Creating Brain-Like Intelligence pp 303-313

Part of the Lecture Notes in Computer Science book series (LNCS, volume 5436) | Cite as

Active Vision for Goal-Oriented Humanoid Robot Walking

  • Mototaka Suzuki
  • Tommaso Gritti
  • Dario Floreano


Complex visual tasks may be tackled with remarkably simple neural architectures generated by a co-evolutionary process of active vision and feature selection. This hypothesis has recently been tested in several robotic applications such as shape discrimination, car driving, indoor/outdoor navigation of a wheeled robot. Here we describe an experiment where this hypothesis is further examined in goal-oriented humanoid bipedal walking task. Hoap-2 humanoid robot equipped with a primitive vision system on its head is evolved while freely interacting with its environment. Unlike wheeled robots, bipedal walking robots are exposed to largely perturbed visual input caused by their own walking dynamics. We show that evolved robots are capable of coping with the dynamics and of accomplishing the task by means of active, efficient camera control.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Aloimonos, J., Weiss, I., Bandopadhay, A.: Active vision. International Journal of Computer Vision 1(4), 333–356 (1987)CrossRefGoogle Scholar
  2. 2.
    Bajcsy, R.: Active perception. Proceedings of the IEEE 76, 966–1005 (1988)CrossRefGoogle Scholar
  3. 3.
    Ballard, D.H.: Animate vision. Artificial Intelligence 48(1), 57–86 (1991)CrossRefGoogle Scholar
  4. 4.
    Hancock, P.J.B., Baddeley, R.J., Smith, L.S.: The principal components of natural images. Network 3, 61–70 (1992)CrossRefGoogle Scholar
  5. 5.
    Floreano, D., Kato, T., Marocco, D., Sauser, E.: Coevolution of active vision and feature selection. Biological Cybernetics 90(3), 218–228 (2004)CrossRefPubMedGoogle Scholar
  6. 6.
    Kagami, S., Nishiwaki, K., Kuffner, J., Kuniyoshi, Y., Inaba, M., Inoue, H.: Online 3D vision, motion planning and bipedal locomotion control. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2557–2562 (2002)Google Scholar
  7. 7.
    Seara, J.F., Schmidt, G.: Intelligent gaze control for vision-guided humanoid walking: methodological aspects. Robotics and Autonomous Systems 48(4), 231–248 (2004)CrossRefGoogle Scholar
  8. 8.
    Sabe, K., Fukuchi, M., Gutmann, J.S., Ohashi, T., Kawamoto, K., Yoshigahara, T.: Obstacle avoidance and path planning for humanoid robots using stereo vision. In: Proceedings of IEEE International Conference on Robotics and Automation, pp. 592–597 (2004)Google Scholar
  9. 9.
    Suzuki, M., Floreano, D., Di Paolo, E.A.: The contribution of active body movement to visual development in evolutionary robots. Neural Networks 18(5/6), 656–665 (2005)CrossRefPubMedGoogle Scholar
  10. 10.
    Floreano, D., Suzuki, M., Mattiussi, C.: Active vision and receptive field development in evolutionary robots. Evolutionary Computation 13(4), 527–544 (2005)CrossRefPubMedGoogle Scholar
  11. 11.
    Suzuki, M., Floreano, D.: Evolutionary active vision toward three dimensional landmark-navigation. In: Nolfi, S., Baldassarre, G., Calabretta, R., Hallam, J.C.T., Marocco, D., Meyer, J.-A., Miglino, O., Parisi, D. (eds.) SAB 2006. LNCS, vol. 4095, pp. 263–273. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  12. 12.
    Elman, J.: Finding structure in time. Cognitive Science 14, 179–211 (1990)CrossRefGoogle Scholar
  13. 13.
    Hinton, G.E., Sejnowski, T.J.: Unsupervised Learning. The MIT Press, Cambridge (1999)Google Scholar
  14. 14.
    Takanishi, A., Takeya, T., Karaki, H., Kumeta, M., Kato, I.: A control method for dynamic walking under unknown external force. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, Tsuchiura, Japan, pp. 795–801 (1990)Google Scholar
  15. 15.
    Reil, T., Husbands, P.: Evolution of central pattern generators for bipedal walking in a real-time physics environment. IEEE Transactions on Evolutionary Computation 6(2), 159–168 (2002)CrossRefGoogle Scholar
  16. 16.
    Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)CrossRefPubMedGoogle Scholar
  17. 17.
    Mattiussi, C., Floreano, D.: Analog genetic encoding for the evolution of circuits and networks. IEEE Transactions on Evolutionary Computation 11(5), 596–607 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Mototaka Suzuki
    • 1
  • Tommaso Gritti
    • 2
  • Dario Floreano
    • 3
  1. 1.Mahoney-Keck Center for Brain & Behavior ResearchColumbia University Medical CenterNew YorkUSA
  2. 2.Video Processing & AnalysisPhilips ResearchEindhovenThe Netherlands
  3. 3.Laboratory of Intelligent SystemsEcole Polytechnique Fédérale de Lausanne (EPFL)LausanneSwitzerland

Personalised recommendations