Facilitating Controller Evolution in Morpho-functional Machines — A Bipedal Case Study
Simulations of bipedal walking showed that the evolution of stable gaits can be greatly facilitated by harnessing design solutions inspired by those of biological organisms.
Three such areas are addressed in this paper: a) the use of passive dynamics such as free-swinging lower legs, knee caps and springy ankles, b) proportional derivative controllers (or their variants) as actuators, and c) a modular, specifically coupled neural controller architecture.
It is shown that an appropriate implementation of these components greatly improves the speed of evolution – stable straight line walking is typically achieved in substantially less than 100 generations. Moreover, compared to earlier experiments, the quality of the solutions arrived at is more satisfying with respect to their resemblance to human body dynamics during walking.
KeywordsCentral Pattern Generator Proportional Integral Derivative Body Dynamic Proportional Derivative Controller Neural Controller
Unable to display preview. Download preview PDF.
-  Mitchell, M. (1996) An Introduction to Genetic Algorithms, MIT Press.Google Scholar
-  Schaffer, J., Whitley, D., and Eschelman, L. (1992) Combinations of genetic algorithms and neural networks: A survey of the state of the art. In Whitley, D. and Schaffer, J. (eds.), Combinations of Genetic Algorithms and Neural Networks. IEEE Computer Society Press.Google Scholar
-  Reeve, R. (1999) Generating walking behaviours in legged robots, PhD Thesis, University of Edinburgh.Google Scholar
-  Ijspeert, A., Hallam, J., Willshaw, D., (1998) From Lampreys to Salamanders: Evolving Neural Controllers for Swimming and Walking, From Animals to Animats, Proceedings of the Fifth International Conferenc of The Society for Adaptive Behaviour (SAB98), Prifer, R. et al. (eds.), pp 390–399, MIT Press.Google Scholar
-  Reil, T. Unpublished.Google Scholar
-  Jakobi, N. (1998) Running Across the Reality Gap: Octopod Locomotion Evolved in a Minimal Simulation, in Husbands, P., Meyer, J. (eds.), Lecture Notes in Computer Science - Evolutionary Robotics, pp. 39–58, Springer Verlag.Google Scholar
- 8.Bachmann, R.J., Nelson, G.M., Flannigan, W.C., Quinn, R.D., Watson, J.T., Tryba, A.K., Ritzmann, R.E., (1997) Construction of a cockroach-like hexapod robot, Proceedings of the Eleventh VPI & SU Symposium on Structural Dynamics and Control: 1997 May 12–14, Blacksburg, Virginia: Virginia Polytechnic Institute and State University: 647–654.Google Scholar
-  Reil, T. (1999) Artificial Evolution of Neural Controllers In a Real-time Physics Environment, MSc Thesis, University of Sussex.Google Scholar
-  Reil, T., Husbands, P. (2001) Evolution of Central Pattern Generators for Bipedal walking in a Real-time Physics Environment, IEEE Transactions on Evolutionary Computation, under review.Google Scholar
-  Ogo, K., Ganse, A., Kato, L., (1980) Dynamic walking of biped walking machine aiming at completion of steady walking. Third symposium on Theory and Practice of Robots and Manipulators, Elsevier Scientific Publishing.Google Scholar
-  Kato, T., Takanishi, A., Jishikawa, H., Kato, I., (1983) The realization of the quasi-dynamic walking by the biped walking machine. Fourth Symposium on Theory and Practice of Robots and Manipulators, Polish Scientific Publishers.Google Scholar
-  Takanishi, A., Tochizawa, M., Karaki, H., Kato, I., (1989) Dynamic biped walking stabilized with optimal trunk and waist motion, IEEE/RSJ International Workshop on Intelligent Robots and Systems ’89, pp. 187–192.Google Scholar
- 15.Miura, H., Shimoyama, I. (1984) Dynamic Walk of a Biped, International Journal of Robotics Research 3: 30–74.Google Scholar
-  Honda P3 Humanoid Robot, http://wrorld.Honda.com/robot/.Google Scholar
-  Berns, K. (2000), The Walking Machine Catalogue, http://www.fzi.de/divisions/ipt/WMC/preface/preface.html Google Scholar
- 20.Pratt, J. (2000), Exploiting Inherent Robustness and Natural Dynamics in the Control of Bipedal Walking Robots. Ph.D. Thesis, Computer Science Department, Massachusetts Institute of Technology, Cambridge, Massachusetts.Google Scholar
- [PRATT_VM] Pratt, J., Dilworth, P., Pratt, G (1997), Virtual Mode Control of a ipedal Walking Robot, Proceedings of the IEEE International Conference on obotics and Automation (ICRA ’97), Albuquerque, NM.Google Scholar
- 21.Rendel, M. (2001) Undegraduate Project Thesis, Biological Sciences, University of Oxford, Oxford.Google Scholar
-  http://www.mathengine.com Google Scholar
-  Hillis, W. D. (1992) Co-evolving parasites improves simulated evolution as an optimization procedure. In C. Langton et al. (eds.) Artificial Life II, Addison-Wesley, pp. 313–324.Google Scholar
-  Adolfsson, J., Dankowicz, and A. Nordmark (1998) 3-d stable gait in passive bipedal mechanisms, Proceedings of 357 Euromech, 1998.Google Scholar
-  Garcia, M., Ruina, A., Coleman, M. and A. Chatterjee (1996) Passive-dynamic Models of Human Gait, Engineering Foundation Conference on Biomechanics and Neural Control of Human Movement, Mt. Sterling, Ohio, June 1–6.Google Scholar
-  Pratt, J. E., Pratt, G. A. (1999) Exploiting Natural Dynamics in the Control of a 3D Bipedal Walking Simulation, International Conference on Climbing and Walking Robots (CLAWAR99), Portsmouth, UK, September 1999.Google Scholar
- 29.Duysens, F., Clarac, F., Cruse, H. (2000) Load-Regulating Mechanisms in Gait and Posture: Comparative Aspects, Physiological Reviews 80(1): 83–133.Google Scholar
-  Kandel, E. R., Schwartz, J. H., Jessell, T. M., (1991) Principles of Neural Science (3rd edition), Elsevier.Google Scholar
- 34.Lloyd, D.P.C. (1946) Integrative pattern of excitation an inhibition in two-neuron reflex arcs, Journal of Neurophysiology 9: 439–444.Google Scholar