Abstract
This paper outlines a system that allows a neural network, which is used to control a robot, to evolve in a structured but open-ended way. The final intention of the research is that, as the network develops, intelligence will eventually emerge. This is accomplished by placing the robot in a developing environment and allowing both this environment and the robot’s body form, sensors and actuators to become more complex and sophisticated as time passes. As this development takes place, neural network modules are added to the control system. The result is that the robot’s complexity and that of the neural network grows with its environment. Results are presented showing the system in operation on a simulated legged robot.
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.
References
Schaffer, J. D. et al: Combinations of Genetic Algorithms and Neural Networks: A Survey of the State of the Art. Proceedings of COGANN-92, IEEE Comp Soc Press (1992) 1–37
Vonk, E., Jain, L. C., Johnson, R. P.: Automatic Generation of Neural Network Architecture using Evolutionary Computation. World Scientific (1997)
de Garis, H.: CAM BRAIN: The evolutionary engineering of a billion neuron artificial brain by 2001 which grows / evolves at electronic speeds inside a cellular automata machine. Neuroinformatics and Neurocomputers (1995) 62–69
MacLeod, C., Maxwell, G.: Evolutionary Electronics. Practical Electronics, August (1999)
MacLeod, C., McMinn, D. et al: Evolution by Devolved Action: Towards the Evolution of Systems. In: Appendix B of McMinn, D.: Using Evolutionary Artificial Neural Networks to Design Hierarchical Animat Nervous Systems, PhD Thesis, The Robert Gordon University, Aberdeen, UK (2002)
Alberts, B., Bray, D. et al.: The Molecular Biology of the Cell. 3rd ed. Garland Publishing (1994)
Fritzsch, B.: Evolution of the Ancestral Vertebrate Brain. In: Arbib, M. A.: The Handbook of Brain Theory and Neural Networks, The MIT press, (1998) 373–376
MacLeod, C., Maxwell G. M.: Incremental Evolution in ANNs: Neural Nets which Grow. Artificial Intelligence Review. Kluwer, 16 (2001) 201–224
Gallinari, P.: Training of Modular Neural Net Syetems. In: Arbib, M. A. (ed): The Handbook of Brain Theory and Neural Networks, The MIT Press, (1998) 582–585
McMinn, D., Maxwell, G., MacLeod, C.: An Evolutionary Artificial Nervous System for Animat Locomotion. EANN 2000: Proceedings of the International Conference on Engineering Applications of Neural Networks, Kingston Upon Thames, UK (2000) 170–176
McMinn, D.: Using Evolutionary Artificial Neural Networks to Design Hierarchical Animat Nervous Systems. PhD Thesis, The Robert Gordon University, Aberdeen, UK (2002)
Guo-Jian, C.: Incremental Learning of Self-organising Variable Topology Neural Networks. Shaker Verlag, Aachen (2001)
McMinn, D., Maxwell, G., MacLeod, C.: Evolutionary Artificial Neural Networks for Quadruped Locomotion. Proceedings of the International Conference on Neural Networks ICANN 2002, Madrid, (2002) 789–794
Shigematsu, Y., Ichikawa, M., Matsumoto, G.: Reconstitution studies on brain computing with the neural network engineering. In: Ono, T., McNaughton, B., Molotchnikoff, S. Rolls, E., Nishijo, H. (Eds.): Perception, memory and emotion: frontiers in neuroscience. Elsevier, (1996) 581–599
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Muthuraman, S., Maxwell, G., MacLeod, C. (2003). The Evolution of Modular Artificial Neural Networks for Legged Robot Control. In: Kaynak, O., Alpaydin, E., Oja, E., Xu, L. (eds) Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003. ICANN ICONIP 2003 2003. Lecture Notes in Computer Science, vol 2714. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44989-2_58
Download citation
DOI: https://doi.org/10.1007/3-540-44989-2_58
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40408-8
Online ISBN: 978-3-540-44989-8
eBook Packages: Springer Book Archive