SVMs for Vibration-Based Terrain Classification

  • Christian Weiss
  • Matthias Stark
  • Andreas Zell
Part of the Informatik aktuell book series (INFORMAT)


When an outdoor mobile robot traverses different types of ground surfaces, different types of vibrations are induced in the body of the robot. These vibrations can be used to learn a discrimination between different surfaces and to classify the current terrain. Recently, we presented a method that uses Support Vector Machines for classification, and we showed results on data collected with a hand-pulled cart. In this paper, we show that our approach also works well on an outdoor robot. Furthermore, we more closely investigate in which direction the vibration should be measured. Finally, we present a simple but effective method to improve the classification by combining measurements taken in multiple directions.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Wilcox B. H.: Non-Geometric Hazard Detection for a Mars Microrover. Proc. AIAA Conf. on Intelligent Robots in Field, Factory, Service, Space. Houston, TX, pp. 675–684, 1994Google Scholar
  2. 2.
    Iagnemma K., Dubowsky S.: Terrain Estimation for High-Speed Rough-Terrain Autonomous Vehicle Navigation. Proc. SPIE Conf. on Unmanned Ground Vehicle Technology IV, 2002Google Scholar
  3. 3.
    Brooks C. A., Iagnemma K.: Vibration-Based Terrain Classification for Planetary Exploration Rovers. IEEE Trans. on Robotics, 21(6), pp. 1185–1191, 2005CrossRefGoogle Scholar
  4. 4.
    Sadhukhan D., Moore C: Online Terrain Estimation Using Internal Sensors. Proc. Florida Conf. on Recent Advances in Robotics, Boca Raton, FL, 2003Google Scholar
  5. 5.
    Sadhukhan D.: Autonomous Ground Vehicle Terrain Classification Using Internal Sensors. Masters Thesis, Dept. Mech. Eng., Florida State University, 2004Google Scholar
  6. 6.
    Weiss C., Fröhlich H., Zell, A.: Vibration-based Terrain Classification Using Support Vector Machines. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, Beijing, China, pp. 4429–4434, 2006Google Scholar
  7. 7.
    Stavens D., Hoffmann G., Thrun S.: Online Speed Adaptation Using Supervised Learning for High-Speed, Off-Road Autonomous Driving. Proc. Int. Joint Conf. on Artificial Intelligence, Hyderabad, India, 2007Google Scholar
  8. 8.
    Cortes C, Vapnik V.: Support Vector Networks. Machine Learning, 20, pp. 273–297, 1995zbMATHGoogle Scholar
  9. 9.
    Schölkopf B., Smola A. J.: Learning with Kernels. MIT Press, Cambridge, MA, 2002Google Scholar
  10. 10.
    Chang C. C, Lin C. J.: LIBSVM: A Library for Support Vector Machines. Software available at∼cjlin/libsvm, 2001

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Christian Weiss
    • 1
  • Matthias Stark
    • 1
  • Andreas Zell
    • 1
  1. 1.Department of Computer ScienceUniversity of TübingenTübingen

Personalised recommendations