Journal of Institute of Control, Robotics and Systems (제어로봇시스템학회논문지)

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지
DOI QR코드

DOI QR Code

An Improved Resampling Technique using Particle Density Information in FastSLAM

FastSLAM 에서 파티클의 밀도 정보를 사용하는 향상된 Resampling 기법

  • 우종석 (서울대학교 전기컴퓨터공학부) ;
  • 최명환 (강원대학교 전기전자공학부) ;
  • 이범희 (서울대학교 전기컴퓨터공학부)
  • Published : 2009.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

FastSLAM which uses the Rao-Blackwellized particle filter is one of the famous solutions to SLAM (Simultaneous Localization and Mapping) problem that estimates concurrently a robot's pose and surrounding environment. However, the particle depletion problem arises from the loss of the particle diversity in the resampling process of FastSLAM. Then, the performance of FastSLAM degenerates over the time. In this work, DIR (Density Information-based Resampling) technique is proposed to solve the particle depletion problem. First, the cluster is constructed based on the density of each particle, and the density of each cluster is computed. After that, the number of particles to be reserved in each cluster is determined using a linear method based on the distance between the highest density cluster and each cluster. Finally, the resampling process is performed by rejecting the particles which are not selected to be reserved in each cluster. The performance of the DIR proposed to solve the particle depletion problem in FastSLAM was verified in computer simulations, which significantly reduced both the RMS position error and the feature error.

Keywords

References

  1. M. Montemerlo, 'FastSLAM: A factored solution to the simultaneous localization and mapping problem with unknown data association,' Ph.D. thesis, Camegie Mellon University, 2003
  2. M. Montemerlo and S. Thrun, 'Simultaneous localimtion and mapping with unknown data association using FastSLAM,' IEEE International Corrference on Robotics and Automation, pp. 1985-1991,2003
  3. T. Bailey, J. Nieto, and E. Nebot, 'Consistency of the FastSLAM algorithm,' IEEE International Conference on Robotics and Automation, pp. 424-429, 2006
  4. S. Thrun, W. Burgard, and D. Fox, 'Probabilistic robotics,' MIT Press, Cambridge, 2005
  5. N. J. Gordon, D. J. Salmond, and A. F. M. Smith, 'Novel approach to nonlinear/non-gaussian Bayesian state estimation,' IEE-Proceedings- F. vol. 140, no. 2. pp. 107-113 https://doi.org/10.1049/ip-f-2.1993.0015
  6. N. Kwak, I. K. Kim, and H. C. Lee, et al., 'Adaptive prior boosting technique for the efficient sample size in FastSLAM,' IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007
  7. I. K. Kim, N. Kwak, H. C. Lee, and B. H. Lee, 'Improved particle filter using geometric relation between particles in FastSLAM,' Robotica, Oct. 2008. (accepted)
  8. Y. Zhao and J. Song, 'GDILC:A grid-based density-isoline clustering algorithm,' Proceedings of International Conforence on Info-tech and lifo-net, 2001
  9. M. Ester, H. Kriegel, J. Sander, and X. Xu, 'A density-based algorithm for discovering clusters in large spatial databases with noise,' inProc. KDD, pp. 226-231,1996
  10. E. Schikuta, 'Grid clustering: An efficient hierarchical clustering method for very large data sets,' Proc. 13th Int. Conf. on Pattern Recognition, vol. 2, pp. 101-105, 1996 https://doi.org/10.1109/ICPR.1996.546732
  11. K. Alsabti, S. Ranka, and V. Singh, 'An efficient K-means clustering algorithm,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, issue. 7, pp. 881-892,2002 https://doi.org/10.1109/TPAMI.2002.1017616
  12. N. Kwak, G W. Kim, and B. H. Lee, 'A new compensation technique based on analysis of resampling process in FastSLAM,' Robotica, vol. 26, no. 2, pp. 205-217, Mar. 2008
  13. S. Lee and S. Lee, 'Recursive particle filter with geometry constraints for SLAM,' IEEE. Int. Conf. Multisensor Fusion and Integration for Intelligent Systems, Heidelberg, pp. 395-401, 2006
  14. S. Thrun, D. Fox, and W. Burgard, 'Monte carlo localization with mixture proposal distribution,' American Association for Artificial Intelligence, pp. 859-865, 2000
  15. G Grisetti, G D. Tipaldi, and C. Stachniss, et al., 'Fast and accurate SLAM with rao-blackwellized particle filters,' Robotics andAutonomous Systems, vol. 55, pp. 30-38, Jan 2007 https://doi.org/10.1016/j.robot.2006.06.007
  16. M. Montemerlo and S. Thrun, 'imultaneous localization and mapping with unknown data association using fastslam,' Proceedings of the 2003 IEEE International Conforence on Robotics and Automation, pp. 185-1991 https://doi.org/10.1109/ROBOT.2003.1241885
  17. J. Kennedy and R. C. Eberhart, 'Particle swarm optimization,' Proceedings of IEEE International 1995 Conforence on Neural Networks, voI.4,pp. 1942-1948, 1995 https://doi.org/10.1109/ICNN.1995.488968