Evolutionary Intelligence

, Volume 3, Issue 3–4, pp 123–136

Real-world transfer of evolved artificial immune system behaviours between small and large scale robotic platforms

  • Amanda M. Whitbrook
  • Uwe Aickelin
  • Jonathan M. Garibaldi
Research Paper

Abstract

In mobile robotics, a solid test for adaptation is the ability of a control system to function not only in a diverse number of physical environments, but also on a number of different robotic platforms. This paper demonstrates that a set of behaviours evolved in simulation on a miniature robot (epuck) can be transferred to a much larger-scale platform (Pioneer), both in simulation and in the real world. The chosen architecture uses artificial evolution of epuck behaviours to obtain a genetic sequence, which is then employed to seed an idiotypic, artificial immune system (AIS) on the Pioneers. Despite numerous hardware and software differences between the platforms, navigation and target-finding experiments show that the evolved behaviours transfer very well to the larger robot when the idiotypic AIS technique is used. In contrast, transferability is poor when reinforcement learning alone is used, which validates the adaptability of the chosen architecture.

Keywords

Artificial immune systems (AIS) Idiotypic networks Evolutionary robotics Cross platform transfer Genetic algorithms 

References

  1. 1.
    Nolfi S, Floreano D (2000) Evolutionary robotics, the biology, intelligence, and technology of self-organizing machines. The MIT Press, CambridgeGoogle Scholar
  2. 2.
    Floreano D, Mondada F (1998) Evolutionary neurocontrollers for autonomous mobile robots. Neural Netw 11(7–8):1416–1478Google Scholar
  3. 3.
    Lungarella M, Sporns O (2006) Mapping information flow in sensorimotor networks. PLOS Comput Biol 2(1):1301–1312CrossRefGoogle Scholar
  4. 4.
    Floreano D, Mondada F (1998) Hardware solutions for evolutionary robotics. In: Proceedings of the 1st European workshop on evolutionary robotics. Springer, London, pp 137–151Google Scholar
  5. 5.
    Walker JH, Garett SM, Wilson MS (2006) The balance between initial training and lifelong adaptation in evolving robot controllers. IEEE Trans Syst Man Cybern B Cybern 36(2):423–432CrossRefGoogle Scholar
  6. 6.
    Michel O (2004) Cyberbotics Ltd—WebotsTM: professional mobile robot simulation. Int J Adv Robot Syst 1(1):39–42Google Scholar
  7. 7.
    Hightower RR, Forrest F, Perelson AS (2005) The evolution of emergent organization in immune system gene libraries. In: Eshelman LJ (ed) Proceedings of the 6th international conference on genetic algorithms. Morgan Kaufmann, San FranciscoGoogle Scholar
  8. 8.
    Spellward P, Kovacs T (2005) On the contribution of gene libraries to artificial immune systems. In: Proceedings of the genetic and evolutionary computation conference, pp 313–319Google Scholar
  9. 9.
    Goosen T, van den Brule R, Janssen J, Haselager P (2007) Interleaving simulated and physical environments improves evolution of robot control structures. In: Proceedings of the 19th Belgium–Netherlands conference on artificial intelligence (BNAIC). Utrecht University Press, Utrect, pp 135–142Google Scholar
  10. 10.
    Whitbrook AM, Aickelin U, Garibaldi JM (2007) Idiotypic immune networks in mobile robot control. IEEE Trans Syst Man Cybern B Cybern 37(6):1581–1598CrossRefGoogle Scholar
  11. 11.
    Whitbrook AM, Aickelin U, Garibaldi JM (2008) An idiotypic immune network as a short-term learning architecture for mobile robots. In: Proceedings of the 7th international conference on artificial immune systems (ICARIS 2008), Phuket, Thailand. Springer, Berlin, pp 266–278Google Scholar
  12. 12.
    Gerkey B, Vaughan R, Howard A (2003) The player/stage project: tools for multi-robot and distributed sensor systems. In: Proceedings of the international conference on advanced robotics (ICAR 2003), Coimbra, Portugal, pp 317–323Google Scholar
  13. 13.
    Utz H, Sablatnog S, Enderle S, Kraetzschmar G (2002) Miro: Middleware for mobile robot applications. IEEE Trans Rob Autom 18(4):493–497CrossRefGoogle Scholar
  14. 14.
    Floreano D, Urzelai J (2000) Evolutionary robots with on-line self-organization and behavioural fitness. Neural Netw 13:431–443CrossRefGoogle Scholar
  15. 15.
