Abstract
In this work we study a way of introducing temporal information in the structure of artificial neural networks that will be used as behavioral controllers for real mobile robots operating in unstructured environments. We introduce networks with delays in their synapses as the building block for these controllers and the evolutionary methodology employed for obtaining them in simulation. The effects of different types of noise added during evolution on the robustness of the controllers in the real robot are commented. Two examples of behaviors that will require time reasoning in our robot implementation are presented: wall following and homing.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Arkin, R.C.: Behaviour Based Robotics. MIT Press, Cambridge, MA (1998)
Nolfi, S., Floreano, D., Miglino, O., Mondada, F.: How to Evolve Autonomous Robots: Different Approaches in Evolutionary Robotics. In Brooks, R., Maes, P. (eds.): Proceedings of Fourth International Conference on Artificial Life. Cambridge, MA, MIT Press (1994).
Cliff, D.T., Harvey, I., Husbands, P.: Explorations in Evolutionary Robotics. Adaptive Behavior, Vol. 2 (1993) 73–110
Takens, F.: On the Numerical Determination of the Dimension of an Attractor, In Rand, D., Young, L.S. (eds.): Dynamical Systems and Turbulence, Warwick 1980 Lecture Notes in Mathematics, Vol. 898, Springer Verlag (1981) 366–381
Elman J. L.: Finding Structures in Time. CRL Technical Report No8801, La Jolla University of California, San Diego (1988)
Jordan, M.I.: Attractor Dynamics and Parallelism in a Connectionist Sequential Machine. In Erlbaum, L., Hillside, N.J. (eds.): Proceedings of the 1986 Cognitive Science Conference (1986) 531–546
Waibel A., Hanazawa, T., Hinton, G., Lang, J., Shikano K: Phoneme Recognition Using Time-Delay Neural Networks. IEEE Trans. Acoust. Speech Signal Processing, Vol. 37. (1989) 328–339
Duro, R.J., Santos, J.: Fast Discrete Time Backpropagation for Adaptive Synaptic Delay Based Neural Networks. Submitted for publication in IEEE Trans. on Neural Networks (1998)
Santos, J., Duro, R.J.: Evolving Neural Controllers for Temporally Dependent Behaviors in Autonomous Robots. In del Pobil, A.P., Mira, J. Ale, M. (eds.): Tasks and Methods in Applied Artificial Intelligence, Lecture Notes in Artificial Intelligence, Vol. 1416. Springer-Verlag, Berlín (1998) 319–328
Jakobi, N.: Evolutionary Robotics and the Radical Envelope of Noise Hypothesis. Adaptive Behavior, Vol. 6, No. 2 (1997) 325–368
Salomon, R.: The Evolution of Different Neuronal Control Structures for Autonomous Agents, Robotics and Autonomous Systems, Vol. 22 (1997) 199–213
Mitchel, O.: Khepera Simulator Package version 2.0, Freeware Mobile Robot Simulator, downloadable from http://wwwi3s.unice.fr/om7khep-sim.html. University of Nice Sophia-Antipolis, France (1996)
Becerra, J.A., Crespo, J.L., Santos, J., Duro, R.J.: Incremental Design of Neural Controllers for an Infrasensorized Autonomous Robot. Las Palmas International Conference Wiener's Cybernetics: 50 Years of Evolution, Las Palmas de Gran Canaria (1999)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Becerra, J.A., Santos, J., Duro, R.J. (1999). Using temporal information in ANNs for the implementation of autonomous robot controllers. In: Mira, J., Sánchez-Andrés, J.V. (eds) Engineering Applications of Bio-Inspired Artificial Neural Networks. IWANN 1999. Lecture Notes in Computer Science, vol 1607. Springer, Berlin, Heidelberg . https://doi.org/10.1007/BFb0100521
Download citation
DOI: https://doi.org/10.1007/BFb0100521
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66068-2
Online ISBN: 978-3-540-48772-2
eBook Packages: Springer Book Archive