Multiscale Dynamic Learning in Cognitive Robotics

  • Pilar Caamaño
  • Andrés Faíña
  • Francisco Bellas
  • Richard J. Duro
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7931)


This paper is concerned with the dynamics of Cognitive Developmental Robotic architectures and how to produce structures that allow these types of architectures to deal with the different time scales a robot must cope with. The most important types of dynamics that occur in different time scales are defined and different mechanisms within a particular cognitive architecture, the Multilevel Darwinist Brain, are suggested to model each one of them. The paper also proposes a novel neuroevolutionary technique, called τ-NEAT, in order to capture processes based on precise temporal cues. This technique is analyzed when addressing dynamic environments in a real robotic test.


Cognitive Robotics Dynamic Learning Neuroevolution NEAT Delay-Based ANN 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Byrne, M.D.: Cognitive architecture. The Humancomputer Interaction Handbook 44(1), 97–117 (2003)Google Scholar
  2. 2.
    Asada, M., Hosoda, K., Kuniyoshi, Y., Ishiguro, H., Inui, T., Yoshikawa, Y., Ogino, M., Yoshida, C.: Cognitive Developmental Robotics: A Survey. IEEE Trans. on Autonomous Mental Development 1(1), 12–34 (2009)CrossRefGoogle Scholar
  3. 3.
    Weng, J.: On developmental mental architectures. Neurocomputing 70(13-15), 2303–2323 (2007)CrossRefGoogle Scholar
  4. 4.
    Weng, J., Hwang, W.S., Zhang, Y., Evans, C.H.: Developmental Robots?: Theory, Method and Experimental Results. In: Proc. of the Int. Symposium on Humanoid Robots, pp. 57–64 (1999)Google Scholar
  5. 5.
    Morse, A.F., Greeff, J.D., Belpeame, T., Cangelosi, A.: Epigenetic Robotics Architecture (ERA). IEEE Trans. on Autonomous Mental Development 2(4), 325–339 (2010)CrossRefGoogle Scholar
  6. 6.
    Vernon, D.: Enaction as a conceptual framework for developmental cognitive robotics. Paladyn 1(2), 89–98 (2010)CrossRefGoogle Scholar
  7. 7.
    Baranes, A., Oudeyer, P.Y.: R-IAC: Robust intrinsically motivated exploration and active learning. IEEE Trans. on Autonomous Mental Development 1(3), 155–169 (2009)CrossRefGoogle Scholar
  8. 8.
    Bellas, F., Duro, R.J., Faina, A., Souto, D.: Multilevel Darwinist Brain (MDB): Artificial Evolution in a Cognitive Architecture for Real Robots. IEEE Trans. on Autonomous Mental Development 2(4), 340–354 (2010)CrossRefGoogle Scholar
  9. 9.
    Bellas, F., Becerra, J.A., Duro, R.J.: Construction of a Memory Management System in an On-line Learning Mechanism. In: Proceedings ESANN 2006, pp. 26–28 (2006)Google Scholar
  10. 10.
    Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)CrossRefGoogle Scholar
  11. 11.
    Stanley, K.O.: Efficient Reinforcement Learning through Evolving Neural Network Topologies. In: Proceedings of the GECCO 2002 Conference, pp. 569–577 (2002)Google Scholar
  12. 12.
    Stanley, K.O., Bryant, B.D., Miikkulainen, R.: Real-time neuroevolution in the NERO video game. IEEE Trans. on Evolutionary Computation 9(6), 653–668 (2005)CrossRefGoogle Scholar
  13. 13.
    Duro, R.J., Reyes, J.S.: Discrete-time backpropagation for training synaptic delay-based artificial neural networks. IEEE Trans. on Neural Networks 10(4), 779–789 (1999)CrossRefGoogle Scholar
  14. 14.
    Salgado, R., Bellas, F., Santos-Diez, B., Caamaño, P., Duro, R.J.: A Procedural Long Term Memory for Cognitive Robotics. Optimizing Adaptive Learning in Dynamic Environments. In: Proceedings of the EAIS 2012 Coference, pp. 1–8 (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Pilar Caamaño
    • 1
  • Andrés Faíña
    • 1
  • Francisco Bellas
    • 1
  • Richard J. Duro
    • 1
  1. 1.Integrated Group for Engineering ResearchUniversidade da CoruñaFerrolSpain

Personalised recommendations