Geographical Group-based FastSLAM Algorithm for Maintenance of the Diversity of Particles

파티클 다양성 유지를 위한 지역적 그룹 기반 FastSLAM 알고리즘

  • Jang, June-Young (Dept. of Electronic and Communication Engr., Kangwon National University) ;
  • Ji, Sang-Hoon (Dept. of Applied Robot Technology, Korea Institute of Industrial Technology) ;
  • Park, Hong Seong (Dept. of Electronic and Communication Engr., Kangwon National University)
  • 장준영 (강원대학교 전자통신공학과) ;
  • 지상훈 (한국생산기술연구원) ;
  • 박홍성 (강원대학교 전자통신공학과)
  • Received : 2013.06.20
  • Accepted : 2013.08.11
  • Published : 2013.10.01


A FastSLAM is an algorithm for SLAM (Simultaneous Localization and Mapping) using a Rao-Blackwellized particle filter and its performance is known to degenerate over time due to the loss of particle diversity, mainly caused by the particle depletion problem in the resampling phase. In this paper, the GeSPIR (Geographically Stratified Particle Information-based Resampling) technique is proposed to solve the particle depletion problem. The proposed algorithm consists of the following four steps : the first step involves the grouping of particles divided into K regions, the second obtaining the normal weight of each region, the third specifying the protected areas, and the fourth resampling using regional equalization weight. Simulations show that the proposed algorithm obtains lower RMS errors in both robot and feature positions than the conventional FastSLAM algorithm.


Supported by : 산업통상자원부


  1. W. Lu and C. Zixing "Progress of CML for mobile robots in unknown environments," Robot, vol. 26, no. 4, pp. 380-384, Jul. 2004.
  2. H. Durrant-Whyte and T. Bailey, "Simultaneous localization and mapping: part1," IEEE Robotics and Automation Magazine, vol. 13, no. 2, pp. 99-110, Jun. 2006.
  3. J.-T. Park and J.-B. Song "Low-cost sensor-based exploration in home environments with salient VVisual features," Ineternational Conference on Control, Automation and Systems, pp. 2218-2222, Oct. 2010.
  4. S.-Y. An and J.-G. Kang, "SLAM with visually salient line features in indoor hallway environments," Journal of Insititute of Control, Robotics and System (in Korean), vol. 16, no. 1, pp. 40-47, Jan. 2010.
  5. S.-Y. Hwang and J.-B. Song "Monocular vision and odometry- based SLAM using position and orientation of ceiling lamps," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 17, no. 2, pp. 164-170, Feb. 2011.
  6. T. Bailey, "Mobile robot localization and mapping in extensive outdoor environments," Ph.D. Thesis, University of Sydney, NSW, Australia, 2002.
  7. S. Williams, G. Dissanayake, and H. F. Durrant-Whyte, "Towards terrain-aided navigation for underwater robotics," Advanced Robotics, vol. 15, pp. 533-549, Apr. 2012.
  8. S. Thrun, D. Hahnel, D. Ferguson, Montemerlo, and R. Triebel, "A system for volumetric robotic mapping of abandoned mines," Proc. of IEEE International Conference on Robotics and Automation, Taipei, pp. 4270-4275, Sep. 2003.
  9. S. Thrun, W. Burgard, and D. Fox, Probabilistic, Cambridge, MIT Press, 2005.
  10. M. Montemerlo, S. Thrun, D. Koller, and B. Wegbreit, "FastSLAM 2.0 : an improved particle filtering algorithm for simultaneous localization and mapping that probably converges," Proc. of International Joint Conference on Artificial Intelligence, 2003.
  11. M. Bolic, P. M. Djuric, and S. Hong, "Resampling algorithms for particle filters: a computational complexity perspective," Journal on Applied Signal Processing, pp. 2267-2277, Apr. 2004.
  12. L. Zhang, X. Meng, and Y. Chen, "Convergence and consistency analysis for FastSLAM," IEEE Intelligent Vehicles Symposium, pp. 447-452, June. 2009.
  13. T. Bailey, J. Nieto, and E. Nebot, "Consistency of the FastSLAM algorithm," IEEE International Conference on Robotics and Automation, pp. 424-429, May 2006.
  14. S. Thrun, M. Montemerlo, D. Koller, B. Wegbreit, J. Nieto, and 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.
  15. M. Montemerlo, "FastSLAM: a factored solution to the simultaneous localization and mapping problem with unknown data association," Ph.D. Thesis, Carnegie Mellon University, pp. 593-598, 2003.
  16. R. Havangi and M. A. Nekoui, "An improved FastSLAM framework using soft computing," Turk J Elec Eng & Comp Sci, vol. 20, pp. 25-46, Apr. 2012.
  17. N. J. Gordon, D. J. Salmond, and A. F. M. Smith, "Novel approach to nonlinear/non-gaussian Bayesian state estimation," IEEE-Proceeding-F, vol. 140, pp. 107-113, Oct. 1993.
  18. G. Grisetti, C. Stachniss, and W. Burgard, "Improved techniques for grid mapping with rao-blackwellized particle filters," Proc. of IEEE Trans. Robot, vol. 23, no. 1, pp. 34-46, Feb. 2007.
  19. X. Li, S. Jia, and W. Cui, "On sample diversity in particle filter based robot SLAM," Proc. of the 2011 IEEE Internatial Conference on Robotics and Biomimetics, Phuket pp. 1072- 1077, Dec. 2011.
  20. D. Napoleon and P. G. Lakshmi "An efficient K-means clustering algorithm for reducing time complexity using uniform distribution data points," IEEE Trendz in Information Sciences & Computing (TISC), pp. 42-45, Dec. 2010.
  21. M.-U.-S. Shameem, "An Efficient K-Means algorithm integrated with Jaccard distanc measure for document clustering," IEEE Conference on AH-ICI, pp. 1-6, Nov. 2009.
  22. 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. 205-257, Mar. 2008.

Cited by

  1. A Cloud-based Integrated Development Environment for Robot Software Development vol.21, pp.2, 2015,