Advertisement

Evolutionary Intelligence

, Volume 3, Issue 1, pp 13–29 | Cite as

Collective neuro-evolution for evolving specialized sensor resolutions in a multi-rover task

  • G. S. NitschkeEmail author
  • M. C. Schut
  • A. E. Eiben
Research Paper

Abstract

This article presents results from an evaluation of the collective neuro-evolution (CONE) controller design method. CONE solves collective behavior tasks, and increases task performance via facilitating emergent behavioral specialization. Emergent specialization is guided by genotype and behavioral specialization difference metrics that regulate genotype recombination. CONE is comparatively tested and evaluated with similar neuro-evolution methods in an extension of the multi-rover task, where behavioral specialization is known to benefit task performance. The task is for multiple simulated autonomous vehicles (rovers) to maximize the detection of points of interest (red rocks) in a virtual environment. Results indicate that CONE is appropriate for deriving sets of specialized rover behaviors that complement each other such that a higher task performance, comparative to related controller design methods, is attained in the multi-rover task.

Keywords

Neuro-evolution Multi-rover Collective behavior Specialization 

References

  1. 1.
    Agogino A (2003) Design and control of large collections of learning agents. Ph. D. Dissertation, Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, USAGoogle Scholar
  2. 2.
    Agogino A, Tumer K (2004) Efficient evaluation functions for multi-rover systems. In: Proceedings of the genetic and evolutionary computation conference. Springer, New York, pp. 1–12Google Scholar
  3. 3.
    Balch T (1998) Behavioral diversity in learning robot teams. PhD Thesis, College of Computing, Georgia Institute of Technology, AltantaGoogle Scholar
  4. 4.
    Baldassarre G, Nolfi S, Parisi D (2003) Evolving mobile robots able to display collective behavior. Artif Life 9(1):255–267CrossRefGoogle Scholar
  5. 5.
    Bonabeau E, Dorigo M, Theraulaz G (1998) Swarm intelligence: from natural to artificial systems. Oxford University Press, OxfordGoogle Scholar
  6. 6.
    Bonabeau E, Theraulaz G, Deneubourg J (1996) Quantitative study of the fixed threshold model for the regulation of division of labour in insect societies. Proc R Soc Lond B 263(1):1565–1569Google Scholar
  7. 7.
    Bryant B, Miikkulainen R (2003) Neuro-evolution for adaptive teams. In: Proceedings of the congress on evolutionary computation. IEEE Press, Canberra, pp. 2194–2201Google Scholar
  8. 8.
    Bull L (1997) Evolutionary computing in multi-agent environments: partners. In: Proceedings of the seventh international conference on genetic algorithms. Morgan Kaufmann, East Lansing, pp. 370–377Google Scholar
  9. 9.
    Bull L, Fogarty T, Snaith M (1995) Evolution in multi-agent systems: evolving communicating classifier systems for gait in a quadrupedal robot. In: Proceedings of the sixth international conference on genetic algorithms. Morgan Kauffman, San Mateo, pp. 382–388Google Scholar
  10. 10.
    Bull L, Holland J (1997) Evolutionary computing in multi-agent environments: eusociality. In: Proceedings of the second annual conference on genetic programming. IEEE Press, San Francisco, pp. 347–352Google Scholar
  11. 11.
    Drezewski R (2003) A model of co-evolution in multi-agent system. In: Multi-agent systems and applications III. Springer, Berlin, pp. 314–323Google Scholar
  12. 12.
    Eiben A, Smith J (2003) Introduction to evolutionary computing. Springer, BerlinzbMATHGoogle Scholar
  13. 13.
    Elman J (1990) Finding structure in time. Cogn Sci 14(1):179–211CrossRefGoogle Scholar
  14. 14.
    Flannery B, Teukolsky S, Vetterling W (1986) Numerical recipes. Cambridge University Press, CambridgeGoogle Scholar
  15. 15.
    Floreano D, Dürr P, Mattiussi C (2008) Neuroevolution: from architectures to learning. Evol Intell 1(1):47–62Google Scholar
  16. 16.
    Funes P, Orme B, Bonabeau E (2003) Evolving emergent group behaviors for simple humans agents. In: Proceedings of the European conference on artificial life. Springer, Berlin, pp. 76–89Google Scholar
  17. 17.
    Gautrais J, Theraulaz G, Deneubourg J, Anderson C (2002) Emergent polyethism as a consequence of increased colony size in insect societies. J Theor Biol 215(1):363–373CrossRefGoogle Scholar
