Advertisement

International Journal of Computer Vision

, Volume 74, Issue 3, pp 303–318 | Cite as

A Study of the Rao-Blackwellised Particle Filter for Efficient and Accurate Vision-Based SLAM

  • Robert SimEmail author
  • Pantelis Elinas
  • James J. Little
Article

Abstract

With recent advances in real-time implementations of filters for solving the simultaneous localization and mapping (SLAM) problem in the range-sensing domain, attention has shifted to implementing SLAM solutions using vision-based sensing. This paper presents and analyses different models of the Rao-Blackwellised particle filter (RBPF) for vision-based SLAM within a comprehensive application architecture. The main contributions of our work are the introduction of a new robot motion model utilizing structure from motion (SFM) methods and a novel mixture proposal distribution that combines local and global pose estimation. In addition, we compare these under a wide variety of operating modalities, including monocular sensing and the standard odometry-based methods. We also present a detailed study of the RBPF for SLAM, addressing issues in achieving real-time, robust and numerically reliable filter behavior. Finally, we present experimental results illustrating the improved accuracy of our proposed models and the efficiency and scalability of our implementation.

Keywords

vision slam robotics rao-blackwellised particle filters mixture proposal feature matching localization 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bailey, T., Nieto, J., and Nebot, E. 2006. Consistency of the FastSLAM algorithm. In Proc. IEEE International Conference on Robotics and Automation (ICRA), IEEE Press: Orlando, FL, pp. 424–429.Google Scholar
  2. Barfoot, T.D. 2005. Online visual motion estimation using FastSLAM with SIFT features. In Proc. IEEE/RSJ Conf. on Intelligent Robots and Systems. IEEE/RSJ, IEEE Press: Edmonton, AB, pp. 3076–3082.Google Scholar
  3. Beis, J.S. and Lowe, D.G. 1997. Shape indexing using approximate nearest-neighbour search in high-dimensional spaces. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, IEEE Press: Peurto Rico, pp. 1000–1006.Google Scholar
  4. Bolles, R.C. and Fischler, M.A. 1981. A RANSAC-based approach to model fitting and its application to finding cylinders in range data. In Proceedings of the Seventh Int. Joint Conf. on Artificial Intelligence. Vancouver, BC, Canada, pp. 637–643.Google Scholar
  5. Davison, A. 2003. Real-time simultaneous localisation and mapping with a single camera. In Proceedings of the IEEE Int. Conf. on Computer Vision. Nice, France, pp. 1403–1410.Google Scholar
  6. Dissanayake, G., Newman, P., Clark, S., Durrant-Whyte, H., and Csorba, M. 2001. A solution to the simultaneous localization and map building (SLAM) problem. IEEE Transactions on Robotics and Automation, 17(3):229–241.CrossRefGoogle Scholar
  7. Doucet, A., de Freitas, N., and Gordon, N. 2001. Sequential Monte Carlo in Practice. Springer-Verlag.Google Scholar
  8. Doucet, A., de Freitas, N., Murphy, K., and Russell, S. 2000. Rao-Blackwellised particle filtering for dynamic Bayesian networks. In Uncertainty in Artificial Intelligence, pp. 176–183.Google Scholar
  9. Eliazar, A.I. and Parr, R. 2004. DP-slam 2.0. In Proceedings of the 2004 IEEE International Conference on Robotics and Automation. IEEE Press: New Orleans, LA, vol. 2, pp. 1314–1320.Google Scholar
  10. Elinas, P., Sim, R., and Little, J.J. 2006. σSLAM: Stereo vision SLAM using the Rao-Blackwellised Particle Filter and a novel mixture proposal distribution. In Proceedings of the 2006 IEEE International Conference on Robotics and Automation. Orlando, FL, USA, pp. 1564–1570.Google Scholar
  11. Elinas, P. and Little, J.J. 2005. σMCL: Monte-Carlo localization for mobile robots with stereo vision. In Proceedings of Robotics: Science and Systems. Cambridge, MA, USA, pp. 373–380.Google Scholar
  12. Eustice, R., Singh, H., and Leonard, J. 2005. Exactly sparse delayed-state filters. In Proceedings of the 2005 IEEE International Conference on Robotics and Automation. Barcelona, Spain, pp. 2428–2435.Google Scholar
  13. Eustice, R., Singh, H., Leonard, J., Walter, M., and Ballard, R. 2005. Visually navigating the RMS Titanic with SLAM information filters. In Proceedings of Robotics Science and Systems. Cambridge, MA.Google Scholar
  14. Faugeras, O.D. 1993. Three-Dimensional Computer Vision: A Geometric Viewpoint. MIT Press.Google Scholar
  15. Folkesson, J., Jensfelt, P., and Christensen, H.I. 2005. Graphical SLAM using vision and the measurement subspace. In Int. Conf. on Intelligent Robotics and Systems (IROS). IEEE/JRS, Edmonton, Canada, pp. 325–330.Google Scholar
  16. Hähnel, D., Fox, D., Burgard, W., and Thrun, S. 2003. A highly efficient FastSLAM algorithm for generating cyclic maps of large-scale environments from raw laser range measurements. In Proc. of the Conference on Intelligent Robots and Systems (IROS), pp. 206–211.Google Scholar
