Abstract
In this paper, we describe possible methods of solving two problems encountered in evolutionary robotics, while applying neuroevolutionary methods to evolve controllers for complex robotic tasks. The first problem is the large number of evaluations required to obtain a solution. We propose that this problem can be addressed by accelerating neuroevolutionary methods using a Kalman filter. The second problem is the difficulty of obtaining a desirable solution that results from the difficulty of defining an appropriate fitness function for a complex robotic task. The solution towards this problem is to apply the principles of behavior based systems to decompose the solution space into smaller subsolutions with lower number of intrinsic dimensions, and incrementally modify the fitness function. We present two case studies towards the solutions to the stated problems.
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
Altug, E., Ostrowski, J.P., Taylor, C.J.: Quadrotor control using dual camera visual feedback. In: Proceedings of the IEEE International Conference on Robotics and Automation, ICRA 2003, pp. 4294–4299 (2003)
Arkin, R.C.: Behaviour-Based Robotics. MIT Press, Massachusetts (1998)
Bongard, J.: Behavior chaining: Incremental behavior integration for evolutionary robotics. Artificial Life (2008)
Botvinick, M., Niv, Y., Barto, A.C.: Hierarchically organized behavior and its neural foundations: A reinforcement learning perspective. Cognition 113, 262–280 (2008)
Brooks, R.A.: A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation 2(1), 14–23 (1986)
Calabretta, R., Nolfi, S., Parisi, D., Wagner, G.P.: Duplication of modules facilitates the evolution of functional specialization. Artificial Life 6, 69–84 (2000)
Dürr, P., Mattiussi, C., Floreano, D.: Neuroevolution with analog genetic encoding. In: Proceedings of the 9th Conference on Parallel Problem Solving from Nature (PPSN IX), pp. 671–680 (2006)
Feldkamp, L.A., Puskorius, G.V.: Training controllers for robustness: multi-stream DEKF. In: IEEE International Conference on Neural Networks, pp. 2377–2382 (1994)
Gomez, F., Schmidhuber, J., Miikkulainen, R.: Accelerated neural evolution through cooperatively coevolved synapses. Journal of Machine Learning Research 9, 937–965 (2008)
Gomez, F.J., Miikkulainen, R.: Incremental evolution of complex general behavior. Adaptive Behavior 5, 317–342 (1997)
Gould, S., Vrba, E.: Exaptation; a missing term in the science of form. Paleobiology 8(1), 4–15 (1982)
Gray, J.E., Murray, W.: A derivation of an analytic expression for the tracking index for alpha-beta-gamma filter. IEEE Transactions on Aerospace and Electronic Systems 29(3), 1064–1065 (1993)
Gruau, F.: Neural Network Synthesis Using Cellular Encoding and the Genetic Algorithm. PhD thesis, Ecole Normale Superieure de Lyon, Laboratoire de l’Informatique du Parallelisme, France (January 1994)
Gruau, F., Whitley, D., Pyeatt, L.: A comparison between cellular encoding and direct encoding for genetic neural networks. In: Koza, J.R., Goldberg, D.E., Fogel, D.B., Riolo, R.L. (eds.) Genetic Programming: Proceedings of the First Annual Conference, Standford University, CA, USA, pp. 81–89. MIT Press, Cambridge (1996)
Gruau, F., Quatramaran, K.: Cellular encoding for interactive evolutionary robotics. Technical report, Amsterdam, The Netherlands (1996)
Hamel, T., Mahony, R., Lozano, R., Ostrowski, J.: Dynamic modelling and configuration stabilization for an X4-flyer. In: International Federation of Automatic Control Symposium, IFAC (2002)
Hansen, N., Ostermeier, A.: Completely derandomized self-adaptation in evolution strategies. Evolutionary Computation 9(2), 159–195 (2001)
Haykin, S.: Kalman Filering and Neural Networks. Wiley, Chichester (2001)
Heidrich-Meisner, V., Igel, C.: Neuroevolution strategies for episodic reinforcement learning. Journal of Algorithms (2009), doi:10.1016/j.jalgor.2009.04.002
Kalata, P.R.: Alpha-beta target tracking systems: A survey. In: American Control Conference, pp. 832–836 (1992)
Kassahun, Y., de Gea, J., Edgington, M., Metzen, J.H., Kirchner, F.: Accelerating neuroevolutionary methods using a Kalman filter. In: Proceedings of the 10th Genetic and Evolutionary Computation Conference, GECCO 2008, pp. 1397–1404 (2008)
Kassahun, Y., Edgington, M., Metzen, J.H., Sommer, G., Kirchner, F.: A common genetic encoding for both direct and indirect encodings of networks. In: Proceedings of the 9th Genetic and Evolutionary Computation Conference, GECCO 2007, pp. 1029–1036 (2007)
Kirchner, F.: Q-learning of complex behaviors on a six-legged walking machine. Journal of Robotics and Autonomous Systems 25, 256–263 (1998)
Lee, W., Hallam, J., Lund, H.: Learning complex robot behaviours by evolutionary computing with task decomposition. In: Learning Robots: 6th European Workshop, pp. 155–172 (1998)
Moriarty, D., Miikkulainen, R.: Efficient reinforcement learning through symbiotic evolution. Machine Learning 22, 11–33 (1996)
Mouret, J.-B., Doncieux, S.: Evolving modular neural-networks through exaptation. In: CEC 2009: Proceedings of the Eleventh conference on Congress on Evolutionary Computation, Piscataway, NJ, USA, pp. 1570–1577. IEEE Press, Los Alamitos (2009)
Ruck, D.W., Rogers, S.K., Kabrisky, M., Maybeck, P.S., Oxley, M.E.: Comparative analysis of backpropagation and the extended Kalman filter for training multilayer perceptrons. IEEE Transactions on Pattern Analysis and Machine Intelligence 14(6), 686–691 (1992)
Singhal, S., Wu, L.: Training multilayer perceptrons with the extended Kalman algorithm, pp. 133–140 (1989)
Stanley, K.O.: Efficient Evolution of Neural Networks through Complexification. PhD thesis, Artificial Intelligence Laboratory. The University of Texas at Austin., Austin, USA (August 2004)
Wieland, A.: Evolving controls for unstable systems. In: Proceedings of the International Joint Conference on Neural Networks, pp. 667–673 (1991)
Williams, R.J.: Training recurrent networks using the extended Kalman filter. In: Proceedings International Joint Conference on Neural Networks, pp. 241–246 (1992)
Ziemke, T., Bergfeldt, N., Buason, G., Susi, T., Svensson, H.: Evolving cognitive scaffolding and environment adaptation: a new research direction for evolutionary robotics. Connection Science 16(4), 339–350 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kassahun, Y., de Gea, J., Schwendner, J., Kirchner, F. (2011). On Applying Neuroevolutionary Methods to Complex Robotic Tasks. In: Doncieux, S., Bredèche, N., Mouret, JB. (eds) New Horizons in Evolutionary Robotics. Studies in Computational Intelligence, vol 341. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-18272-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-18272-3_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-18271-6
Online ISBN: 978-3-642-18272-3
eBook Packages: EngineeringEngineering (R0)