Abstract
In this paper a novel method for car racing controller learning is proposed. Car racing simulation is an active research field where new advances in aerodynamics, consumption and engine power are modelled and tested. The proposed approach is based on Neural Networks that learn the driving behaviour of other rule-based bots. Additionally, the resulted neural-networks controllers are evolved in order to adapt and increase their performance to a given racing track using genetic algorithms. The proposed bots are implemented and tested on several tracks of the open racing car simulator (TORCS) providing smoother driving behaviour than the corresponding rule-based bots and increased performance using the evolutionary adaptation.
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
Torcs the open race car simulator, http://torcs.sourceforge.net/
Petrakis, S., Tefas, A.: Neural Networks Training for Weapon Selection in First-Person Shooter Games. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds.) ICANN 2010, Part III. LNCS, vol. 6354, pp. 417–422. Springer, Heidelberg (2010)
Laird, J.E., Van Lent, M.: Human-level AI’s Killer Application: Interactive Computer Games. In: Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence, pp. 1171–1178 (2000)
Onieva, E., Pelta, D.A., Alonso, J., Milanés, V., Pérez, J.: A modular parametric architecture for the TORCS racing engine. In: Proceedings of the 5th International Conference on Computational Intelligence and Games (CIG 2009), pp. 256–262. IEEE Press, Piscataway (2009)
Haykin, S.S.: Neural networks and learning machines, 3rd edn. Multi Layer Perceptron, pp. 152–258 (2008)
Hecht-Nielsen, R.: Theory of back-propagation neural network. In: Proc. of the Int. Conf. of Neural Networks I, pp. 593–611 (1989)
Robot auto racing simulator (2006), http://torcs.sourceforge.net
Stanley, K., Kohl, N., Sherony, R., Miikkulainen, R.: Neuroevolution of an automobile crash warning system. In: Genetic and Evolutionary Computation Conference, CECCO 2006, pp. 1977–1984 (2006)
Martin, B., Butz, V., Lonneker, T.D.: Optimized Sensory-motor Couplings plus Strategy Extensions for the TORCS car Racing Challenge. In: IEEE Symposium on Computational Intelligence and Games, CIG 2009, pp. 317–324 (2009)
Cardamone, L., Loiacono, D., Lanzi, P.L.: Applying cooperative coevolution to compete in the 2009 TORCS Endurance World Championship. In: Evolutionary Computation (CEC), pp. 1–8. IEEE (2010)
Perez, D., Saez, Y., Recio, G., Isasi, P.: Evolving a rule system controller for automatic driving in a car racing competition. In: Symposium on Computational Intelligence and Games (CIG), pp. 336–342. IEEE (2009)
Holland, J.H.: Adaptation in Natural and Artificial Systems, 2nd edn. MIT Press, Cambridge (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Galanopoulos, D., Athanasiadis, C., Tefas, A. (2012). Evolutionary Optimization of a Neural Network Controller for Car Racing Simulation. In: Maglogiannis, I., Plagianakos, V., Vlahavas, I. (eds) Artificial Intelligence: Theories and Applications. SETN 2012. Lecture Notes in Computer Science(), vol 7297. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-30448-4_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-30448-4_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-30447-7
Online ISBN: 978-3-642-30448-4
eBook Packages: Computer ScienceComputer Science (R0)