  17. Hartley, R., and Zisserman, A. 2000. Multiple View Geometry in Computer Vision. Cambridge University Pr.: Cambridge, UK.zbMATHGoogle Scholar
  18. Karlsson, N., Di Bernardo, E., Ostrowski, J., Goncalves, L., Pirjanian, P., and Munich, M.E. 2005. The vSLAM algorithm for robust localization and mapping. In IEEE Int. Conf. on Robotics and Automation (ICRA). Barcelona, Spain, pp. 24–29.Google Scholar
  19. Kwok, N.M. and Dissanayake, G. 2004. An efficient multiple hypothesis filter for bearing-only SLAM. In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems. IEEE Press: Sendai, Japan, pp. 736–741.Google Scholar
  20. Leonard, J.J., and Durrant-Whyte, H.F. 1991. Simultaneous map building and localization for an autonomous mobile robot. In Proceedings of the IEEE Int. Workshop on Intelligent Robots and Systems. Osaka, Japan, pp. 1442–1447.Google Scholar
  21. Lowe, D.G. 1999. Object recognition from local scale-invariant features. In Proceedings of the Int. Conf. on Computer Vision. IEEE Press: Corfu, Greece, pp. 1150–1157.Google Scholar
  22. Lowe, D.G. 1991. Fitting parameterized three-dimensional models to images. IEEE Trans. Pattern Analysis Mach. Intell. (PAMI), 13(5):441–450.CrossRefMathSciNetGoogle Scholar
  23. Montemerlo, M. and Thrun, S. 2003. Simultaneous localization and mapping with unknown data association using FastSLAM. In Proceedings of the 2003 International Conference on Robotics and Automation, pp. 1985–1991.Google Scholar
  24. Montemerlo, M., Thrun, S., Koller, D., and Wegbreit, B. 2002. FastSLAM: A factored solution to the simultaneous localization and mapping problem. In Proceedings of the AAAI National Conf. on Artificial Intelligence. AAAI, Edmonton, pp. 593–598.Google Scholar
  25. Montemerlo, M., Thrun, S., Koller, D., and Wegbreit, B. 2003. FastSLAM 2.0: An improved particle filtering algorithm for simultaneous localization and mapping that provably converges. In Proceedings of the Eighteenth Int. Joint Conf. on Artificial Intelligence (IJCAI-03). Morgan Kaufmann Publishers: San Francisco, CA, pp. 1151–1156.Google Scholar
  26. Murphy, K. 1999. Bayesian map learning in dynamic environments. In 1999 Neural Information Processing Systems (NIPS), pp. 1015–1021.Google Scholar
  27. Paskin, M.A. 2003. Thin junction tree filters for simultaneous localization and mapping. In Proceedings of the Eighteenth Int. Joint Conf. on Artificial Intelligence (IJCAI-03). Morgan Kaufmann Publishers: San Francisco, CA, pp. 1157–1164.Google Scholar
  28. Se, S., Lowe, D.G., and Little, J.J. 2002. Mobile robot localization and mapping with uncertainty using scale-invariant visual landmarks. Int. J. Robotics Research, 21(8):735–758.CrossRefGoogle Scholar
  29. Sim, R., Elinas, P., Griffin, M., and Little, J.J. 2005. Vision-based SLAM using the Rao-Blackwellised particle filter. In Proceedings of Reasoning with Uncertainty in Robotics. Edinburgh, Scotland, pp. 9–16.Google Scholar
  30. Sim, R., Griffin, M., Shyr, A., and Little, J.J. 2005. Scalable real-time vision-based SLAM for planetary rovers. In IEEE IROS Workshop on Robot Vision for Space Applications. IEEE, IEEE Press: Edmonton, AB, pp. 16–21.Google Scholar
  31. Smith, R., Self, M., and Cheeseman, P. 1990. Estimating uncertain spatial relationships in robotics. In Autonomous Robot Vehicles, I.J. Cox and G.T. Wilfong (Eds.). Springer-Verlag, pp. 167–193.Google Scholar
  32. Arun, K.S., Huang, T.S., and Blostein, S.D. 1987. Least-squares fitting of two 3-d point sets. IEEE Trans. Pattern Anal. Mach. Intell., 9(5):698–700.CrossRefGoogle Scholar
  33. Solà, J., Monin, A., Devy, M., and Lemaire, T. 2005. Undelayed initialization in bearing only SLAM. In Proc. Int. Conf on Intelligent Robots and Systems (IROS). IEEE/RSJ, IEEE Press: Edmonton, AB, pp. 2751–2756.Google Scholar
  34. Stachniss, C., Grisetti, G., and Burgard, W. 2005. Recovering particle diversity in a Rao-Blackwellized particle filter for SLAM after actively closing loops. In Proc. of the IEEE Int. Conf. on Robotics & Automation (ICRA). Barcelona, Spain, pp. 667–672.Google Scholar
  35. Thrun, S., Liu, Y., Koller, D., Ng, A.Y., Ghahramani, Z., and Durrant-Whyte, H. 2004. Simultaneous localization and mapping with sparse extended information filters. International Journal of Robotics Research, 23(7–8):693–716.Google Scholar
  36. Thrun, S., Fox, D., and Burgard, W. 2000. Monte Carlo localization with mixture proposal distribution. In Proceedings of the 2000 National Conference of the American Association for Artificial Intelligence (AAAI), pp. 859–865.Google Scholar
  37. Zhang, Z., and Shan, Y. 2001. Incremental motion estimation through local bundle adjustment. Microsoft Research Technical Report MSR-TR-01-5.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2006

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of British ColumbiaVancouverUSA

Personalised recommendations