Advertisement

Outdoor Simultaneous Localisation and Mapping Using RatSLAM

  • David Prasser
  • Michael Milford
  • Gordon Wyeth
Part of the Springer Tracts in Advanced Robotics book series (STAR, volume 25)

Summary

In this paper an existing method for indoor Simultaneous Localisation and Mapping (SLAM) is extended to operate in large outdoor environments using an omnidirectional camera as its principal external sensor. The method, RatSLAM, is based upon computational models of the area in the rat brain that maintains the rodent’s idea of its position in the world. The system uses the visual appearance of different locations to build hybrid spatial-topological maps of places it has experienced that facilitate relocalisation and path planning. A large dataset was acquired from a dynamic campus environment and used to verify the system’s ability to construct representations of the world and simultaneously use these representations to maintain localisation.

Keywords

SLAM Omnidirectional Vision 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    A. Arleo, F. Smeraldi, S. Hug, and W. Gerstner. Place cells and spatial navigation based on vision, path integration, and reinforcement learning. Advances in Neural Information Processing Systems, 2001.Google Scholar
  2. 2.
    G. Dissanayake, P. Newman, S. Clark, H.F. Durrant-Whyte, and M. Csorba. A solution to the simultaneous localization and map building (SLAM) problem. Robotics and Automation, IEEE Transactions on, 17(3):229–241, 2001.CrossRefGoogle Scholar
  3. 3.
    M. O. Franz, B. Schölkopf, H. A. Mallot, and H. H. Bülthoff. Learning view graphs for robot navigation. Autonomous Robots, 5(1):111–125, 1998.zbMATHCrossRefGoogle Scholar
  4. 4.
    J. Košecká and F. Li. Vision based topological markov localization. In Proceedings International Conference on Robotics and Automation, volume 2, pages 1481–1486, 2004.Google Scholar
  5. 5.
    P. Lamon, A. Tapus, E. Glauser, N. Tomatis, and R. Siegwart. Environmental modeling with fingerprint sequences for topological global localization. In Proceedings of the International Conference on Intelligent Robots and Systems, volume 4, pages 3781–3786, 2003.Google Scholar
  6. 6.
    M. Milford, G. Wyeth, and D. Prasser. RatSLAM: a hippocampal model for simultaneous localization and mapping. In Proceedings of the International Conference on Robotics and Automation, volume 1, pages 403–408, 2004.Google Scholar
  7. 7.
    J. Nieto, J. Guivant, E. Nebot, and S. Thrun. Real time data association for FastSLAM. In Proceedings International Conference on Robotics and Automation, 2003.Google Scholar
  8. 8.
    D. Prasser, G. Wyeth, M. Milford, J. Roberts, and K. Usher. Experiments in outdoor operation of RatSLAM. In Proceedings of the 2004 Australasian Conference on Robotics and Automation. Canberra, 2004.Google Scholar
  9. 9.
    P.E. Rybski, F. Zacharias, and J.-F. Lett. Using visual features to build topological maps of indoor environments. In Proceedings International Conference on Robotics and Automation, volume 1, pages 850–855, 2003.Google Scholar
  10. 10.
    I. Ulrich and I. Nourbakhsh. Appearance-based place recognition for topological localization. In Proceedings of the IEEE International Conference on Robotics and Automation, volume 2, pages 1023–1029, 2000.Google Scholar
  11. 11.
    K. Usher, P. Ridley, and P. Corke. Visual servoing of a car-like vehicle-an application of omnidirectional vision. In Proceedings of the IEEE International Conference on Robotics and Automation, volume 3, pages 4288–4293, 2003.Google Scholar
  12. 12.
    J. Wolf, W. Burgard, and H. Burkhardt. Using an image retrieval system for vision-based mobile robot localization. In Proc. of the International Conference on Image and Video Retrieval (CIVR). 2002.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • David Prasser
    • 1
  • Michael Milford
    • 1
  • Gordon Wyeth
    • 1
  1. 1.School of Information Technology and Electrical EngineeringThe University of QueenslandAustralia

Personalised recommendations