Walk Calibration in a Four-legged Robot

  • Boyan Bonev
  • Miguel Cazorla
  • Humberto Martínez
Conference paper

5 Conclusions and future work

The use of walk calibration using machine learning proved to be feasible, as well as necessary, specially when changing the walking surface. The TeamChaos improved its maximum speed a 30% using simulated annealing. On the other hand, using multiple parameters sets allowed us to improve the speed response by fixing the discontinuities in the speed space. We obtained our best result using 2 sets of parameters. Moreover, the precise error measures enable the odometry system with more precise information about the motion uncertainity.

Calibrating the walk parameters for forward speed only is a good solution for the RoboCup domain. Using the infrastructure of our experiments, a study on a more complete calibration could be done, by calibrating simultaneously forward, lateral and rotational walking. This is not necessary in our domain and it would take much more time; still it is possible because of our instant speed measuring procedure. Finally, a calibration on curve lines could be considered, instead of separating calibration into three different walking types.


Simulated Annealing Speed Response Quadruped Robot Instant Speed Speed Interval 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    SONY (2005) Sony AIBO ERS7. Scholar
  2. 2.
    Team Chaos (2005) Team Chaos website. Scholar
  3. 3.
    B. Hengst, B. Ibbotson, Pham, P., and Sammut, C. (2002) Omnidirectional locomotion for quadruped robots. In RoboCup 2001.Google Scholar
  4. 4.
    Hafmar, H. and Lundin, J. (2002) Quadruped locomotion for football robots.Google Scholar
  5. 5.
    Wasik, Z. and Saffiotti, A. (2002) Robust color segmentation for the robocup domain. In IEEE Int. Conf. on Pattern Recognition (ICPR).Google Scholar
  6. 6.
    Kirkpatrick, S., Gelatt, C. D., and Vecchi, M. P. (1983) Optimization by simulated annealing. Science, no. 4598, pp. 671–680.MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Boyan Bonev
    • 1
  • Miguel Cazorla
    • 1
  • Humberto Martínez
    • 2
  1. 1.Robot Vision GroupUniversity of AlicanteAlicanteSpain
  2. 2.Departamento de Ingenierá de la Información y las ComunicacionesUniversidad de MurciaMurciaSpain

Personalised recommendations