single-jc.php

JACIII Vol.17 No.6 pp. 932-942
doi: 10.20965/jaciii.2013.p0932
(2013)

Paper:

Cooperative Transport by a Swarm Robotic System Based on CMA-NeuroES Approach

Tian Yu*, Toshiyuki Yasuda*, Kazuhiro Ohkura*,
Yoshiyuki Matsumura**, and Masanori Goka***

*Graduate School of Engineering, Hiroshima University, 1-4-1 Kagamiyama, Higashi-Hiroshima, Hiroshima 739-8527, Japan

**Graduate School of Science and Technology, Shinshu University, 3-15-1 Tokida, Ueda, Nagano 386-8567, Japan

***Graduate School of Engineering, Fukuyama University, 985-1 Fukuyama City, Hiroshima 729-0251, Japan

Received:
March 20, 2013
Accepted:
September 26, 2013
Published:
November 20, 2013
Keywords:
swarm robotic systems, evolving artificial neural network, evolutionary robotics, covariance matrix adaptation evolution strategy
Abstract

Swarm robotic systems consist of many homogeneous autonomous robots with no type of global controllers. It is difficult to design controllers for such behavioral systems, since the behavior of system level is the emergent results of the dynamical interaction between the systems and the environment. This paper uses a method that in which robot controllers are designed by a covariance matrix adaptation evolution strategy (CMA-ES) with artificial neural networks. This approach is referred to as CMA-NeuroES. Among the many evolutionary algorithms for evolving artificial neural networks, two conventionally representation approaches, fast evolution strategies and differential evolution, are used for comparison. The cooperative transport problem is used as a benchmark of swarm robotic systems to test their performance. Results show that CMA-NeuroES has the overall best performance of the three.

Cite this article as:
Tian Yu, Toshiyuki Yasuda, Kazuhiro Ohkura,
Yoshiyuki Matsumura, and Masanori Goka, “Cooperative Transport by a Swarm Robotic System Based on CMA-NeuroES Approach,” J. Adv. Comput. Intell. Intell. Inform., Vol.17, No.6, pp. 932-942, 2013.
Data files:
References
  1. [1] E. Sahin, “Swarm Robotics: From Sources of Inspiration to Domains of Application,” Swarm Robotics WS2004, LNCS, Vol.3342, pp. 10-20, 2005.
  2. [2] E. Sahin, S. Girgin, L. Bayindir, and A. E. Turgut, “Swarm Robotics,” Swarm Intelligence – introductionand Applications –, Berlin, Heidelberg, Springer Verlag, pp. 87-100, 2008.
  3. [3] C. R. Kube and H. Zhang, “TaskModelling in Collective Robotics,” Autonomous Robots, Vol.4, No.1, Kluwer Academic, pp. 53-72, 1997.
  4. [4] http://www.swarm-bots.org/
    [Accessed July 20, 2012]
  5. [5] hhttp://www.swarmanoid.org/
    [Accessed July 20, 2012]
  6. [6] I. Harvey, P. Husbands, and D. Cliff, “Issues in Evolutionary Robotics,” J. of Adaptive Behavior, Vol.2, pp. 73-110, 1993.
  7. [7] D. Floreano, P. Durr, and C. Mattiussi, “Neuroevolution: from architectures to learning,” Evolutionary Intelligence, Vol.1, pp. 47-62, 2008.
  8. [8] K. Ohkura, T. Yasuda, Y. Kawamatsu, Y. Matsumura, and K. Ueda, “MBEANN: Mutation-Based Evolving Artificial Neural Networks,” Advances in Artificial Life, the 9th European Conf. on Artificial Life, LNAI, Vol.4648, pp. 936-945, 2007.
  9. [9] N. Hansen, A. Auger, R. Ros, S. Finck, and P. Posik, “Comparing results of 31 algorithms from the black-box optimization benchmarking BBOB-2009,” Proc. of GECCO’10, ACM, pp. 1689-1696, 2010.
  10. [10] C. Igel, “Neuroevolution for reinforcement learning using evolution strategies,” Proc. of CEC’03, Vol.4, pp. 2588-2595, 2003.
  11. [11] K. Ohkura, T. Yasuda, Y. Kotani, and Y. Matsumura, “A Swarm Robotics Approach to Cooperative Package-Pushing Problems with Evolving Recurrent Neural Networks,” Proc. of SICE Annual Conf. 2010, LNAI, Vol.4648, pp. 706-711, 2010.
  12. [12] N. Hansen, “The CMA Evolution Strategy: A Tutorial,” Towards a new evolutionary computation Advances in estimation of distribution algorithms, Springer, pp. 75-102, 2011.
  13. [13] N. Hansen et al., “On the adaptation of arbitrary normal mutation distributions in evolution strategies: The generating set adaptation,” Morgan Kaufmann L. Eshelman (Ed.), pp. 57-64, 1995.
  14. [14] N. Hansen and A. Ostemeier, “Adapting arbitrary normal mutation distributions in evolution strategies: The covariance matrix adaptation,” IEEE Int. Conf. on Evolutionary Computation, pp. 312-317, 1996.
  15. [15] N. Hansen and A. Ostemeier, “Convergence properties of evolution strategies with the derandomized covariance matrix adaptation: The (μ/μI,λ )-ES,” EUFIT’97, pp. 650-654, 1997.
  16. [16] H. Moriguchi and S. Honiden, “CMA-TWEANN: Efficient Optimization of Neural Networks via Self-adaptation and Seamless Augmentation,” Genetic and Evolutionary Computation Conference (GECCO’12), pp. 903-910, 2012.
  17. [17] X. Yao and Y. Liu, “Fast Evolution Strategies,” Control and Cybernetics, Vol.26, No.3, pp. 467-496, 1997.
  18. [18] R. Storn and K. Price, “Differential Evolution-A Simple and Efficient Heuristic for Global Optimization over Continuous Space,” Morgan Kaufmann, J. of Global Optimization, Vol.11, pp. 341-359, 1997.
  19. [19] K. Ohkura, T. Yasuda, and Y. Matsumura, “Coordinating the Adaptive Behavior for Swarm Robotic Systems by Using Topology and Weight Evolving Artificial Neural Networks,” Proc. of WCCI 2010 IEEE World Congress on Computational Intelligence, 2010 IEEE Congress on Evolutionary Computation, pp. 1788-1795, 2010.
  20. [20] K. Ohkura, T. Yasuda, T. Sakamoto, and Y. Matsumura, “Evolving Robot Controllers for a Homogeneous Robotic Swarm,” Proc. of 2011 IEEE/SICE Int. Symposium on System Integration, pp. 708-713, 2011.

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

Last updated on Oct. 22, 2021