Abstract
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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Aloimonos, J., Weiss, I., Bandopadhay, A.: Active vision. International Journal of Computer Vision 1(4), 333–356 (1987)
Bajcsy, R.: Active perception. Proceedings of the IEEE 76, 966–1005 (1988)
Ballard, D.H.: Animate vision. Artificial Intelligence 48(1), 57–86 (1991)
Hancock, P.J.B., Baddeley, R.J., Smith, L.S.: The principal components of natural images. Network 3, 61–70 (1992)
Floreano, D., Kato, T., Marocco, D., Sauser, E.: Coevolution of active vision and feature selection. Biological Cybernetics 90(3), 218–228 (2004)
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)
Seara, J.F., Schmidt, G.: Intelligent gaze control for vision-guided humanoid walking: methodological aspects. Robotics and Autonomous Systems 48(4), 231–248 (2004)
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)
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)
Floreano, D., Suzuki, M., Mattiussi, C.: Active vision and receptive field development in evolutionary robots. Evolutionary Computation 13(4), 527–544 (2005)
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)
Elman, J.: Finding structure in time. Cognitive Science 14, 179–211 (1990)
Hinton, G.E., Sejnowski, T.J.: Unsupervised Learning. The MIT Press, Cambridge (1999)
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)
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)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)
Mattiussi, C., Floreano, D.: Analog genetic encoding for the evolution of circuits and networks. IEEE Transactions on Evolutionary Computation 11(5), 596–607 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Suzuki, M., Gritti, T., Floreano, D. (2009). Active Vision for Goal-Oriented Humanoid Robot Walking. In: Sendhoff, B., Körner, E., Sporns, O., Ritter, H., Doya, K. (eds) Creating Brain-Like Intelligence. Lecture Notes in Computer Science(), vol 5436. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-00616-6_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-00616-6_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-00615-9
Online ISBN: 978-3-642-00616-6
eBook Packages: Computer ScienceComputer Science (R0)