International Journal of Fuzzy Logic and Intelligent Systems

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Learning of Emergent Behaviors in Collective Virtual Robots using ANN and Genetic Algorithm

  • Cho, Kyung-Dal (Dept. of Computer Science & Engineering, Chung-Ang University)
  • Published : 2004.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

In distributed autonomous mobile robot system, each robot (predator or prey) must behave by itself according to its states and environments, and if necessary, must cooperate with other robots in order to carry out a given task. Therefore it is essential that each robot have both learning and evolution ability to adapt to dynamic environment. This paper proposes a pursuing system utilizing the artificial life concept where virtual robots emulate social behaviors of animals and insects and realize their group behaviors. Each robot contains sensors to perceive other robots in several directions and decides its behavior based on the information obtained by the sensors. In this paper, a neural network is used for behavior decision controller. The input of the neural network is decided by the existence of other robots and the distance to the other robots. The output determines the directions in which the robot moves. The connection weight values of this neural network are encoded as genes, and the fitness individuals are determined using a genetic algorithm. Here, the fitness values imply how much group behaviors fit adequately to the goal and can express group behaviors. The validity of the system is verified through simulation. Besides, in this paper, we could have observed the robots' emergent behaviors during simulation.

Keywords

References

  1. Floreano, D.,Evolutionary Agentics in Artificial Life and Behavior Engineering. In T. Gomi (ed.), Evolutionary Agentics II, Ontario (Canada): AAI Books, 1998
  2. Gomez, F., & Miikkulainem, R., 'Incremental evolution of complex general behavior', Adaptive Behavior, 5, pp. 317342,1997 https://doi.org/10.1177/105971239700500305
  3. Floreano, D., Nolfi, S. and Mondada, F. (2001) CoEvolution and Ontogenetic Change in Competing Agents.In M. Patel, V. Honavar, and K. Balakrishnan (eds.), Advances in the Evolutionary Synthesis of Intelligent Agents, Cambridge (MA): MIT Press
  4. Brooks and Maes ed., Artificial Life , MIT Press, 1994
  5. A. Asama et. AI. eds, Distributed Autonomous Agentic Systems I, II, Springer-Verlag, 1994
  6. D. W. Lee, K. B. Sim, 'Behavior Learning and Evolution of Collective Autonomous Mobile Agents using Distributed Genetic Algorithms,' Proc. of 2nd AScian Control Conference, Vol.2, pp.575-678, 1997.7
  7. D.W. Lee, K.B. Sim, 'Development of Communication System for Cooperative Behavior in Collective Autonomous Mobile Agents,', Proc. of 2nd AScian Control Conference, Vol.2, pp.615-618, 1997.7
  8. D.W. Lee, H. B. Jun, and K.B. Sim, 'Artificial Immune System for Realization of Cooperative Strategies and Group Behavior in Collective Autonomous Mobile Agents,', Proc. of Fourth Int'l Symp. On Artificial Life and Agentics, pp.232-235, 1999
  9. K.B Sim, 'Realixation of Intelligent agent system Based on Artificial Life', Journal of Korean Electronics, Vol.24, No.3, pp. 70-82, 1997.3
  10. Lisa, M.J. Hogg and Nichola R. Jennings, 'Socially Intelligent Reasoning for Autonomous Agents', IEEE Trans. On Systems, Man, and Cybernetics-Part A: Systems and Humans, Vol.31, No.5, pp. 381-393, September, 2001 https://doi.org/10.1109/3468.952713
  11. Marco Dorigo, Vittorio Maniezzo, and Alberto Colorni, 'Ant System: Optimization by a Colony of Cooperating Agents', IEEE Trans. On Systems, Man, and CyberneticsPart B: Cybernetics, Vol.26, No.1, pp. 29-41, February, 1996 https://doi.org/10.1109/3477.484436
  12. Collins, Robert J. and David R, 'An artificial Neural network representauion for artificial organisms', Proceedings of the First workshop on Parallel Problem Solving, Number 496, In Lecture Notes in Computer Science, pp. 259-263, Springer-Verlag, 1992
  13. Victor R. Lesser, 'Cooperative Multiagent systems: A personal view of the state of the art', IEEE Transactions on knowledge data engineering, Vol, No. 1, pp.133-142.1999
  14. Takayuki Kohri and Matsubayashi , 'An Adaptive Architecture for Modular Q-Learning', In Proceedings of the 10th International Confernece on Simulation of Adaptive Behavior, MIT Press, pp.I-6, 2000
  15. Yasuo Nagayuki, Shin Ishii, 'Multi-Agent Reinforcement Learning: An Approach Based on the Other Agent's Internal Model', From Animals to mates:Proceedings of the 8th Confernece on the Simulation of Adaptive Behavior, MIT Press, pp.478-485, 1999
  16. H. Asama et aI., Distributed Autonomous Agentic Systems, Springer- Verlag, 1994
  17. H. Asama et aI., Distributed Autonomous Agentic Systems 2, Springer-Verlag, 1996
  18. Kam-Chuen Jim, C.Lee Giles, 'Talkin Helps: Evolving Communicating Agents for the Predator-Prey Pursuit Problem', Artificial Life 6, pp. 237-254, 2000 https://doi.org/10.1162/106454600568861
  19. Il-Kwon Jeong and Ju-Jang Lee, 'Evolving Fuzzy Logic Controllers for Multiple Mobile Agents Solving a Continuous Pursuit Problem', IEEE International Fuzzy Systems Conference Froceedings, pp.685-689, 1999
  20. Carlos Andres Penz-Reyes and Moshe Sipper, 'Fuzzy CoCo: A Cooperative Co-evolutionary Approach to Fuzzy Modeling', IEEE Trans. On Fuzzy Systems, Vo1.9, No.5, pp.727-737, October, 2001 https://doi.org/10.1109/91.963759
  21. Genetic Programrr.ing : On the Programming of Computers by Means of Natural Selection, MIT Press, 1992
  22. D.E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison Wesley, 1989
  23. Nolfi, S. and Floreano, D. ,"Co-evolving predator and prey agents: Do 'arm races' arise in artificial evolution?", Artificial Life, 4(4), 311-335, 1998 https://doi.org/10.1162/106454698568620
  24. Peter Stone and Manuela Veloso,'Multiagent Systems: A survey from a Machine Learning Perspective', Autonomous Robots, 8, 345-383, 2000 https://doi.org/10.1023/A:1008942012299
  25. Haynes, T. and Sen, S., 'Learning cases to resolve conflicts and improve group behavior', International Journal of Human Computer Studies, 48, pp. 31-49, 1998

Cited by

  1. Univector Field Method based Multi-Agent Navigation for Pursuit Problem vol.12, pp.1, 2012, https://doi.org/10.5391/IJFIS.2012.12.1.86