Abstract
A two-stage incremental approach has been used to simulate the evolution of neural controllers for robust obstacle-avoidance in a Khepera robot and has proved to be more efficient than a competing direct approach. During a first evolutionary stage, obstacle-avoidance controllers in medium-light conditions have been generated. During a second evolutionary stage, controllers avoiding strongly-lighted regions, where the previously acquired obstacle-avoidance capacities would be impaired, have been obtained. The best controller thus evolved has been successfully downloaded on a Khepera robot. The SGOCE evolutionary paradigm that has been used in these experiments is described in the text. Additional experiments are required to assess the usefulness of the corresponding implementation details. Future research will target furthering the incremental evolutionary process and evolving more intricate behaviors.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Beer, R. D.: On the dynamics of small continuous-time recurrent neural networks. Adaptive Behavior 3(4) (1995) 469–510
Boers, E. and Kuiper, H.: Biological Metaphors and the Design of Modular Artificial Neural Networks. Master's thesis, Dept. of CS and Exp. and The. Psy., Leiden University, (August 1992)
Cangelosi, A., Parisi, D. and Nolfi, S.: Cell division and migration in a ‘genotype’ for neural networks. Network: computation in neural systems (1995)
de Garis, H.: Genetic Programming: GenNets, Artificial Nervous Systems, Artificial Embryos. Ph.D. thesis, University Libre de Bruxelles, Belgium, (1991)
Dellaert, F. and Beer, R.: Toward an evolvable model of development for autonomous agent synthesis. In R. A. Brooks, P. Maes, eds., Proceedings of the Fourth International Workshop on Artificial Life. The MIT Press/Bradford Books, Cambridge, MA, (1994)
Eggenberger, P.: Cell-cell interactions as a control tool of developmental processes for evolutionary robotics, (1996). Submitted to SAB96
Floreano, D. and Mondada, F.: Evolution of homing behavior in a real mobile robot. IEEE Transactions on Systems, Man, and Cybernetics — Part B: Cybernetics 26 (1996) 396–407
Floreano, D. and Mondada, F.: Automatic creation of an autonomous agent: Genetic evolution of a neural-network driven robot. In D. Cliff, P. Husbands, J.A. Meyer, S. W. Wilson, eds., From Animals to Animats 3. Proceedings of the Third International Conference on Simulation of Adaptive Behavior. The MIT Press/Bradford Books, Cambridge, MA, (1994)
Gruau, F.: Automatic definition of modular neural networks. Adaptive Behavior 3(2) (1994) 151–184
Gruau, F. and Quatramaran, K.: Cellular encoding for interactive evolutionary robotics. Tech. rep., University of Sussex, School of Cognitive Sciences, EASY Group, Brighton, UK, (1996)
Harvey, I., Husbands, P. and Cliff, D.: Seeing the light: Artificial evolution, real vision. In D. Cliff, P. Husbands, J.-A. Meyer, S. W. Wilson, eds., From Animals to Animats 3. Proceedings of the Third International Conference on Simulation of Adaptive Behavior, 392–401. The MIT Press/Bradford Books, Cambridge, MA, (1994)
Husbands, P., Harvey, I., Cliff, D. and Miller, G.: The use of genetic algorithms for the development of sensorimotor control systems. In P. Gaussier, J. Nicoud, eds., From Perception to Action. Proceedings of the PerAc'94 Conference, 110–121. IEEE Computer Society Press, Los Alamitos, CA, (1994)
Jakobi, N.: Evolutionary Robotics and the radical envelope of noise hypothesis. Adaptive Behavior 6(1) (1997) 131–174
Jakobi, N.: Half-baked, ad-hoc and noisy: minimal simulation for Evolutionary Robotics. In Husbands, Harvey, eds., Fourth European Conference on Artificial Life. The MIT Press / Bradford Books, (1997)
Jakobi, N., Husbands, P. and Harvey, I.: Noise and the reality gap: The use of simulation in Evolutionary Robotics. In Moran, Moreno, Merelo, Chacon, eds., Advances in Artificial Life: Proceedings of the Third European Conference on Artificial Life. Springer Verlag, (1995)
Kodjabachian, J. and Meyer, J.-A.: Evolution and development of control architectures in animats. Robotics and Autonomous Systems 16(2–4) (December 1995) 161–182
