Abstract
To model complex systems for agent behaviors, genetic algorithms have been used to evolve neural networks which are based on cellular automata. These neural networks are popular tools in the artificial life community. This hybrid architecture aims at achieving synergy between the cellular automata and the powerful generalization capabilities of the neural networks. Evolutionary algorithms provide useful ways to learn about the structure of these neural networks, but the use of direct evolution in more difficult and complicated problems often fails to achieve satisfactory solutions. A more promising solution is to employ incremental evolution that reuses the solutions of easy tasks and applies these solutions to more difficult ones. Moreover, because the human brain can be divided into many behaviors with specific functionalities and because human beings can integrate these behaviors for high-level tasks, a biologically-inspired behavior selection mechanism is useful when combining these incrementally evolving basic behaviors. In this paper, an architecture based on cellular automata, neural networks, evolutionary algorithms, incremental evolution and a behavior selection mechanism is proposed to generate high-level behaviors for mobile robots. Experimental results with several simulations show the possibilities of the proposed architecture.
Similar content being viewed by others
References
Crutchfield JP, Mitchell M (1995) The evolution of emergent computation. In: Proceedings of the National Academy of Sciences, vol 91, pp 10742–10746
Morales FJ, Crutchfield JP, Mitchell M (2001) Evolving two-dimensional cellular automata to perform density classification: a report on work in progress. Parall Comput 27(5):571–585
Gers F, de Garis H, Korkin M (1997) CoDi-1Bit: a simplified cellular automata based neural model. In: Proc Conf on Artificial Evolution, Nimes, France, pp 315–334
de Garis H, Korkin M (2002) The CAM-Brain Machine (CBM): an FPGA-based hardware tool that evolves a 1000 neuron-net circuit module in seconds and updates a 75 million neuron artificial brain for real-time robot control. Neurocomputing 42(1–4):35–68
Nicolescu MN, Mataric MJ (2001) Learning and interacting in human-robot domains. IEEE Trans on Systems, Man and Cybernetics-Part A 31(5):419–430
Mataric MJ (2001) Learning in behavior-based multi-robot systems: Policies, models and other agents. Cognitive Systems Research 2(1):81–93
Mali AD (2002) On the behavior-based architectures of autonomous agency. IEEE Trans Syst, Man Cybernetics-Part C 32(3):231–242
Lyons DM (1993) Representing and analyzing action plans as networks of concurrent processes. IEEE Trans Robot Autom 9(3):241–256
Pirjanian P (1999) Behavior coordination mechanisms: State-of-the-art. Tech-report IRIS-99-375 Institute for Robotics and Intelligent Systems, School of Engineering, University of Southern California
Shi L, Zhen Y, Zengqi-Sun (2000) A new agent architecture for RoboCup tournament: cognitive architecture. In: Proc of the 3 rd World Congress on Intelligent Control and Automation vol 1, pp 199–202
Guessoum Z (1997) A hybrid agent model: a reactive and cognitive behavior. In: The International Symposium on Autonomous Decentralized Systems, pp 25–32
Lyons DM, Hendriks AJ (1995) Planning as incremental adaptation of a reactive system. Robot Autonom Syst 14(4):255–288
Murphy RR, Hughes K, Marzilli A, Noll E (1999) Integration explicit path planning with reactive control of mobile robots using Trulla. Robot Autonom Syst 27(4):225–245
Aguirre E, Gonzalez A (2000) Fuzzy behaviors for mobile robot navigation: design, coordination and fusion. Int J Approx Reas 25(3):255–289
Nolfi S, Floreano D (2002) Synthesis of autonomous robots through evolution. Trends in Cogn Sci 6(1):31–37
Lee W-P (1999) Evolving complex robot behaviors. Inform Sci 121:1–25
Iwakoshi Y, Furuhashi T, Uchikawa Y (1998) A fuzzy classifier system for evolutionary learning of robot behaviors. Appl Math Comput 91:73–81
Floreano D, Mondada F (1998) Evolving neurocontrollers for autonomous mobile robots. Neur Netw 11(7–8):1461–1478
Gutowitz H (1991) Cellular automata: theory and experiment. Physica D 45(1–3)
Goldberg DE (1989) Genetic Algorithms in Search, Optimization, and Machine Learning Addison-Wesley Publishing Company
Mathias KE, Whitley LD (1994) Initial performance comparisons for the delta coding algorithm. In: Proc. of IEEE Conf on Evolutionary Computation vol 1, pp 433–438
Gomez F, Mikkulainen R (1997) Incremental evolution of complex general behavior. Adapt Behav 5:317–342
Team (1999) Khepera Simulator Version 5.02 User Manual
Cho S-B, Song G-B (2000) Evolving CAM-Brain to control a mobile robot. Appl Mathe Comput 111:147–162
Floreano D, Mondada F (1996) Evolution of homing navigation in a real mobile robot. IEEE Trans Syst, Man Cybern-Part B 26(3):396–407
Song G-B, Cho S-B (1999) Rule-based integration of multiple neural networks evolved based on cellular automata. In: Proc of the IEEE Int Conf on Fuzzy Syst, pp 791–796
Author information
Authors and Affiliations
Corresponding author
Additional information
Kyung-Joong Kim (Student Member, IEEE) received the B.S. and M.S. degree in computer science from Yonsei University, Seoul, Korea, in 2000 and 2002, respectively. Since 2002, he has been a Ph.D. student in the Department of Computer Science, Yonsei University. His research interests include evolutionary neural network, robot control, and agent architecture.
Sung-Bae Cho (Member, IEEE) received the B.S. degree in computer science from Yonsei University, Seoul, Korea, in 1988 and the M.S. and Ph.D. degrees in computer science from Korea Advanced Institute of Science and Technology (KAIST), Taejeon, Korea, in 1990 and 1993, respectively. From 1991 to 1993, he worked as a Member of the Research Staff at the Center for Artificial Intelligence Research at KAIST. From 1993 to 1995, he was an Invited Researcher of Human Information Processing Research Laboratories at ATR (Advanced Telecommunications Research) Institute, Kyoto, Japan. In 1998, he was a Visiting Scholar at University of New South Wales, Canberra, Australia. Since 1995, he has been a Professor in the Department of Computer Science, Yonsei University. His research interests include neural networks, pattern recognition, intelligent man-machine interfaces, evolutionary computation, and artificial life. Dr. Cho is a Member of the Korea Information Science Society, INNS, the IEEE Computer Society, and the IEEE Systems, Man and Cybernetics Society. He was awarded outstanding paper prizes from the IEEE Korea Section in 1989 and 1992, and another one from the Korea Information Science Society in 1990. In 1993, he also received the Richard E. Merwin prize from the IEEE Computer Society. In 1994, he was listed in Who’s Who in Pattern Recognition from the International Association for Pattern Recognition and received the best paper awards at International Conference on Soft Computing in 1996 and 1998. In 1998, he received the best paper award at World Automation Congress. He was listed in Marquis Who’s Who in Science and Engineering in 2000 and in Marquis Who’s Who in the World in 2001.
Rights and permissions
About this article
Cite this article
Kim, KJ., Cho, SB. A unified architecture for agent behaviors with selection of evolved neural network modules. Appl Intell 25, 253–268 (2006). https://doi.org/10.1007/s10489-006-0106-z
Issue Date:
DOI: https://doi.org/10.1007/s10489-006-0106-z