GPU Implementation of Food-Foraging Problem for Evolutionary Swarm Robotics Systems

详细信息    查看全文

• 作者：Kazuhiro Ohkura (21)
  Toshiyuki Yasuda (21)
  Yoshiyuki Matsumura (22)
  Masaki Kadota (21)
  
• 刊名：Lecture Notes in Computer Science
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：8667
• 期：1
• 页码：238-245
• 全文大小：213 KB
• 参考文献：1. 艦ahin, E.: Swarm robotics: From sources of inspiration to domains of application. In: 艦ahin, E., Spears, W.M. (eds.) Swarm Robotics 2004. LNCS, vol.聽3342, pp. 10鈥?0. Springer, Heidelberg (2005) CrossRef
  2. Turgut, A.E., 脟elikkanat, H., G枚k莽e, F., 艦ahin, E.: Self-organized flocking in mobile robot swarms. Swarm Intelligence聽2(2-4), 97鈥?20 (2008) CrossRef
  3. Liu, W., Winfield, A.F., Sa, J.: Modelling swarm robotic systems: A case study in collective foraging. Towards Autonomous Robotic Systems (TAROS 2007), 25鈥?2 (2007)
  4. Harvey, I., Husbands, P., Cliff, D., et al.: Issues in evolutionary robotics. School of Cognitive and Computing Sciences, University of Sussex (1992)
  5. 艦ahin, E., Girgin, S., Bayindir, L., Turgut, A.E.: Swarm robotics. In: Swarm Intelligence, pp. 87鈥?00. Springer (2008)
  6. Trianni, V.: Evolutionary swarm robotics: evolving self-organising behaviours in groups of autonomous robots, vol.聽108. Springer (2008)
  7. Stone, S.S., Haldar, J.P., Tsao, S.C., Hwu, W.M., Sutton, B.P., Liang, Z.P., et al.: Accelerating advanced mri reconstructions on gpus. Journal of Parallel and Distributed Computing聽68(10), 1307鈥?318 (2008) CrossRef
  8. Preis, T., Virnau, P., Paul, W., Schneider, J.J.: Accelerated fluctuation analysis by graphic cards and complex pattern formation in financial markets. New Journal of Physics聽11(9), 093024 (2009) CrossRef
  9. Riegel, E., Indinger, T., Adams, N.: Implementation of a lattice boltzmann method for numerical fluid mechanics using the nvidia cuda technology. Computer Science-Research and Development聽23(3-4), 241鈥?47 (2009) CrossRef
  10. Oiso, M., Matsumura, Y., Yasuda, T., Ohkura, K.: Implementing genetic algorithms to cuda environment using data parallelization. Tehnicki vjesnik/Technical Gazette聽18(4) (2011)
  11. Goldberg, D.E., et al.: Genetic algorithms in search, optimization, and machine learning, vol.聽412. Addison-Wesley, Reading (1989)
  12. Deep, K., Thakur, M.: A new crossover operator for real coded genetic algorithms. Applied Mathematics and Computation聽188(1), 895鈥?11 (2007) CrossRef
  13. Deep, K., Thakur, M.: A new mutation operator for real coded genetic algorithms. Applied mathematics and Computation聽193(1), 211鈥?30 (2007) CrossRef
  14. Marsaglia, G.: Xorshift rngs. Journal of Statistical Software聽8(14), 1鈥? (2003)
  
• 作者单位：Kazuhiro Ohkura (21)
  Toshiyuki Yasuda (21)
  Yoshiyuki Matsumura (22)
  Masaki Kadota (21)
  
  21. Graduate School of Engineering, Hiroshima University, Hiroshima, Japan
  22. Faculty of Textile Science and Technology, Shinshu University, Nakano, Japan
  
• ISSN：1611-3349

文摘

Evolutionary swarm robotics (ESR) is an artificial approach for developing smart collective behavior in a system of homogenous autonomous robots. Robot behavior is generally controlled by evolving artificial neural networks. ESR has been considered a promising approach for swarm robotics systems (SRSs), because swarm behavior naturally emerges from numerous local interactions among the autonomous robots. In contrast, programming individual robots to display appropriate swarm behavior is extremely difficult. However, even in a simulated SRS, ESR is precluded by a very high computational cost. In this study, we introduce a novel implementation that overcomes the computational cost problem. The method employs parallel problem solving on a graphics processing unit (GPU) and OpenMP on a multicore CPU. To demonstrate the efficiency of the proposed method, we engage an evolving SRS in a food-foraging problem.