents a modified FastSLAM framework by soft computing. In our proposed method, an adaptive neuro-fuzzy extended Kalman filter is used for landmark feature estimation. The free parameters of the adaptive neuro-fuzzy inference system (ANFIS) are trained using the steepest gradient descent (SD) to minimize the differences of the actual value of the covariance of the residual from its theoretical value as much possible. A novel multiswarm particle filter is then presented to overcome the impoverishment of FastSLAM. The multiswarm particle filter moves samples toward the region of the state space in which the likelihood is significant, without allowing them to go far from the region of significant proposal distribution. The simulation results show the effectiveness of the proposed algorithm.

Anahtar Kelimeler:

SLAM, mobile robot, particle filter, particle swarm optimization, neuro-fuzzy, extended Kalman filter, gradient descent

An improved FastSLAM framework using soft computing

Keywords:

SLAM, mobile robot, particle filter, particle swarm optimization, neuro-fuzzy, extended Kalman filter, gradient descent,

PDF

___

S. Thrun, D. Fox, W. Burgard, “A probabilistic approach to concurrent mapping and localization for mobile robots”, Machine Learning, Vol. 31, pp. 29-53, 1999.
T. Bailey, J. Nieto, E. Nebot, “Consistency of the FastSLAM algorithm”, IEEE International Conference on Robotics and Automation, pp. 424-429, 2006.
M. Bosse, J. Leonard, S. Teller, “Large-scale CML using a network of multiple local maps”, Workshop Notes of the ICRA Workshop on Concurrent Mapping and Localization for Autonomous Mobile Robots (W4), Washington, DC, 2002.
T. Bailey, Mobile Robot Localization and Mapping in Extensive Outdoor Environments, PhD thesis, University of Sydney, Sydney, NSW, Australia, 2002.
S. Williams, G. Dissanayake, H.F. Durrant-Whyte, “Towards terrain-aided navigation for underwater robotics”, Advanced Robotics, Vol. 15, pp. 533-550, 2001.
S. Thrun, D. Hahnel, D. Ferguson, M. Montemerlo, R. Triebel, “A system for volumetric robotic mapping of abandoned mines”, in IEEE International Conference on Robotics and Automation, Taipei, Taiwan, pp. 4270-4275,
S. Thrun, W. Burgard, D. Fox, Probabilistic Robotics, Cambridge, MIT Press, 2005.
T. Bailey, J. Nieto, E. Nebot, “Consistency of the FastSLAM algorithm”, IEEE International Conference on Robotics and Automation, pp. 424-429, 2006.
M. Bolic, P.M. Djuric, S. Hong, “Resampling algorithms for particle Şlters: a computational complexity perspec- tive”, Journal on Applied Signal Processing, Vol. 2004, pp. 2267-2277, 2004.
L. Zhang, X. Meng, Y. Chen, “Convergence and consistency analysis for FastSLAM”, IEEE Intelligent Vehicles Symposium, 2009.
M. Montemerlo, FastSLAM: A Factored Solution to the Simultaneous Localization and Mapping Problem with Unknown Data Association, PhD thesis, Carnegie Mellon University, 2003.
M. Montemerlo, S. Thrun, D. Koller, B. Wegbreit, “FastSLAM 2.0: an improved particle Şltering algorithm for simultaneous localization and mapping that provably converges”, International Joint Conference on ArtiŞcial Intelligence, 2003.
N. Kwak, I.K. Kim, H.C. Lee, B.H. Lee, “Adaptive prior boosting technique for the eﬃcient sample size in FastSLAM”, in IEEE/RSJ International Conference on Intelligent Robots and Systems, San Diego, CA, USA, pp. 630-635, 2007.
C. Kim, R. Sakthivel, W.K. Chung, “Unscented FastSLAM: A robust algorithm for the simultaneous localization and mapping problem”, in IEEE International Conference on Robotics and Automation, pp. 2439-2445, 2007.
