JRM Vol.17 No.1 pp. 52-58
doi: 10.20965/jrm.2005.p0052


A Study on Autonomous Mobile Robot Behavior Adjustment Using a Cytokine Reaction Model

Yosuke Shigeta*, and Yukinori Kakazu**

*Graduate School of Engineering, Hokkaido University, Kita 13, Nishi 8, Kita-ku, Sapporo 060-8628, Japan

**Graduate School of Information Science and Technology, Hokkaido University, Kita 14, Nishi 9, Kita-ku, Sapporo 060-8628, Japan

December 22, 2004
January 11, 2005
February 20, 2005
artificial immune system, idiotype network, cytokine reaction, autonomous mobile robot, behavior arbitration
We propose an Artificial Immune System (AIMS) model using the cytokine reaction to navigate an autonomous mobile robot in a fluctuating environment. AIMS extracts the biological immune system mechanism adjusting macroscopic idiotype network behavior using cytokines. Such behavior for autonomous mobile robots is defined as the topology of a set of selected actions per unit time. Topology adjustment is important, because describing all possible actions for large fluctuating environments may cause a frame problem. To design the AIMS of the action extractor and the macroscopic behavior adjuster, we study influences of environmental parameters. Basic experiments showed that the action extractor must take into account the effect of the number of Relating Strict antibodies (nRS), a feature value of the AIMS antibody and that prior knowledge about the relationship between macroscopic behavior and environmental parameters enables efficient adjustment.
Cite this article as:
Y. Shigeta and Y. Kakazu, “A Study on Autonomous Mobile Robot Behavior Adjustment Using a Cytokine Reaction Model,” J. Robot. Mechatron., Vol.17 No.1, pp. 52-58, 2005.
Data files:
  1. [1] R. Brooks, “A Robust Layered Control System for a Mobile Robot,” IEEE Journal of Robotics and Automation, Vol.RA-2, No.1, pp. 14-23, 1986.
  2. [2] Y. Watanabe, A. Ishiguro, and Y. Uchikawa, “Behavior Control for an Autonomous Mobile Robot Using Immune Network,” JRM, Vol.10, No.4, pp. 326-332, 1998.
  3. [3] Y. Watanabe et al., “Emergent Construction of Behavior Arbitration Mechanism Based on the Immune System,” Advanced Robotics, Vol.12, No.3, pp. 227-242, 1998.
  4. [4] M. Kinoshita et al., “Macroscopic Quantitative Observation of Multi-Robot Behavior,” Intern. J. of Comp. Intel. and App., Imperial College Press, Vol.2, No.4, pp. 457-466, 2002.
  5. [5] N. Mitsumoto, T. Fukuda, and F. Arai, “Generation and Adaptation Mechanism of Swarm Strategy for Multi-Agent System,” Trans. of JSME Series C, Vol.61, No.586, pp. 2440-2447, 1995 (in Japanese).
  6. [6] N. K. Jerne, “Towards a Network Theory of the Immune System,” Ann. Im. (Inst. Pasteur), 125 C, pp. 373-389, 1974.
  7. [7] C. A. Janeway Jr, and P. Travers, “Immuno Biology 3rd Ed.,” Garland Publishing Inc. Current Biology Ltd., 1997.
  8. [8] S. Forrest et al., “Using Genetic Algorithms to Explore Pattern Recognition in the Immune System,” Evolutionary Computation, Vol.1, No.3, pp. 191-211, 1993.
  9. [9] J. D. Farmer et al., “The Immune System, Adaptation, and Machine Learning,” Physica D, pp. 187-204, 1986.
  10. [10] Z. Wei, and K. Nakano, “A Network Model of Regulation for Immune Responses,” IEICE D-II, Vol.J74-D-II, No.3, pp. 407-415, 1991.
  11. [11] V. Detourst et al., “Development of an Idiotypic Network in Shape Space,” J. Theor. Biol., 170, pp. 401-414, 1994.
  12. [12] Y. Shigeta, H. Yokoi, and Y. Kakazu, “Artificial Immune Rule System using Heuristic Environment Parameters,” JSPE autumn ann. conf., 2002 (in Japanese).

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Apr. 22, 2024