A General Classifier of Whisker Data Using Stationary Naive Bayes: Application to BIOTACT Robots

  • Nathan F. Lepora
  • Charles W. Fox
  • Mat Evans
  • Ben Mitchinson
  • Asma Motiwala
  • J. Charlie Sullivan
  • Martin J. Pearson
  • Jason Welsby
  • Tony Pipe
  • Kevin Gurney
  • Tony J. Prescott
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6856)

Abstract

A general problem in robotics is how to best utilize sensors to classify the robot’s environment. The BIOTACT project (BIOmimetic Technology for vibrissal Active Touch) is a collaboration between biologists and engineers that has led to many distinctive robots with artificial whisker sensing capabilities. One problem is to construct classifiers that can recognize a wide range of whisker sensations rather than constructing different classifiers for specific features. In this article, we demonstrate that a stationary naive Bayes classifier can perform such a general classification by applying it to various robot experiments. This classifier could be a key component of a robot able to learn autonomously about novel environments, where classifier properties are not known in advance.

Keywords

BIOTACT Active touch Whiskers Bayes’ rule Classifier 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bar-Cohen, Y.: Biomimetics - using nature to inspire human innovation. Bioinspiration & Biomimetics 1, 1 (2006)CrossRefGoogle Scholar
  2. 2.
    BIOTACT consortium, http://www.biotact.org
  3. 3.
    Evans, M., Fox, C., Pearson, M., Prescott, T.: Spectral Template Based Classification of Robotic Whisker Sensor Signals in a Floor Texture Discrimination Task. In: Proceedings TAROS 2009, pp. 19–24 (2009)Google Scholar
  4. 4.
    Evans, M., Fox, C., Prescott, T.: Tactile discrimination using template classifiers: Towards a model of feature extraction in mammalian vibrissal systems. In: Doncieux, S., Girard, B., Guillot, A., Hallam, J., Meyer, J.-A., Mouret, J.-B. (eds.) SAB 2010. LNCS, vol. 6226, pp. 178–187. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  5. 5.
    Fend, M.: Whisker-based texture discrimination on a mobile robot. Advances in Artificial Life, 302–311 (2005)Google Scholar
  6. 6.
    Fend, M., Bovet, S., Yokoi, H., Pfeifer, R.: An active artificial whisker array for texture discrimination. In: Proc. IEEE/RSJ Int. Conf. Intel. Robots and Systems, IROS 2003, vol. 2 (2003)Google Scholar
  7. 7.
    Fox, C.W., Mitchinson, B., Pearson, M.J., Pipe, A.G., Prescott, T.J.: Contact type dependency of texture classification in a whiskered mobile robot. Autonomous Robots 26(4), 223–239 (2009)CrossRefGoogle Scholar
  8. 8.
    Hipp, J., Arabzadeh, E., Zorzin, E., Conradt, J., Kayser, C., Diamond, M., Konig, P.: Texture signals in whisker vibrations. J. Neurophysiol. 95(3), 1792 (2006)CrossRefGoogle Scholar
  9. 9.
    Kim, D., Moller, R.: Biomimetic whiskers for shape recognition. Robotics and Autonomous Systems 55(3), 229–243 (2007)CrossRefGoogle Scholar
  10. 10.
    Lepora, N., Evans, M., Fox, C., Diamond, M., Gurney, K., Prescott, T.: Naive Bayes texture classification applied to whisker data from a moving robot. In: Proc. IEEE World Congress on Comp. Int., WCCI 2010 (2010)Google Scholar
  11. 11.
    Lepora, N., Pearson, M., Mitchinson, B., Evans, M., Fox, C., Pipe, A., Gurney, K., Prescott, T.: Naive Bayes novelty detection for a moving robot with whiskers. In: Proc. IEEE Int. Conf. on Robotics and Biomimetics, ROBIO 2010 (2010)Google Scholar
  12. 12.
    Pearson, M.J., Gilhespy, I., Melhuish, C., Mitchinson, B., Nibouche, M., Pipe, A.G., Prescott, T.J.: A biomimetic haptic sensor. International Journal of Advanced Robotic Systems 2(4), 335–343 (2005)CrossRefGoogle Scholar
  13. 13.
    Prescott, T.: Vibrissal behavior and function. Scholarpedia (in press)Google Scholar
  14. 14.
    Prescott, T., Pearson, M., Mitchinson, B., Sullivan, J., Pipe, A.: Whisking with robots from rat vibrissae to biomimetic technology for active touch. IEEE Robotics and Automation Magazine 16(3), 42–50 (2009)CrossRefGoogle Scholar
  15. 15.
    Solomon, J., Hartmann, M.: Biomechanics: Robotic whiskers used to sense features. Nature 443(7111), 525 (2006)CrossRefGoogle Scholar
  16. 16.
    Solomon, J., Hartmann, M.: Artificial whiskers suitable for array implementation: Accounting for lateral slip and surface friction. IEEE Transactions on Robotics 24(5), 1157–1167 (2008)CrossRefGoogle Scholar
  17. 17.
    Sullivan, J., Mitchinson, B., Pearson, M., Evans, M., Lepora, N., Fox, C., Melhuish, C., Prescott, T.: Tactile Discrimination using Active Whisker Sensors. IEEE Sensors 99, 1 (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Nathan F. Lepora
    • 1
  • Charles W. Fox
    • 1
  • Mat Evans
    • 1
  • Ben Mitchinson
    • 1
  • Asma Motiwala
    • 1
  • J. Charlie Sullivan
    • 2
  • Martin J. Pearson
    • 2
  • Jason Welsby
    • 2
  • Tony Pipe
    • 2
  • Kevin Gurney
    • 1
  • Tony J. Prescott
    • 1
  1. 1.Adaptive Behaviour Research Group, Department of PsychologyUniversity of SheffieldSheffieldUK
  2. 2.Bristol Robotics LaboratoryBristolUK

Personalised recommendations