Outdoor Self-Localization of a Mobile Robot Using Slow Feature Analysis

  • Benjamin Metka
  • Mathias Franzius
  • Ute Bauer-Wersing
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8226)


We apply slow feature analysis (SFA) to the problem of self-localization with a mobile robot. A similar unsupervised hierarchical model has earlier been shown to extract a virtual rat’s position as slowly varying features by directly processing the raw, high dimensional views captured during a training run. The learned representations encode the robot’s position, are orientation invariant and similar to cells in a rodent’s hippocampus.

Here, we apply the model to virtual reality data and, for the first time, to data captured by a mobile outdoor robot. We extend the model by using an omnidirectional mirror, which allows to change the perceived image statistics for improved orientation invariance. The resulting representations are used for the notoriously difficult task of outdoor localization with mean absolute localization errors below 6%.


Self-Localization SFA Mobile Robot Biomorphic System Omnidirectional Vision Outdoor Environment 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Földiak, P.: Learning invariance from transformation sequences. Neural Comput. 3, 194–200 (1991)CrossRefGoogle Scholar
  2. 2.
    Stone, J.V., Bray, A.: A learning rule for extracting spatio-temporal invariances. Network-Comp. Neural 6, 429–436 (1995)CrossRefzbMATHGoogle Scholar
  3. 3.
    Wiskott, L., Sejnowski, T.: Slow feature analysis: Unsupervised learning of invariances. Neural Comput. 14(4), 715–770 (2002)CrossRefzbMATHGoogle Scholar
  4. 4.
    Körding, K., Kayser, C., Einhäuser, W., König, P.: How are complex cell properties adapted to the statistics of natural scenes? J. Neurophysiol. 91(1), 206–212 (2004)CrossRefGoogle Scholar
  5. 5.
    Wyss, R., König, P., Verschure, P.: A model of the ventral visual system based on temporal stability and local memory. PLoS Biol. 4, 1–8 (2006)CrossRefGoogle Scholar
  6. 6.
    Berkes, P., Wiskott, L.: Slow feature analysis yields a rich repertoire of complex cell properties. J. Vision 5(6) (2005)Google Scholar
  7. 7.
    Milford, M., Schulz, R., Prasser, D., Wyeth, G., Wiles, J.: Learning spatial concepts from RatSLAM representations. Robot Auton Syst. 55(5), 403–410 (2007)CrossRefGoogle Scholar
  8. 8.
    Zito, T., Wilbert, N., Wiskott, L., Berkes, P.: Modular toolkit for data processing (mdp): a python data processing framework. Front Neuroinform 2(8) (2009)Google Scholar
  9. 9.
    Davison, A., Reid, I., Molton, N., Stasse, D.: MonoSLAM: Real-time single camera SLAM. IEEE Trans Pattern Anal. Mach. Int. 29(6), 1052–1067 (2007)CrossRefGoogle Scholar
  10. 10.
    Franzius, M., Sprekeler, H., Wiskott, L.: Slowness and sparseness lead to place, head-direction, and spatial-view cells. PLoS Comp. Biol. 3(8) (2007)Google Scholar
  11. 11.
    Bradski, G.: The OpenCV Library. Dr. Dobb’s Journal of Software Tools (2000)Google Scholar
  12. 12.
    Smith, A., Balakrishnan, H., Goraczko, M., Priyantha, N.: Tracking Moving Devices with the Cricket Location System. MobiSys (2004)Google Scholar
  13. 13.
    Jeffery, K., O’Keefe, J.: Learned interaction of visual and idiothetic cues in the control of place field orientation. Exp. Brain Res. 127(2), 151–161 (1999)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Benjamin Metka
    • 1
  • Mathias Franzius
    • 2
  • Ute Bauer-Wersing
    • 1
  1. 1.University of Applied Sciences FrankfurtFrankfurt am MainGermany
  2. 2.Honda Research Institute Europe GmbHOffenbachGermany

Personalised recommendations