An artificial life approach for the synthesis of autonomous agents
This paper describes an evolutionary process producing dynamical neural networks used as “brains” for autonomous agents. The main concepts used: genetic algorithms, morphogenesis process, artificial neural networks and artificial metabolism, illustrate our conviction that some fundamental principles of nature may help to design processes from which emerge artificial autonomous agents. The evolutionary process presented here is applied to a simulated autonomous robot. The resulting neural networks are then embedded on a real mobile robot. We emphasize the role of the artificial metabolism and the role of the environment which appear to be the motors of evolution. The first results observed are encouraging and motivate a deeper investigation of this research area.
KeywordsNeural Network Genetic Algorithm Mobile Robot Cellular Automaton Autonomous Agent
Unable to display preview. Download preview PDF.
- 1.Joëlle Biondi and Olivier Michel. Evolution de structures neuronales. application à un robot mobile autonome. In Actes des journées de Rochebrune, ENST, 46 rue Barrault — 75634 Paris cedex 13, Mars 1995. ENST 95 S 001.Google Scholar
- 2.Valentino Braitenberg. Vehicles: Experiments in Synthetic Psychology. MIT Press, Cambridge, 1984.Google Scholar
- 3.R.A. Brooks. Artificial life and real robots. In F. Varela and P. Bourgine, editors, Towards a Practice of Autonomous Systems, Proceedings of the First International Conference on Artificial Life, Paris. MIT Press, 1992.Google Scholar
- 4.Marco Colombetti and Marco Dorigo. Learning to control an autonomous robot by distributed genetic algorithms. In Jean-Arcady Meyer, H. Roitblat, and Wilson Stewart, editors, From animals to animats 2: Proceedings of the Second International Conference on Simulation of Adaptive Behavior. MIT Press, Bradford Books, 1992.Google Scholar
- 5.Hugo De Garis. Cam-brain: The evolutionary engineering of a billion neuron artificial brain by 2001 which grows/evolves at electronic epeeds inside a cellular automata machine (cam). In D. W. Pearson, N. C. Steele, and R. F. Albrecht, editors, Proceedings of the International Conference on Artificial Neural Networks and Genetic Algorithms (ICANNGA'95) Springer-Verlag Wien New York, 1995.Google Scholar
- 6.Dario Floreano and Francesco Mondada. Automatic creation of an autonomous agent: Genetic evolution of a neural-network driven robot. In Dave Cliff, Phil Husband, Jean-Arcady Meyer, and W. Stewart Wilson, editors, From animals to animats 3: Proceedings of the Third International Conference on Simulation of Adaptive Behavior. MIT Press, 1994.Google Scholar
- 7.Frédéric Gruau and Darrell Whitley. The cellular developmental of neural networks: the interaction of learning and evolution. Technical report, Ecole Normale Supérieure de Lyon, 46, Allée d'Italie, 69364 Lyon Cedex 07, France, January 1993.Google Scholar
- 8.Inman Harvey, Philip Husbands, and Dave Cliff. Seeing the light: Artificial evolution, real vision. In Dave Cliff, Phil Husband, Jean-Arcady Meyer, and W. Stewart Wilson, editors, From animals to animats 3: Proceedings of the Third International Conference on Simulation of Adaptive Behavior. MIT Press, 1994.Google Scholar
- 9.Stuart A. Kauffman. The Origins of Order: Self-Organisation and Selection in Evolution. Oxford University Press, 1993.Google Scholar
- 10.Olivier Michel and Joëlle Biondi. Morphogenesis of neural networks. Neural Processing Letters, 2(1), January 1995.Google Scholar
- 11.F. Mondada, E. Franzi, and P. Ienne. Mobile robot miniaturisation: A tool for investigation in control algorithms. In Third International Symposium on Experimental Robotics, Kyoto, Japan, October 1993.Google Scholar