MULTILEVEL DARWINIST BRAIN IN ROBOTS - Initial Implementation

Francisco Bellas, Richard J. Duro

2004

Abstract

In this paper we present a Cognitive Mechanism called MDB (Multilevel Darwinist Brain) based on Darwinist theories and its initial application to autonomous learning by robotic systems. The mechanism has been designed to permit an agent to adapt to its environment and motivations in an autonomous way. The general structure of the MDB is particularized into a two level architecture: reasoning and interaction. This structure corresponds to a generic cognitive model where world, internal and satisfaction models are used to select strategies that fulfil the motivation of the agent. The main idea behind the proposal is that all of the components of the mechanism are obtained and modified through interaction with the environment in real time by means of on line Darwinist processes, allowing for a natural learning curve. The mechanism is able to provide solutions based on experience or original solutions to new situations. The knowledge used by the agent is acquired automatically and not imposed by the designer. Here we discuss the basic operation of the mechanism and demonstrate it through a real example in which a hexapod robot is taught to walk efficiently and to reach an objective in its surroundings.

References

  1. Agre, P. E., Chapman, D. 1987. Pengi: An implementation of a theory of activity. American Association for Artificial Intelligence. pp 268-272
  2. Bellas F., Becerra J.A., Santos J. and Duro R.J., 2000. Applying Synaptic Delays for Virtual Sensing and Actuation in Mobile Robots. Proc IJCNN 2000. pp 6144-6153
  3. Beer R., Quinn R., Chiel H., Ritzmann R. 1997. Biologically Inspired Approaches to Robotics. Communications of the ACM, V.40 N. 3, pp 30-38
  4. Bratman, M., Israel, D., Pollack, M., 1988. Plans and Resourcebounded Practical Reasoning. Computational Intelligence, 4. pp 349-355.
  5. Brooks, R., 1986. A Robust Layered Control System for a Mobile Robot. IEEE J. Robotics and Automation RA-2 (1). pp 14-23
  6. Changeux, J., Courrege, P., Danchin, A., 1973. A Theory of the Epigenesis of Neural Networks by Selective Stabilization of Synapses, Proc.Nat. Acad. Sci. USA 70, pp 2974-2978
  7. Changeux, J., Danchin, A., 1976. Selective Stabilization of Developing Synapsis as a Mechanism for the Specification of Neural Networks. Nature 264. pp 705-712.
  8. Changeux, J., Heidmann, T., Patte, P., 1984 Learning by Selection. Springer-Verlag
  9. Chapman, D., 1987. Planning for conjunctive goals, Artificial Intelligence, 32, pp 333-378
  10. Conrad, M, 1974. Evolutionary Learning Circuits. Theor. Biol. 46, pp 167-188
  11. Conrad, M., 1976. Complementary Molecular Models of Learning and Memory. BioSystems 8, pp 119-138
  12. Edelman, G., 1987. Neural Darwinism. The Theory of Neuronal Group Selection. Basic Books
  13. Floreano, D., Mondada, F., 1996. Evolution of Homing Navigation in a Real Mobile Robot. IEEE Trans. on Sys. Man and Cybernetics Part B, 26(3), pp 396-407.
  14. Kaelbling L., 1986. An Architecture for Intelligent Reactive Systems. Reasoning about Actions and Plans. Proceedings for the 1986 Workshop. pp 395-410
  15. Maes, P., 1991. The Agent Network Architecture (ANA)" SIGART Bulletin, 2(4), pp 115-120.
  16. Yao, X., Liu, Y., Darwen, P., 1996. How to make best use of evolutionary learning. Complex Systems: From Local Interactions to Global Phenomena, pp 229-242.
Download


Paper Citation


in Harvard Style

Bellas F. and Duro R. (2004). MULTILEVEL DARWINIST BRAIN IN ROBOTS - Initial Implementation . In Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 972-8865-12-0, pages 25-32. DOI: 10.5220/0001140700250032


in Bibtex Style

@conference{icinco04,
author={Francisco Bellas and Richard J. Duro},
title={MULTILEVEL DARWINIST BRAIN IN ROBOTS - Initial Implementation },
booktitle={Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2004},
pages={25-32},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001140700250032},
isbn={972-8865-12-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - MULTILEVEL DARWINIST BRAIN IN ROBOTS - Initial Implementation
SN - 972-8865-12-0
AU - Bellas F.
AU - Duro R.
PY - 2004
SP - 25
EP - 32
DO - 10.5220/0001140700250032