Modules, Layers, Hierarchies, and Loops Where Artificial Intelligence Meets Ethology and Neuroscience – In Context of Action Selection

  • Pinar Öztürk
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3561)


The paper presents arguments for why AI methodologies should be informed of both behavioural science and neuroscience studies, and argues why this is possible. Through identifying the resemblance points, we will discuss whether findings of ethology and neuroscience can be used in the process of design and development of non-classical AI systems. To this end, we focus on a specific example that has long been investigated in all the concerned disciplines: the action selection problem. The paper overviews action selection mechanisms in behaviour-based AI and neuroscience in order to identify the commonalities that underly the understanding of action selection in different disciplines, and that may constitute the pieces of a common language with which AI can communicate ideas and findings to and from ethology and neuroscience.


Action Selection Behaviour Node Subsumption Architecture Action Selection Process Action Selection Mechanism 
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.
    Marr, D.: Vision: A computational approach. Freeman, San Francisco (1982)Google Scholar
  2. 2.
    Chandrasekaran, B.: Generic tasks involved in knowledge-based reasoning: High-level building blocks for expert system design. IEEE expert 1, 23–29 (1986)CrossRefGoogle Scholar
  3. 3.
    Brooks, R.: Intelligence without representation. Artificial Intelligence, 139–159 (1991)Google Scholar
  4. 4.
    Minsky, M.: The society of mind. Simon and Schuster, New York (1986)Google Scholar
  5. 5.
    Newell, A.: The knowledge level. Artificial Intelligence 18, 87–127 (1982)CrossRefGoogle Scholar
  6. 6.
    Maes, P.: Situated agents can have goals. Robotics and Autonomous Systems, 49–70 (1990)Google Scholar
  7. 7.
    Rosenblatt, K.J.: A distributed architecture for mobile navigation. PhD thesis (1997)Google Scholar
  8. 8.
    Arkin, R.C.: Behaviour-based Robotics. MIT press, Cambridge (1998)Google Scholar
  9. 9.
    Graybiel, A., Saka, E.: The basal ganglia and the control of action. In: Gazzaniga, M.S. (ed.) The cognitive neuroscience III, xx, pp. 495–510 (2004)Google Scholar
  10. 10.
    Weedman Molavi, D.: Tutorial (2005),
  11. 11.
    Gurney, K., Humpries, R.W., Prescott, T.J., Redgrave, P.: Testing computationa hypotheses of brain systems function: a case study with the basal ganglia. Network: Computation in neural systems, 263–290 (2004)Google Scholar
  12. 12.
    Montes-Gonzales, F.: A robot model of action selection in the vertebrate brain. Sheffield University (2001)Google Scholar
  13. 13.
    Tyrrell, T.: Computational mechanisms for action selection. Center for cognitive science. University of Edinburg (1993)Google Scholar
  14. 14.
    Blumberg, B., Todd, P., Maes, P.: No bad dogs: Ethological lessons for learning in hamsterdam. In: From animals to animats, pp. 295–304. MIT Press, Cambridge (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Pinar Öztürk
    • 1
  1. 1.Department of Computer and Information ScienceNorwegian University of Science and Technology (NTNU)TrondheimNorway

Personalised recommendations