Kodjabachian, J. and Meyer, J.-A.: Evolution and development of modular control architectures for 1-d locomotion in six-legged animats, (1997). Submitted for publication in Evolutionary Computation
Kodjabachian, J. and Meyer, J.-A.: Evolution and development of neural networks controlling locomotion, gradient-following, and obstacle-avoidance in artificial insects, (1998). IEEE Transaction on Neural Networks, In press
Koza, J.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. The MIT Press, (1992)
Koza, J.: Genetic Programming II: Automatic Discovery of Reusable Subprograms. The MIT Press, (1994)
Lee, W., Hallam, J. and Lund, H.: Proceedings of the 6th european workshop on learning robots. In Learning complex robot behaviours by evolutionary approaches. Brighton, (1997)
Lund, H. and Miglino, O.: From simulated to real robots. In Proceedings of the 3rd IEEE International Conference on Evolutionary Computation. IEEE Computer Society Press, (1996)
McClelland, J. L. and Rumelhart, D. E., eds.: Parallel Distributed Processing, vol. l. The MIT Press/Bradford Books, Cambridge, MA, (1986)
Meyer, J.-A.: Evolutionary approaches to neural control in mobile robots. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. San Diego, (October 1998)
Michel, O.: Une approace inspirée de la vie artificielle pour la synthèse d'agents autonomes, (1995). Submitted to EA95, Brest, France
Michel, O.: An artificial life approach for the synthesis of autonomous agents. In Alliot, Lutton, Ronald, Schoenauer, Snyers, eds., Artificial Evolution. Springer, (1996)
Michel, O. and Collard, P.: Artificial neurogenesis: An application to autonomous robotics. In Radle, ed., Proceedings of the 8th. International Conference on Tools in Artificial Intelligence. IEEE Computer Society Press, (1996)
Miglino, O., Lund, R. and Nolfi, S.: Evolving mobile robots in simulated and real environments. Artificial Life 2 (1995) 417–434
Mondada, F., Franzi, E. and Ienne, P.: Mobile robot miniaturization: A tool for investigation in control algorithms. In T. Yoshikawa, F. Miyazaki, eds., Proceedings of the Third International Symposium on Experimental Robotics, 501–513. Springer Verlag, Tokyo, (1993)
Nolfi, S., Miglino, O. and Parisi, D.: Phenotypic plasticity in evolving neural networks. In P. Gaussier, J. Nicoud, eds., From Perception to Action. Proceedings of the PerAc'94 Conference. IEEE Computer Society Press, Los Alamitos, CA, (1994)
Rumelhart, D. E. and McClelland, J. L., eds.: Parallel Distributed Processing, vol. 2. The MIT Press/Bradford Books, Cambridge, NIA, (1986)
Salomon, R.: Increasing adaptativity through Evolutionary Strategies. In P. Maes, M. J. Mataric, J.-A. Meyer, J. B. Pollack, S. W. Wilson, eds., From Animals to Animats 4. Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior. The MIT Press/Bradford Books, Cambridge, MA, (1996)
Segev, I.: Simple neuron models: Oversimple, complex and reduced. Trends in Neurosciences 15(11) (1992) 414–421
Sims, K.: Evolving 3D morphology and behavior by competition. In R. A. Brooks, P. Maes, eds., Proceedings of the Fourth International Workshop on Artificial Life. The MIT Press/Bradford Books, Cambridge, MA, (1994)
Spencer, G.: Automatic generation of programs for crawling and walking. In K. E. K. Jr., ed., Advances in Genetic Programming, 335–353. The MIT Press / Bradford Books, Cambridge, MA, (1994)
Vaario, J.: An Emergent Modeling Method for Artificial Neurol Networks. Ph.D. thesis, University of Tokyo, (August 1993)
Vaario, J., Onitsuka, A. and Shimohara, K.: Formation of neural structures. In Proceedings of the Fourth European Conference on Artificial Life, ECAL97, 214–223. The MIT Press, (1997)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chavas, J., Corne, C., Horvai, P., Kodjabachian, J., Meyer, JA. (1998). Incremental evolution of neural controllers for robust obstacle-avoidance in Khepera. In: Husbands, P., Meyer, JA. (eds) Evolutionary Robotics. EvoRobots 1998. Lecture Notes in Computer Science, vol 1468. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-64957-3_75
Download citation
DOI: https://doi.org/10.1007/3-540-64957-3_75
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64957-1
Online ISBN: 978-3-540-49902-2
eBook Packages: Springer Book Archive