Abstract
The search for variants of effective neural behavior is a major requirement for the identification of novel neuro-dynamical control principles. Evolutionary algorithms are successfully used to search for such controllers. But neuro-evolution tends to find similar, well performing solutions when run multiple times, instead of many, perhaps also weaker performing, but neuro-dynamically highly interesting variants. Furthermore, variants only develop by chance, so that a systematic exploration of different neural control strategies is difficult. With the ICONE method the search space can be shaped by so-called constraint masks (CM) to bias the evolving networks towards specific configurations. On the basis of an animat experiment we demonstrate that the number of evolved distinct variants can be significantly increased using different CMs.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
D’Ambrosio, D.B., Stanley, K.O.: A novel generative encoding for exploiting neural network sensor and output geometry. In: Lipson, H. (ed.) Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2007), pp. 974–981 (2007)
Floreano, D., Dürr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evolutionary Intelligence 1(1), 47–62 (2008)
Floreano, D., Husbands, P., Nolfi, S.: Evolutionary robotics. In: Siciliano, B., Khatib, O. (eds.) Springer Handbook of Robotics, pp. 1423–1451. Springer (2008)
Gomez, F.J.: Robust Non-Linear Control through Neuroevolution. PhD thesis, The University of Texas at Austin (2003)
Hornby, G., Lipson, H., Pollack, J.: Generative representations for the automated design of modular physical robots. IEEE Transactions on Robotics and Automation 19, 703–719 (2003)
Hülse, M., Wischmann, S., Pasemann, F.: Structure and function of evolved neuro-controllers for autonomous robots. Connection Science 16(4), 249–266 (2004)
Inden, B., Jin, Y., Haschke, R., Ritter, H.: Evolving neural fields for problems with large input and output spaces. Neural Networks 28, 24–39 (2012)
Kodjabachian, J., Meyer, J.: Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects. IEEE Transactions on Neural Networks 9(5), 796–812 (1998)
Lehman, J., Stanley, K.: Abandoning objectives: Evolution through the search for novelty alone. Evolutionary Computation 19(2), 189–223 (2011)
Mahfoud, S.W.: Niching methods for genetic algorithms. PhD Thesis. Department of Computer Science, University of Illinois at Urbana-Champaign (1995)
Meyer, J., Guillot, A.: Simulation of adaptive behavior in animats: Review and prospect. In: Meyer, J., Wilson, S. (eds.) From Animals to Animats 1, pp. 2–14 (1991)
Mouret, J., Doncieux, S.: Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity. In: Proceedings of the Eleventh Congress on Evolutionary Computation (CEC 2009), pp. 1161–1168 (2009)
Nolfi, S., Parisi, D.: Growing neural networks. Tech. Rep. PCIA-91-15, Institute of Psychology (1991)
Rempis, C.: Evolving Complex Neuro-Controllers with Interactively Constrained Neuro-Evolution. PhD thesis, to appear: University of Osnabrueck (2012)
Rempis, C., Pasemann, F.: An Interactively Constrained Neuro-Evolution Approach for Behavior Control of Complex Robots. In: Chiong, R., Weise, T., Michalewicz, Z. (eds.) Variants of Evolutionary Algorithms for Real-World Applications, vol. 87, pp. 305–341. Springer, Heidelberg (2012)
Rempis, C., Thomas, V., Bachmann, F., Pasemann, F.: NERD Neurodynamics and Evolutionary Robotics Development Kit. In: Ando, N., Balakirsky, S., Hemker, T., Reggiani, M., von Stryk, O. (eds.) SIMPAR 2010. LNCS (LNAI), vol. 6472, pp. 121–132. Springer, Heidelberg (2010)
Sareni, B., Krahenbuhl, L.: Fitness sharing and niching methods revisited. IEEE Transactions on Evolutionary Computation 2(3), 97–106 (1998)
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
Rempis, C., Pasemann, F. (2012). Evolving Variants of Neuro-Control Using Constraint Masks. In: Ziemke, T., Balkenius, C., Hallam, J. (eds) From Animals to Animats 12. SAB 2012. Lecture Notes in Computer Science(), vol 7426. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33093-3_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-33093-3_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33092-6
Online ISBN: 978-3-642-33093-3
eBook Packages: Computer ScienceComputer Science (R0)