Incorporating Reactive Learning Behaviour into a Mini-robot Platform

  • Mark Elshaw
  • Debra Lewis
  • Stefan Wermter
Conference paper


In the Neuro-robotics Lab of the Centre for Hybrid Intelligent Systems we have organised various challenging undergraduate student projects using Mindstorm, Khepera and PeopleBot robots. In this paper we will describe a particularly interesting undergraduate student project involving the introduction of intelligent behaviour onto a mini-robot platform. In the past robots were mainly hardcoded to perform actions that limited their adaptability to their environment. As a response to this problem there has been considerable interest in producing robots that can learn. By developing a fly-catcher robot scenario using a mini-robot platform it was possible to consider the incorporation of learned intelligent behaviour for navigation and the use of object recognition. In doing so neural network learning was incorporated into a mini-robot. This research offers a restricted insight for robot users into issues associated with intelligent goal-directed learning on mini-robots that are also applicable to those using more sophisticated robots including our work on the MirrorBot (Biomimetic multimodal learning in a mirror neuron-based robot) project.


Object Recognition Mirror Neuron Touch Sensor Intelligent Behaviour Robot Action 
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.
    Baum, D. Dave Baum’s Definitive Guide to Lego Mindstorms, Apress, 2000.Google Scholar
  2. 2.
    Baum, D., Gasperi, M., Hempel, R. & Villa, L. Extreme mindstorm: advanced guide to LEGO mindstorm. Apress, 2000.Google Scholar
  3. 3.
    Nagata, J. Lego Mindstorms idea book, Starch Press, 2001.Google Scholar
  4. 4.
    Penfold, R. More Advanced Robotics with Lego Mindstorms. Bernard Babani (Publishing) Ltd, 2000.Google Scholar
  5. 5.
    Sato, J. Jim Sato’s Lego mindstorms: The master’s technique. Starch Press, 2001.Google Scholar
  6. 6.
    Rizzolatti G, & Arbib, M. Language within our grasp. Trends in Neuroscience, 1998; 21: 188–194.Google Scholar
  7. 7.
    Umilta, M. Kohler, E. Gallese, V., Fogassi, L. Fadiga, L., Keysers, C. & Rizzolatti, G. I know what you are doing: A neurophysical study. Neuron, 2001; 31:31.Google Scholar
  8. 8.
    Schaal, S. Is imitation learning the route to humanoid robots. Trends in Cognitive Science, 1999; 3(6): 233–242.CrossRefGoogle Scholar
  9. 9.
    Araujo, A. & Barrato, G. A self-organizing context-based approach to the tracking of multiple robot trajectories. International Journal of Computer Research, 2001; 10(2): 139–179.Google Scholar
  10. 10.
    Elshaw M., Wermter S. & Watt P. Self-organisation of language instruction for robot action. Proceedings of the International Joint Conference on Neural Networks. Oregon, USA, July 2003.Google Scholar
  11. 11.
    Wermter S. & Elshaw M. Learning robot actions based on self-organising language memory. Neural Networks, 2003, 16(5-6): 661–669.CrossRefGoogle Scholar
  12. 12.
    Calabretta, R., Nolfi, S., Parisi, D. & Wagner, P. Emergence of functional modularity in robots. In Proceedings of Artificial Life VI, Los Angeles, Editors C. Adami, R. Belew, H. Kitano and C. Taylor, MIT Press, 1998.Google Scholar
  13. 13.
    Kazer, J. & Sharkey, A. The role of memory, anxiety and Hebbian learning in hippocampal function: Novel explorations in computational neuroscience and robotics. In Emergent Neural Computational Architectures based on Neuroscience, Editors S. Wermter, J. Austin, and D. Willshaw, SpringerVerlag, Heidelberg, Germany, 2001, pp. 507–521.CrossRefGoogle Scholar
  14. 14.
    Pérez-Uribe, A. Using a time-delay actor-critic neural architecture with dopamine-like reinforcement signal for learning in autonomous robots, In Emergent Neural Computational Architectures based on Neuroscience, Editors S. Wermter, J. Austin, and Willshaw, D., Springer-Verlag, Heidelberg, Germany, 2001, pp. 522–533.CrossRefGoogle Scholar
  15. 15.
    Demiris, Y. Biologically inspired robot imitation mechanisms and their application as models of mirror neurons. Proceedings of the EPSRC/BBSRC International Workshop on Biological Inspired Robotics Bristol 14-16 August, 2002.Google Scholar
  16. 16.
    Kohonen, T. Self-organizing maps. Springer Verlag, Heidelberg, Germany, 1997.MATHCrossRefGoogle Scholar
  17. 17.
    McClelland, J. & Rumelhart, D. Mechanisms of sentence processing: assigning roles to constituents of sentences. Parallel Distributed Processing: Explorations in the Microstructure of Cognition Vo1.2, MIT Press, Cambridge MA, 1986, pp. 272–325.Google Scholar
  18. 18.
    Beale, R. & Jackson, T. Neural computing an introduction. IOP Ltd, 1990, pp.39–128.Google Scholar
  19. 19.
    Nehmzow, U. Meaning through clustering by self-organisation of spatial and temporal information. Computation for Metaphors, Analogy and Agents, Editor C. Nehaniv, Springer-Verlag, Heidelberg, Germany1999, pp. 209–299.CrossRefGoogle Scholar
  20. 20.
    Weber C. & Wermter S. Object localisation using laterally connected “What” and “Where” associator networks. Proceedings of the International Conference on Artificial Neural Networks, Istanbul, Turkey, pp. 813–820, 2003.Google Scholar
  21. 21.
    Wilson, J. & Mitchell, R. Object detecting artificial retina. Kybernetes: The International Journal of Systems and Cybernetics, 2002; 29(1): 31–52.CrossRefGoogle Scholar
  22. 22.
    Cipolla, R., Hollinghurst, N., Gee, A. & Dowland, R. Computer vision in interactive robotics. Assembly Automation, 1996, 16(1): 18–24.CrossRefGoogle Scholar
  23. 23.
    Roy, D. & Pentland, A. Learning words from sights and sounds: A computational model. Cognitive Science, 2002; 26(1), 113–146.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2004

Authors and Affiliations

  • Mark Elshaw
    • 1
  • Debra Lewis
    • 1
  • Stefan Wermter
    • 1
  1. 1.School of Computing and Technology, Centre for Hybrid Intelligent SystemsUniversity of SunderlandSunderlandUK

Personalised recommendations