Abstract
In engineering aspects, the goal of artificial life is to incarnate unique behaviors or phenomena of living creatures in nature into artifacts like computers. Artificial life can provide a useful methodology for multiple mobile agent learning which is full of autonomy and creativity. In this paper, a neural network is used for the behavior decision controller. The input of the neural network is decided by the existence of other agents and the distance to the other agents. The output determines the directions in which the agent moves. The connection weight values of this neural network are encoded as genes, and the fitness of individuals is determined using a genetic algorithm. Here, the fitness values imply how much group behaviors fit adequately to the goal. The validity of the system is verified through simulation. Moreover, in this paper, we could have observed the agents' emergent behaviors during simulation.
Similar content being viewed by others
References
Asama, A. et al. (eds): Distributed Autonomous Robotic Systems, Vols I, II, Springer, Berlin, Vol. I 1994, Vol. II 1996.
Brooks and Maes (eds): Artificial Life, Vol. IV, MIT Press, Cambridge, MA, 1994.
Collins, R. J. and David, R.: An artificial Neural network representation for artificial organisms, in: Proc. of the 1st Workshop on Parallel Problem Solving, Lecture Notes in Computer Science 496, Springer, New York, 1992, pp. 259-263.
Collins, R. J. and Jefferson, D. R.: Ant farm: Towards simulated evolution, in: Artificial Life, Vol. II, Addison-Wesley, Reading, MA, 1991, pp. 1-23.
Dorigo, M., Maniezzo, V., and Colorni, A.: Ant system: Optimization by a colony of cooperating robots, IEEE Trans. Systems Man Cybernet. B: Cybernetics 26(1) (1996), 29-41.
Floreano, D.: Evolutionary robotics in artificial life and behavior engineering, in: T. Gomi (ed.), Evolutionary Robotics, Vol. II, Ontario, Canada, AAI Books, 1998.
Floreano, D., Nolfi, S., and Mondada, F.: Co-evolution and ontogenetic change in competing robots, in: M. Patel, V. Honavar and K. Balakrishnan (eds), Advances in the Evolutionary Synthesis of Intelligent Robots, MIT Press, Cambridge, MA, 2001.
Genetic Programming: On the Programming of Computers by Means of Natural Selection, MIT Press, Cambridge, MA, 1992.
Goldberg, D. E.: Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, Reading, MA, 1989.
Gomez, F. and Miikkulainem, R.: Incremental evolution of complex general behavior, Adaptive Behavior 5 (1997), 317-342.
Haynes, T. and Sen, S.: Learning cases to resolve conflicts and improve group behavior, Internat. J. Human Computer Studies 48 (1998), 31-49.
Hogg, L. M. J. and Jennings, N. R.: Socially intelligent reasoning for autonomous robots, IEEE Trans. Systems Man Cybernet. A: Systems and Humans 31(5) (2001), 381-393.
Il-Kwon, J. and Lee, J.-J.: Evolving fuzzy logic controllers for multiple mobile robots solving a continuous pursuit problem, in: IEEE Internat. Fuzzy Systems Conf. Proceedings, 1999, pp. 685-689.
Kam-Chuen, J. and Giles, C. L.: Talkin helps: Evolving communicating robots for the predator-prey pursuit problem, Artificial Life 6 (2000), 237-254.
Lee, D. W., Jun, H. B., and Sim, K. B.: Artificial immune system for realization of cooperative strategies and group behavior in collective autonomous mobile robots, in: Proc. of the 4th Internat. Symp. on Artificial Life and Robotics, 1999, pp. 232-235.
Lee, D. W. and Sim, K. B.: Development of communication system for cooperative behavior in collective autonomous mobile robots, in: Proc. of the 2nd Ascian Control Conf., Vol. 2, July 1997, pp. 615-618.
Lee, D. W. and Sim, K. B.: Behavior learning and evolution of collective autonomous mobile robots using distributed genetic algorithms, in: Proc. of the 2nd Ascian Control Conf., Vol. 2, July 1997, pp. 675-678.
Lesser, V. R.: Cooperative multi-robot systems: A personal view of the state of the art, IEEE Trans. Knowledge Data Engrg. 11(1) (1999), 133-142.
Nolfi, S. and Floreano, D.: Co-evolving predator and prey robots: Do 'arm races' arise in artificial evolution?, Artificial Life 4(4) (1998), 311-335.
Pena-Reyes, C. A. and Sipper, M.: Fuzzy CoCo: A cooperative-Co-evolutionary approach to fuzzy modeling, IEEE Trans. Fuzzy Systems 9(5) (2001), 727-737.
Sim, K. B.: Realixation of intelligent robot system based on artificial life, J. Korean Electronics 24(3) (1997), 70-82.
Stone, P. and Veloso, M.: Multiagent systems: A survey from a machine learning perspective, Autonomous Robots 8 (2000), 345-383.
Takayuki, K. and Matsubayashi: An adaptive architecture for modular Q-learning, in: Proc. of the 10th Internat. Conf. on Simulation of Adaptive Behavior, MIT Press, Cambridge, MA, 2000, pp. 1-6.
Tzafestas, E. S., Raptis, S. N., and Tzafestas, S. G.: Multi-agent robot architectures: The decomposition issue and a case study, Internat. J. Artificial Intelligence Tools 7(2) (1998), 163-187.
Tzafestas, E. S.: Compromising algorithmicity and plasticity in autonomous agent control systems: The autonomous cell, J. Intelligent Systems 9(2) (1999), 135-176.
Tzafestas, E. S.: Aging agents, Artificial Life Robotics 5 (2001), 46-57.
Yasuo, N. and Shin, I.: Multi-robot reinforcement learning: An approach based on the other robot's internal model, in: Proc. of the 8th Conf. on the Simulation of Adaptive Behavior: From Animals to Animates:: MIT Press, Cambridge, MA, 1999, pp. 478-485.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Lee, M., Chang, OB., Yoo, CJ. et al. Behavior Evolution of Multiple Mobile Agents under Solving a Continuous Pursuit Problem Using Artificial Life Concept. Journal of Intelligent and Robotic Systems 39, 433–445 (2004). https://doi.org/10.1023/B:JINT.0000026083.64909.e4
Issue Date:
DOI: https://doi.org/10.1023/B:JINT.0000026083.64909.e4