Abstract
This paper describes a procedure to provide a way for the Multilevel Darwinist Brain evolutionary cognitive architecture to be able to learn and preserve procedural knowledge while operating on-line. This procedural knowledge is acquired in the form of ANNs that implement behaviors in the sense of traditional evolutionary robotics. The behaviors are produced in real time as the robot is interacting with the world. It is interesting to see in the results presented that this approach of learning procedural representations instead of exhaustively selecting the appropriate action every instant of time provides better generalization results and more efficient action sequences.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Asada, M., MacDorman, K.F., Ishiguro, H., Kuniyoshi, Y.: Cognitive developmental robotics as a new paradigm for the design of humanoid robots. Robot. Auton. Syst. 37, 185–193 (2001)
Krichmar, J.L., Edelman, G.M.: Principles underlying the construction of brain-based devices. In: Proceedings of AISB 2006, vol. 2, pp. 37–42 (2006)
Laird, J.E.: Extending the soar cognitive architecture. In: Proceeding of the 2008 Conference on Artificial General Intelligence, pp. 224–235. IOS Press, Amsterdam (2008)
Franklin, S.: Cognitive robots: perceptual associative memory and learning. In: IEEE International Workshop on Robot and Human Interactive Communication, pp. 427–433 (2005)
Bach, J.: Principles of synthetic intelligence PSI: an architecture of motivated cognition, 1st edn. Oxford University Press Inc., New York (2009)
Goertzel, B., de Garis, H.: XIA-MAN: an extensible, integrative architecture for intelligent humanoid robotics. In: Proceedings of the BICA 2008, pp. 86–90 (2008)
Kawamura, K., Gordon, S., Ratanaswasd, P., Erdemir, E., Hall, J.: Implementation of cognitive control for a humanoid robot. Int. J. Humanoid Rob. 5(4), 547–586 (2008)
Atkinson, R., Shiffrin, R.: Human memory: A proposed system and its control processes. Psychol. Learn. Motivation 2, 89–195 (1968)
Baddeley, A.D., Hitch, G.: Working memory. In: Bower, G.H. (ed.) The Psychology of Learning and Motivation: Advances in Research and Theory, vol. 8, pp. 47–89 (1974)
Solms, M., Turnbull, O.: The Brain and the Inner World. Karnac/Other Press, Cathy Miller Foreign Rights Agency, London (2002)
Cowan, N.: What are the differences between long-term, short-term, and working memory? Prog. Brain Res. 169, 323–338 (2008)
Duro, R.J., Santos, J., Bellas, F., Lamas, A.: On line darwinist cognitive mechanism for an artificial organism. In: Proceedings Supplement Book SAB2000, pp. 215–224 (2000)
Bellas, F., Duro, R.J.: Multilevel darwinist brain in robots, initial implementation. In: Proceedings IROS 2004, pp. 25–32 (2004)
Bellas, F., Becerra, J.A., Duro, R.J.: Induced behavior in a real agent using the multilevel darwinist brain. In: Mira, J., Álvarez, J.R. (eds.) IWINAC 2005. LNCS, vol. 3562, pp. 425–434. Springer, Heidelberg (2005)
Bellas, F., Becerra, J.A., Duro, R.J.: Internal and external memory in neuroevolution for learning in non-stationary problems. In: Asada, M., Hallam, J.C., Meyer, J.-A., Tani, J. (eds.) SAB 2008. LNCS (LNAI), vol. 5040, pp. 62–72. Springer, Heidelberg (2008)
Bellas, F., Duro, R.J., Faiña, A., Souto, D.: Multilevel Darwinist Brain (MDB): Artificial evolution in a cognitive architecture for real robots. IEEE Trans. Auton. Ment. Dev. 2(4), 340–354 (2010)
Santos-Diez, B., Bellas, F., Faiña, A., Duro, R.J.: Lifelong learning by evolution in robotics: Bridging the gap from theory to reality. In: Proceedings EIS 2010, pp. 48–53 (2010)
Duro, R.J., Bellas, F., Caamaño, P., Varela, G.: Automatic model decomposition and reuse in an evolutionary cognitive mechanism. Evol. Syst. 1(2), 129–141 (2010)
Duro, R.J., Bellas, F., Becerra, J.A.: Evolutionary architecture for lifelong learning and real-time operation in autonomous robots. In: Angelov, P., Filev, D.P., Kasabov, N. (eds.) Evolving Intelligent Systems: Methodology and Applications. Wiley, Hoboken (2010)
Bellas, F., Caamaño, P., Faiña, A., Duro, R.J.: Dynamic learning in cognitive robotics through a procedural long term memory. Evol. Syst. 5(1), 49–63 (2014)
Duro, R.J., Bellas, F., Becerra, J.A., Salgado, R.: A role for sleep in artificial cognition through deferred restructuring of experience in autonomous machines. In: del Pobil, A.P., Chinellato, E., Martinez-Martin, E., Hallam, J., Cervera, E., Morales, A. (eds.) SAB 2014. LNCS, vol. 8575, pp. 1–10. Springer, Heidelberg (2014)
Caamaño, P., Tedín, R., Paz-López, A., Becerra, J.A.: JEAF: A java evolutionary algorithm framework. In: Proceedings WCCI 2010, pp. 3081–3088 (2010)
Acknowledgements
Funding for this work was related to the preparation of the DREAM project in the EU’s H2020 R&I programme under grant agreement No 640891.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Salgado, R., Bellas, F., Duro, R.J. (2015). Autonomous Learning of Procedural Knowledge in an Evolutionary Cognitive Architecture for Robots. In: Mora, A., Squillero, G. (eds) Applications of Evolutionary Computation. EvoApplications 2015. Lecture Notes in Computer Science(), vol 9028. Springer, Cham. https://doi.org/10.1007/978-3-319-16549-3_65
Download citation
DOI: https://doi.org/10.1007/978-3-319-16549-3_65
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16548-6
Online ISBN: 978-3-319-16549-3
eBook Packages: Computer ScienceComputer Science (R0)