Abstract
A new approach to evolutionary robotics is presented. Neural networks are abstracted and supplanted by a system of ordinary differential equations that govern the changes in controller outputs. The equations are evolved as trees using an evolutionary algorithm based on symbolic regression in genetic programming. Initial proof-of-concept experiments are performed using a simulated two-wheeled robot that must drive a straight line while wheel response properties vary. Evolved controllers demonstrate the ability to learn and adapt to a changing environment, as well as the ability to generalize and perform well in novel situations.
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
Federici, D., Downing, K.: Evolution and Development of a Multicellular Organism: Scalability, Resilience, and Neutral Complexification. Artificial Life 12, 381–409 (2006)
Floreano, D., Mondada, F.: Evolution of Plastic Neurocontrollers for Situated Agents. In: 4th International Conference on Simulation of Adaptive Behavior. MIT Press, MA (1996)
Poli, R., Langdon, W.B., Mcphee, N.F.: A Field Guide to Genetic Programming (2008), Published via http://lulu.com and freely available at http://www.gp-field-guide.org.uk
Soltoggio, A., Durr, P., Mattiussi, C., Floreano, D.: Evolving Neuromodulatory Topologies for Reinforcement Learning-like Problems. In: IEEE Congress on Evolutionary Computation, pp. 2471–2478. IEEE Press, Los Alamitos (2007)
Stanley, K.O., Miikkulainen, R.: Evolving Neural Networks Through Augmenting Topologies. Evolutionary Computation 10, 99–127 (2002)
Stanley, K.O.: Compositional Pattern Producing Networks: A Novel Abstraction of Development. Genetic Programming and Evolvable Machines Special Issue on Developmental Systems 8, 131–162 (2007)
Thangavelautham, J., D’Eleuterio, G.M.T.: A Coarse-Coding Framework for a Gene-Regulatory-Based Artificial Neural Tissue. In: Capcarrère, M.S., Freitas, A.A., Bentley, P.J., Johnson, C.G., Timmis, J. (eds.) ECAL 2005. LNCS (LNAI), vol. 3630, pp. 67–77. Springer, Heidelberg (2005)
Wieland, A.: Evolving Neural Network Controllers for Unstable Systems. In: Proceedings of the International Joint Conference on Neural Networks, pp. 667–673. IEEE Press, Los Alamitos (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Grouchy, P., D’Eleuterio, G.M.T. (2010). Supplanting Neural Networks with ODEs in Evolutionary Robotics. In: Deb, K., et al. Simulated Evolution and Learning. SEAL 2010. Lecture Notes in Computer Science, vol 6457. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17298-4_31
Download citation
DOI: https://doi.org/10.1007/978-3-642-17298-4_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17297-7
Online ISBN: 978-3-642-17298-4
eBook Packages: Computer ScienceComputer Science (R0)