Introducing Novelty Search in Evolutionary Swarm Robotics

  • Jorge Gomes
  • Paulo Urbano
  • Anders Lyhne Christensen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7461)


Novelty search is a recent and promising evolutionary technique. The main idea behind it is to reward novel solutions instead of progress towards a fixed goal, in order to avoid premature convergence and deception. In this paper, we use novelty search together with NEAT, to evolve neuro-controllers for a swarm of simulated robots that should perform an aggregation task. In the past, novelty search has been applied to single robot systems. We demonstrate that novelty search can be applied successfully to multirobot systems, and we discuss the challenges introduced when moving from a single robot setup to a multirobot setup. Our results show that novelty search can outperform the fitness-based evolution in swarm robotic systems, finding (i) a more diverse set of successful solutions to an aggregation task, (ii) solutions with higher fitness scores earlier in the evolutionary runs, and (iii) simpler solutions in terms of the topological complexity of the evolved neural networks.


Hide Neuron Aggregation Task Neural Controller Evolutionary Robotic Behaviour Space 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bahgeçi̇, E., Şahi̇n, E.: Evolving aggregation behaviors for swarm robotic systems: A systematic case study. In: Swarm Intelligence Symposium, pp. 333–340. IEEE, New York (2005)Google Scholar
  2. 2.
    Baldassarre, G., Nolfi, S., Parisi, D.: Evolving mobile robots able to display collective behaviors. Artificial Life 9(3), 255–268 (2003)CrossRefGoogle Scholar
  3. 3.
    Cuccu, G., Gomez, F.: When Novelty Is Not Enough. In: Di Chio, C., Cagnoni, S., Cotta, C., Ebner, M., Ekárt, A., Esparcia-Alcázar, A.I., Merelo, J.J., Neri, F., Preuss, M., Richter, H., Togelius, J., Yannakakis, G.N. (eds.) EvoApplications 2011, Part I. LNCS, vol. 6624, pp. 234–243. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  4. 4.
    Goldberg, D.E.: Simple genetic algorithms and the minimal, deceptive problem. In: Genetic Algorithms and Simulated Annealing. Research Notes in Artificial Intelligence, pp. 74–88. Pitman Publishing, London (1987)Google Scholar
  5. 5.
    Harvey, I., Husbands, P., Cliff, D., et al.: Issues in evolutionary robotics. In: Second Int. Conf. on Simulation of Adaptive Behavior, pp. 364–373. MIT Press, Cambridge (1993)Google Scholar
  6. 6.
    Heaton, J.: Programming Neural Networks with Encog3 in Java. Heaton Research, Chesterfield (2011)Google Scholar
  7. 7.
    Hugues, L., Bredeche, N.: Simbad: An Autonomous Robot Simulation Package for Education and Research. In: Nolfi, S., Baldassarre, G., Calabretta, R., Hallam, J.C.T., Marocco, D., Meyer, J.-A., Miglino, O., Parisi, D. (eds.) SAB 2006. LNCS (LNAI), vol. 4095, pp. 831–842. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  8. 8.
    Kohonen, T.: The self-organizing map. Proc. of the IEEE 78(9), 1464–1480 (1990)CrossRefGoogle Scholar
  9. 9.
    Lehman, J., Stanley, K.O.: Revising the evolutionary computation abstraction: minimal criteria novelty search. In: Genetic and Evolutionary Computation Conf., pp. 103–110. ACM, New York (2010)Google Scholar
  10. 10.
    Lehman, J., Stanley, K.O.: Abandoning objectives: Evolution through the search for novelty alone. Evolutionary Computation 19(2), 189–223 (2011)CrossRefGoogle Scholar
  11. 11.
    Lehman, J., Stanley, K.O.: Evolving a diversity of virtual creatures through novelty search and local competition. In: Genetic and Evolutionary Computation Conf., pp. 211–218. ACM, New York (2011)Google Scholar
  12. 12.
    Mondada, F., Bonani, M., Raemy, X., Pugh, J., Cianci, C., Klaptocz, A., Magnenat, S., Zufferey, J.C., Floreano, D., Martinoli, A.: The e-puck, a robot designed for education in engineering. In: 9th Conf. on Autonomous Robot Systems and Competitions, pp. 59–65. IPCB, Castelo Branco (2009)Google Scholar
  13. 13.
    Mouret, J.: Novelty-based multiobjectivization. New Horizons in Evolutionary Robotics, pp. 139–154. Springer, Berlin (2011)Google Scholar
  14. 14.
    Risi, S., Vanderbleek, S.D., Hughes, C.E., Stanley, K.O.: How novelty search escapes the deceptive trap of learning to learn. In: Genetic and Evolutionary Computation Conf., pp. 153–160. ACM, New York (2009)Google Scholar
  15. 15.
    Soysal, O., Bahgeçi̇, E., Şahi̇n, E.: Aggregation in swarm robotic systems: Evolution and probabilistic control. Turkish Journal of Electrical Eng. 15(2), 199–225 (2007)Google Scholar
  16. 16.
    Stanley, K.O.: Efficient Evolution of Neural Networks Through Complexification. Ph.D. thesis, Dep. of Computer Sciences, The University of Texas, Austin (2004)Google Scholar
  17. 17.
    Stanley, K.O., Miikkulainen, R.: Evolving neural network through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)CrossRefGoogle Scholar
  18. 18.
    Trianni, V., Groß, R., Labella, T.H., Şahin, E., Dorigo, M.: Evolving Aggregation Behaviors in a Swarm of Robots. In: Banzhaf, W., Ziegler, J., Christaller, T., Dittrich, P., Kim, J.T. (eds.) ECAL 2003. LNCS (LNAI), vol. 2801, pp. 865–874. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  19. 19.
    Whitley, L.D.: Fundamental principles of deception in genetic search. In: Foundations of Genetic Algorithms, pp. 221–241. Morgan Kaufmann, San Mateo (1991)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Jorge Gomes
    • 1
    • 3
  • Paulo Urbano
    • 1
  • Anders Lyhne Christensen
    • 2
    • 3
  1. 1.LabMAgFaculdade de Ciências da Universidade de LisboaPortugal
  2. 2.Instituto Universitário de Lisboa (ISCTE-IUL)LisboaPortugal
  3. 3.Instituto de TelecomunicaçõesLisboaPortugal

Personalised recommendations