  18. 18.
    Gomez F (2003) Robust non-linear control through neuroevolution. PhD thesis, Department of Computer Sciences, The University of Texas, AustinGoogle Scholar
  19. 19.
    Gomez F, Miikkulainen R (1999) Solving non-markovian control tasks with neuroevolution. In: Proceedings of the international joint conference on artificial intelligence. Morgan Kaufmann, Stockholm, Sweden, pp. 1356–1361Google Scholar
  20. 20.
    Gomez F, Schmidhuber J, Miikkulainen R (2006) Efficient non-linear control through neuroevolution. In: Machine learning: ECML 2006. Springer, Berlin, pp. 654–662Google Scholar
  21. 21.
    Gomez F, Schmidhuber J, Miikkulainen R (2008) Accelerated neural evolution through cooperatively coevolved synapses. J Mach Learn Res 9(1):937–965MathSciNetGoogle Scholar
  22. 22.
    Hertz J, Krogh A, Palmer R (1991) Introduction to the theory of neural computation. Addison-Wesley, Redwood CityGoogle Scholar
  23. 23.
    Holland J, Reitman J (1978) Cognitive systems based on adaptive algorithms. Pattern Direct Inference Syst 7(2):125–149Google Scholar
  24. 24.
    Hurst J, Bull L (2006) A neural learning classifier system with self-adaptive constructivism for mobile robot control. Artif Life 12(3):353–380CrossRefGoogle Scholar
  25. 25.
    Husbands P, Mill F (1991) Simulated co-evolution as the mechanism for emergent planning and scheduling. In: Proceedings of the fourth conference on genetic algorithms. Morgan Kaufmann, Cambridge, pp. 264–270Google Scholar
  26. 26.
    Kreiger M, Billeter J (2000) The call of duty: self-organized task allocation in a population of up to twelve mobile robots. Rob Auton Syst 30(1):65–84CrossRefGoogle Scholar
  27. 27.
    Li L, Martinoli A, Mostafa Y (2002) Emergent specialization in swarm systems. In: Lecture notes in computer science, vol 2412. Intelligent data engineering and automated learning. Springer, Berlin, pp. 261–266Google Scholar
  28. 28.
    Moriarty D (1997) Symbiotic evolution of neural networks in sequential decision tasks. PhD thesis, Department of Computer Sciences, The University of Texas, AustinGoogle Scholar
  29. 29.
    Moriarty D, Miikkulainen R (1996) Efficient reinforcement learning through symbiotic evolution. Mach Learn 22(1):11–33Google Scholar
  30. 30.
    Murciano A, Millan J (1997) Learning signaling behaviors and specialization in cooperative agents. Adapt Behav 5(1):5–28CrossRefGoogle Scholar
  31. 31.
    Nitschke G (2007) Neuro-evolution methods for designing emergent specialization. In: Proceedings of the ninth European conference on artificial life. Springer, Lisbon, pp. 1120–1130Google Scholar
  32. 32.
    Nitschke G (2008) Neuro-evolution for emergent specialization in collective behavior systems. PhD thesis, Computer Science Department, Vrije Universiteit, AmsterdamGoogle Scholar
  33. 33.
    Nitschke G, Schut M, Eiben A (2006) Collective specialization for evolutionary design of a multi-robot system. In: Proceedings of the second international workshop on swarm robotics. Springer, Rome, pp. 189–206Google Scholar
  34. 34.
    Nitschke G, Schut M, Eiben A (2007) Emergent specialization in biologically inspired collective behavior systems. In: Intelligent complex adaptive systems. IGI, New York, pp. 100–140Google Scholar
  35. 35.
    Nolfi S, Baldassarre G, Parisi D (2003) Evolution of collective behaviour in a team of physically linked robots. In: Applications of evolutionary computing. Springer, Berlin, pp. 581–592Google Scholar
  36. 36.
    Nolfi S, Deneubourg J, Floreano D, Gambardella L, Mondada F, Dorigo M (2003) Swarm-bots: swarm of mobile robots able to self-assemble and self-organize. Ecrim News 53(1):25–26Google Scholar
  37. 37.
    Potter M, De Jong K (2000) Cooperative coevolution: an architecture for evolving coadapted subcomponents. Evol Comput 8(1):1–29CrossRefGoogle Scholar
  38. 38.
    Potter M, De Jong K, Grefenstette J (1995) A co-evolutionary approach to learning sequential decision rules. In: Proceedings of the sixth international conference on genetic algorithms. Morgan Kaufmann, San Franciso, pp. 366–372Google Scholar
  39. 39.
    Potter M, De Jong K (1994) A cooperative coevolutionary approach to function optimization. In: Proceedings of the third conference on parallel problem solving from nature (PPSN III). Springer, Jerusalem, pp. 249–257Google Scholar
