Abstract
We present an example of the dynamical systems approach to learning and adaptation. Our goal is to explore how both control and learning can be embedded into a single dynamical system, rather than having a separation between controller and learning algorithm. First, we present our adaptive frequency Hopf oscillator, and illustrate how it can learn the frequencies of complex rhythmic input signals. Then, we present a controller based on these adaptive oscillators applied to the control of a simulated 4-degrees-of-freedom spring-mass hopper. By the appropriate design of the couplings between the adaptive oscillators and the mechanical system, the controller adapts to the mechanical properties of the hopper, in particular its resonant frequency. As a result, hopping is initiated and locomotion similar to the bound emerges. Interestingly, efficient locomotion is achieved without explicit inter-limb coupling, i.e. the only effective inter-limb coupling is established via the mechanical system and the environment. Furthermore, the self-organization process leads to forward locomotion which is optimal with respect to the velocity/power ratio.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Movies of the spring-mass hopper are, available at http://birg.epfl.ch
Open Dynamics Engine Documentation, available at http://ode.org
Blickhan, R., Full, R.J.: Similarity in multilegged locomotion: bouncing like a monopode. Journal of Comparative Physiology 173, 509–517 (1993)
Buchli, J., Ijspeert, A.J.: A simple, adaptive locmotion toy-system. In: Schaal, S., Ijspeert, A.J., Billard, A., Vijayakumar, S., Hallam, J., Meyer, J.A. (eds.) Proceedings SAB 2004. MIT Press, Cambridge (2004)
Buehler, M., Battaglia, R., Cocosco, R., Hawker, G., Sarkis, J., Yamazaki, K.: SCOUT: a simple quadruped that walks, climbs, and runs. In: Proceedings ICRA, vol. 2, pp. 1707–1712 (1998)
Cham, J.G., Karpick, J.K., Cutkosky, M.R.: Stride period adaptation of a biomimetic running hexapod. Int. J. of Robotics Research 23(2), 141–153 (2004)
Collins, J.J., Richmond, S.A.: Hard-wired central pattern generators for quadrupedal locomotion. Biological Cybernetics 71(5), 375–385 (1994)
de Lasa, M., Buehler, M.: Dynamic compliant quadruped walking. In: ICRA 2001, vol. 3, pp. 3153–3158 (2001)
Eguíluz, V.M., Ospeck, M., Choe, Y., Hudspeth, A.J., Magnasco, M.O.: Essential nonlinearities in hearing. Phys. Rev. Lett. 84(22), 5232–5235 (2000)
Fukuoka, Y., Kimura, H., Cohen, A.H.: Adaptive dynamic walking of a quadruped robot on irregular terrain based on biological concepts. The International Journal of Robotics Research 3-4, 187–202 (2003)
Full, R.J., Koditscheck, D.E.: Templates and anchors: neuromechanical hypotheses of legged locomotion on land. J. Exp. Biology 202, 3325–3332 (1999)
Geyer, H., Seyfarth, A., Blickhan, R.: Spring-mass running: simple approximate solution and application to gait stability. J. Theor. Biol. 232(3), 315–328 (2004)
Iida, F., Pfeifer, R.: Cheap rapid locomotion of a quadruped robot: Self-stabilization of bounding gait. In: Groen, F., et al. (eds.) Intelligent Autonomous Systems, vol. 8, pp. 642–649. IOS Press, Amsterdam (2004)
Kimura, H., Fukuoka, Y., Cohen, A.V.: Biologically inspired adaptive dynamic walking of a quadruped robot. In: From Animals to Animats 8. Proceedings SAB 2004, pp. 201–210. MIT Press, Cambridge (2004)
Michel, O.: Webots: Professional mobile robot simulation. Int. J. Adv. Robotic Systems 1(1), 39–42 (2004)
Nishii, J.: A learning model for oscillatory networks. Neural Networks 11(2), 249–257 (1998)
Raibert, M., Hodgins, J.K.: Biol. Neural Networks in Invertebrate Neuroethology and Robotics. chapter Legged Robots, pp. 319–354. Academic Press, London (1993)
Righetti, L., Buchli, J., Ijspeert, A.J.: Dynamic Hebbian learning for adaptive frequency oscillators. Physica D (2005) (submitted)
Taga, G.: A model of the neuro-musculo-skeletal system for anticipatory adjustment of human locomotion during obstacle avoidance. Biol. Cybernetics 78, 9–17 (1998)
Tsuchiya, K., Aoi, S., Tsujita, K.: Locomotion control of a multi-legged locomotion robot using oscillators. In: 2002 IEEE Intl. Conf. SMC, vol. 4 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Buchli, J., Righetti, L., Ijspeert, A.J. (2005). A Dynamical Systems Approach to Learning: A Frequency-Adaptive Hopper Robot. In: Capcarrère, M.S., Freitas, A.A., Bentley, P.J., Johnson, C.G., Timmis, J. (eds) Advances in Artificial Life. ECAL 2005. Lecture Notes in Computer Science(), vol 3630. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11553090_22
Download citation
DOI: https://doi.org/10.1007/11553090_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28848-0
Online ISBN: 978-3-540-31816-3
eBook Packages: Computer ScienceComputer Science (R0)