C. Kim, R. Sakthivel, W.K. Chung, “Unscented FastSLAM: a robust and eﬃcient solution to the SLAM problem”, IEEE Transactions on Robotics, Vol. 24, pp. 808-820, 2008.
X. Wang, H. Zhang, “A UPF-UKF framework for SLAM”, IEEE International Conference on Robotics and Automation, pp. 1664-1669, 2007.
A. Kong, J.S. Liu, W.H. Wong, “Sequential and Bayesian missing data problems”, Journal of the American Statistical Association, Vol. 89, pp. 278-288, 1994.
M. Li, B. Hong, R. Luo, Z. Wei, “A novel method for mobile robot simultaneous localization and mapping”, Journal of Zhejiang University Science A, pp. 937-944, 2006.
X. Chen, “An adaptive UKF-based particle Şlter for mobile robot SLAM”, International Joint Conference on ArtiŞcial Intelligence, 2009.
N. Kwak, G. Kim, B. Lee, “A new compensation technique based on analysis of resampling process in FastSLAM”, Robotica, Vol. 26, pp. 205-217, 2007.
I. Kim, N. Kwak, H. Lee, B. Lee, “Improved particle fusing geometric relation between particles in FastSLAM”, Robotica, Vol. 27, pp. 853-859, 2009.
R. Havangi, M.A. Nekoui, M. Teshnehlab, “A multi swarm particle Şlter for mobile robot localization”, International Journal of Computer Science Issues, Vol. 7, pp. 15-22, 2010.
R.J. Fitzgerald, “Divergence of the Kalman Şlter”, IEEE Transactions on Automatic Control, Vol. AC-16, pp. 747, 1971.
R.K. Mehra, “On the identiŞcation of variances and adaptive Kalman Şltering”, IEEE Transactions on Automatic Control, Vol. AC-15, pp. 175-184, 1970.
R. Havangi, M.A. Nekoui, M. Teshnehlab, “Adaptive neuro-fuzzy extended Kalman Şltering for robot localization”, International Journal of Computer Science Issues, Vol. 7, pp. 15-23, 2010.
G. Reina, A. Vargas, K. Nagatani, K. Yoshida, “Adaptive Kalman Şltering for GPS-based mobile robot localization”, IEEE International Workshop on Safety, Security and Rescue Robotics, 2007.
L. Jetto, S. Longhi, “Development and experimental validation of an adaptive extended Kalman Şlter for the localization of mobile robots”, IEEE Transactions on Robotics and Automation, Vol. 15, pp. 219-229, 1999.
A.P. Sage, G.W. Husa, “Adaptive Şltering with unknown prior statistics”, Joint Automatic Control Conference, pp. 760-769, 1969.
K. Murphy, “Bayesian map learning in dynamic environments”, Proceedings of the Conference on Neural Informa- tion Processing Systems, Denver, CO, USA, pp. 1015-1021, 1999.
S. Thrun, M. Montemerlo, D. Koller, B. Wegbreit, J. Nieto, E. Nebot, “FastSLAM: An eﬃcient solution to the simultaneous localization and mapping problem with unknown data association”, Journal of Machine Learning Research, Vol. 4, pp. 380-407, 2004.
M. Montemerlo, S. Thrun, D. Koller, B.Wegbreit, “FastSLAM: a factored solution to the simultaneous localization and mapping problem”, Proceedings of AAAI National Conference on ArtiŞcial Intelligence, Edmonton, AB, Canada, 2002.
G. Grisetti, C. Stachniss, W. Burgard, “Improving grid-based SLAM with Rao-Blackwellized particle Şlters by adaptive proposal and selective resampling”, IEEE International Conference on Robotics and Automation, pp. 2448, 2005.
G. Grisetti, C. Stachniss, W. Burgard, “Improved techniques for grid mapping with Rao-Blackwellized particle Şlters”, IEEE Transactions on Robotics, Vol. 23, pp. 34-46, 2007.
R. Krohling, “A Gaussian swarm: a novel particle swarm optimization algorithm”, IEEE Conference on Cybernetics and Intelligent Systems, Singapore, pp. 372-376, 2004.
T. Bailey, Source Code, University of Sydney, available at: http://www-personal.acfr.usyd.edu.au/tbailey/software/index.html, 2008.