  40. 40.
    Potter M, Meeden L, Schultz A (2001) Heterogeneity in the coevolved behaviors of mobile robots: the emergence of specialists. In: Proceedings of the international joint conference on artificial intelligence. AAAI Press, Seattle, pp. 1337–1343Google Scholar
  41. 41.
    Quinn M (2000) Evolving cooperative homogeneous multi-robot teams. In: Proceedings of the international conference on intelligent robots and systems (IROS 2000). IEEE Press, Takamatsu, pp. 1798–1803Google Scholar
  42. 42.
    Quinn M (2001) A comparison of approaches to the evolution of homogeneous multi-robot teams. In: Proceedings of the congress evolutionary computation. IEEE Press, Seoul, pp. 128–135Google Scholar
  43. 43.
    Quinn M, Smith L, Mayley G, Husbands P (2009) Evolving teamwork and role-allocation with real robots. In: Proceedings of the 8th international conference on artificial life. MIT Press, Cambridge, pp. 302–311Google Scholar
  44. 44.
    Resnick M (1997) Turtles, termites, and traffic jams: explorations in massively parallel microworlds. MIT Press, CambridgeGoogle Scholar
  45. 45.
    Schaffer J, Whitley D, Eshelman L (1992) Combinations of genetic algorithms and neural networks: a survey of the state of the art. In: Whitley D, Schaffer J (eds) Proceedings of an international workshop on the combinations of genetic algorithms and neural networks (COGANN-92). IEEE Press, New YorkGoogle Scholar
  46. 46.
    Schultz A, Bugajska M (2000) Co-evolution of form and function in the design of autonomous agents: micro air vehicles project. In: Proceedings of the workshop on evolution of sensors in nature, hardware, and simulation, GECCO. AAAI Press, Chicago, pp. 154–166Google Scholar
  47. 47.
    Schultz C, Parker L (2002) Multi-robot systems: from swarms to intelligent automata. Kluwer, Washington DCGoogle Scholar
  48. 48.
    Seligmann H (1999) Resource partition history and evolutionary specialization of subunits in complex systems. Biosystems 51(1):31–39CrossRefGoogle Scholar
  49. 49.
    Stanley K, Bryant B, Miikkulainen R (2005) Evolving neural network agents in the nero video game. In: Proceedings of the IEEE 2005 symposium on computational intelligence and games. IEEE Press, Piscataway, pp. 182–189Google Scholar
  50. 50.
    Stanley K, Bryant B, Miikkulainen R (2005) Real-time neuro-evolution in the nero video game. IEEE Trans Evol Comput 9(6):653–668CrossRefGoogle Scholar
  51. 51.
    Wenseleers T, Ratnieks F, Billen J (2003) Caste fate conflict in swarm-founding social hymenoptera: an inclusive fitness analysis. Evol Biol 16(1):647–658Google Scholar
  52. 52.
    Whiteson S, Kohl N, Miikkulainen R, Stone P (2003) Evolving keep-away soccer players through task decomposition. In: Proceeding of the genetic and evolutionary computation conference. AAAI Press, Chicago, pp. 356–368Google Scholar
  53. 53.
    Whiteson S, Kohl N, Miikkulainen R, Stone P (2005) Evolving keepaway soccer players through task decomposition. Mach Learn 59(1):5–30CrossRefGoogle Scholar
  54. 54.
    Wiegand R (2004) An analysis of cooperative coevolutionary algorithms. PhD. Thesis, George Mason University Press, George Mason University, FairfaxGoogle Scholar
  55. 55.
    Wineberg M, Oppacher F (2003) The underlying similarity of diversity measures used in evolutionary computation. In: Proceedings of the genetic and evolutionary computation conference. Springer, Berlin, pp. 1493–1504Google Scholar
  56. 56.
    Yao X (1993) Evolutionary artificial neural networks. J Neural Syst 4(3):203–222CrossRefGoogle Scholar
  57. 57.
    Yong C, Miikkulainen R (2007) Coevolution of role-based cooperation in multi-agent systems. Technical Report AI07-338. Department of Computer Sciences, The University of Texas, AustinGoogle Scholar
  58. 58.
    Young L, Pisanich G, Ippolito C (2005) Aerial explorers. In: Proceeding of the 43rd AIAA aerospace sciences meeting and exhibit. AIAA Press, Reno, pp. 4–12Google Scholar

Copyright information

© Springer-Verlag 2009

Authors and Affiliations

  1. 1.Computational Intelligence Research Group, Department of Computer ScienceUniversity of PretoriaPretoriaSouth Africa
  2. 2.Computational Intelligence GroupVrije Universiteit AmsterdamAmsterdamThe Netherlands

Personalised recommendations