Abstract
This study follows a recent investigation on evolutionary training of counter-propagation neural-networks for multi-objective robot navigation in various environments. Here, in contrast to the original study, the training of the counter-propagation networks is done using an improved two-phase algorithm to achieve tuned weights for both classification of inputs and the control function. The proposed improvement concerns the crossover operation among the networks, which requires special attention due to the classification layer. The numerical simulations, which are reported here, suggest that both the current and original algorithms are superior to the classical approach of using a feed-forward network. It is also observed that the current version has better convergence properties as compared with the original one.
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
Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.A.: A Fast and Elitist Multi Objective Genetic Algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)
Floreano, D., Mondada, F.: Evolution of Homing Navigation in a Real Mobile Robot. Systems, Man and Cybernetics, Part B 26(3), 396–407 (1996)
Grossberg, S.: Studies of Mind and Brain: Neural Principles of Learning, Perception, Development, Cognition, and Motor Control, SERBIULA, Venezuela (1982)
Han, S.J., Oh, S.Y.: An Optimized Modular Neural Network Controller Based on Environment Classification and Selective Sensor Usage for Mobile Robot Reactive Navigation. Neural Comput. Appl. 17(2), 161–173 (2008)
Hecht-Nielsen, R.: Counterpropagation Networks. Applied Optics 26(23), 4979–4984 (1987)
Israel, S., Moshaiov, A.: Bootstrapping Aggregate Fitness Selection with Evolutionary Multi-objective Optimization. In: Coello, C.A.C., Cutello, V., Deb, K., Forrest, S., Nicosia, G., Pavone, M. (eds.) PPSN 2012, Part II. LNCS, vol. 7492, pp. 52–61. Springer, Heidelberg (2012)
Kohonen, T.: Self-Organizing Feature Maps and Abstractions. In: 3rd Int. Conf. on Artificial Intelligence and Information-Control Systems of Robots, pp. 39–45 (1984)
Moshaiov, A., Ashram-Wittenberg, A.: Multi-objective Evolution of Robot Neuro-Controllers. In: CEC 2009, Proceedings of the 11th Conference on Congress on Evolutionary Computation, pp. 1093–1100. IEEE Press, Piscataway (2009)
Moshaiov, A., Zadok, M.: Evolution of CPN Controllers for Multi-objective Robot Navigation in Various Environments. In: Proc. of the Int. Workshop on Evolutionary and Reinforcement Learning for Autonomous Robot Systems, ERLARS (2012)
Mouret, J.B., Doncieux, S.: Overcoming the Bootstrap Problem in Evolutionary Robotics using Behavioral Diversity. In: CEC 2009, Proceedings of the 11th Conference on Congress on Evolutionary Computation, pp. 1161–1168. IEEE Press, Piscataway (2009)
Yao, X.: Evolving Artificial Neural Networks. Proc. IEEE 87(9), 1423–1447 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Moshaiov, A., Zadok, M. (2013). Evolving Counter-Propagation Neuro-controllers for Multi-objective Robot Navigation. In: Esparcia-Alcázar, A.I. (eds) Applications of Evolutionary Computation. EvoApplications 2013. Lecture Notes in Computer Science, vol 7835. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37192-9_59
Download citation
DOI: https://doi.org/10.1007/978-3-642-37192-9_59
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37191-2
Online ISBN: 978-3-642-37192-9
eBook Packages: Computer ScienceComputer Science (R0)