Abstract
In the field of evolutionary robotics artificial neural networks are often used to construct controllers for autonomous agents, because they have useful properties such as the ability to generalize or to be noise-tolerant. Since the process to evolve such controllers in the real-world is very time-consuming, one usually uses simulators to speed up the evolutionary process. By doing so a new problem arises: The controllers evolved in the simulator show not the same fitness as those in the real-world. A gap between the simulated and real environments exists. In order to alleviate this problem we introduce the concept of neuromodulators, which allows to evolve neural networks which can adjust not only the synaptic weights, but also the structure of the neural network by blocking and/or activating synapses or neurons. We apply this concept to a peg-pushing problem for K hepera ™ and compare our method to a conventional one, which evolves directly the synaptic weights. Simulation and real experimental results show that the proposed approach is highly promising.
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
Floreano94. Floreano, D. and Mondada, F. (1994). Automatic creation of an autonomous agent: Genetic evolution of a neural-network driven robot, Proc. of the 3rd International Conference on Simulation of Adaptive Behavior, MIT Press, pp.421–430
Floreano96. Floreano, D. and Mondada, F. (1996). Evolution of Plastic Neurocontrollers for Situated Agents, From animals to animats 4: Proc. of the 4rd International Conference on Simulation of Adaptive Behavior, MIT Press, pp.401–411
Nolfi97. Nolfi, S. Parisi, D. (1997). Learning to adapt to changing environments in evolving neural networks, Adaptive Behavior, 5-1, pp.75–98
Reynolds94. Reynolds, C. W. (1994). An Evolved, Vision-Based Model of Obstacle Avoidance Behavior, ARTIFICIALL IFE III, pp.327–346
Jacobi95. Jacobi, N. Husbands, P. and Hervey, I. (1995). Noise and the Reality Gap: The Use of Simulation in Evolutionary Robotics, Third European Conf. on Artificial Life (ECAL95), Advances in Artificial Life, pp.704–720, Springer
Husbands98. Husbands, P. Smith, T. O’Shea, M. Jakobi, N. Anderson, J. and Philippides, A. (1998). Brains, Gases and Robots. In Proc. ICANN98, pp 51–63, Springer-Verlag.
Miglino95. Miglino, O. Lund, H. H. and Nolfi, S. (1995). Evolving Mobile Robots in Simulated and Real Environments, Artificial Life 2, pp.417–434
Beer89. Beer, R. Chiel, J. and Sterling, L. (1989). An artificial insect, American Scientist, 79, pp.444–452
Ackley92. Ackley, D. Littman, M. (1992). Interactions Between Learning and Evolution, Artificial Life II, Addison-Wesley, pp.487–509
Meyrand91. Meyrand, P. Simmers J. and Moulins, M. (1991). Construction of a pattern-generating circuit with neurons of different networks, NATURE, 351-2MAY, pp.60–63
Hooper89. Hooper, S. L. and Moulins, M. (1989). Switching of a Neuron from One Network to Another by Sensory-Induced Changes in Membrane Properties, SCIENCE, 244, pp.1587–1589
Hasselmo95. Hasselmo, M. (1995). Neuromodulation and cortical function: modeling the physiological basis of behavior, Behavioral Brain Research, 67, Elsevier Science B.V., pp.1–27
Hoshino94. Hoshino, T (1994). Dreams and Worries of Artificial Life, Popular Science Series, Shouka-Bo (in Japanese)
Ishiguro99. Ishiguro, A. Kondo, T. Uchikawa, Y. and Eggenberger, P. (1999). Autonomous Robot Control by a Neural Network with Dynamically-Rearranging Function, Proc. of the 11th SICE Symposium on Decentralized Autonomous Systems, pp.213–218 (in Japanese)
Kondo99. Kondo, T. Ishiguro, A. Uchikawa, Y. and Eggenberger, P. (1999). Autonomous Robot Control by a Neural Network with Dynamically-Rearranging Function, Proc. of the 4th International Conference on Artificial Life and Robotics (AROB99), 1, pp.324–329
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Eggenberger, P., Ishiguro, A., Tokura, S., Kondo, T., Uchikawa, Y. (2000). Toward Seamless Transfer from Simulated to Real Worlds: A Dynamically—Rearranging Neural Network Approach. In: Wyatt, J., Demiris, J. (eds) Advances in Robot Learning. EWLR 1999. Lecture Notes in Computer Science(), vol 1812. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-40044-3_3
Download citation
DOI: https://doi.org/10.1007/3-540-40044-3_3
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41162-8
Online ISBN: 978-3-540-40044-8
eBook Packages: Springer Book Archive