    Urzelai J, Floreano D (2000) Evolutionary robotics: coping with environmental change. In: Proceedings of the genetic and evolutionary computation conference GECCO-00. Morgan Kaufmann, San Francisco, pp 941–948Google Scholar
  16. 16.
    Jerne NK (1974) Towards a network theory of the immune system. Ann Immunol 125C(1–2):373–389Google Scholar
  17. 17.
    Aziz-Alaoui MA, Bertelle C (2006) Emergent properties in natural and artificial dynamical systems (understanding complex systems). Springer, BerlinCrossRefGoogle Scholar
  18. 18.
    Hoffman GW (1986) A neural network model based on the analogy with immune system. J Theor Biol 122:33–67CrossRefGoogle Scholar
  19. 19.
    Richter PH (1978) Complexity and regulation of the immune system: the network approach. In: Proceedings of the working conference on system theory in immunology, Rome, Italy. Springer, New York, pp 219–227Google Scholar
  20. 20.
    Mohler RR, Bruni C, Gandolfi A (1980) A systems approach to immunology. Proc IEEE 68(8):964–990CrossRefGoogle Scholar
  21. 21.
    Ishida Y (1990) Fully distributed diagnosis by pdp learning algorithm: towards immune network pdp model. In: Proceedings of the international joint conference on neural networks, pp 777–782Google Scholar
  22. 22.
    Watanabe Y, Sato S, Ishida Y (2004) An approach for self-repair in distributed system using immunity-based diagnostic mobile agents. In: Negoita MGh et al. (eds) KES 2004, LNAI 3214. Springer, Berlin, pp 504–510Google Scholar
  23. 23.
    Cayzer S, Aickelin U (2005) A recommender system based on idiotypic artificial immune networks. J Math Model Algorithms 4(2):181–198MATHCrossRefGoogle Scholar
  24. 24.
    Suzuki J, Yamamoto Y (2000) Building an artificial immune network for decentralized policy negotiation in a communication end system: open webserver/inexus study. In: Proceedings of the 4th world conference on systemics, cybernetics and informatics (SCI 2000), OrlandoGoogle Scholar
  25. 25.
    Farmer JD, Packard NH, Perelson AS (1986) The immune system, adaptation, and machine learning. Phys D 2(1–3):187–204CrossRefMathSciNetGoogle Scholar
  26. 26.
    Krautmacher M, Dilger W (2004) AIS based robot navigation in a rescue scenario. In: Proceedings of the 3rd international conference on artificial immune systems (ICARIS 2004), Catania, Italy. Springer, Berlin, pp 106–118Google Scholar
  27. 27.
    Kondo T, Ishiguro A, Watanabe Y, Shirai Y, Uchikawa Y (1998) Evolutionary construction of an immune network-based behavior arbitration mechanism for autonomous mobile robots. Electr Eng Jpn 123(3):1–10CrossRefGoogle Scholar
  28. 28.
    Michelan R, Von Zuben FJ (2002) Decentralized control system for autonomous navigation based on an evolved artificial immune network. In: Proceedings of the 2002 congress on evolutionary computation (CEC 2002), Honolulu, May 12–17 2002, vol 2, pp 1021–1026Google Scholar
  29. 29.
    Opp WJ, Sahin F (2004) An artificial immune system approach to mobile sensor networks and mine detection. In: Proceedings of the SMC 2004, IEEE international conference on systems, man, and cybernetics, vol 1, pp 947–952Google Scholar
  30. 30.
    Whitbrook AM, Aickelin U, Garibaldi JM (2008) Genetic algorithm seeding of idiotypic networks for mobile-robot navigation. In: Proceedings of the 5th international conference on informatics in control, automation and robotics (ICINCO 2008), Madeira, Portugal, pp 5–13Google Scholar
  31. 31.
    Renders JM, Flasse SP (1996) Hybrid methods using genetic algorithms for global optimization. IEEE Trans Syst Man Cybern B Cybern 26(2):243–258CrossRefGoogle Scholar
  32. 32.
    Franz J, Ruppel CCW, Seifert F, Weigel R (1997) Hybrid optimization techniques for the design of saw-filters. In: Proceedings of the IEEE ultrasonics symposium. Springer, Berlin, pp 33–36Google Scholar
  33. 33.
    Whitbrook AM (2010) Programming mobile robots with aria and player: a guide to object-oriented control. Springer, BerlinCrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  • Amanda M. Whitbrook
    • 1
  • Uwe Aickelin
    • 1
  • Jonathan M. Garibaldi
    • 1
  1. 1.Intelligent Modelling and Analysis Research Group (IMA), School of Computer ScienceUniversity of NottinghamNottinghamUK

Personalised recommendations