A Neural Model for Animats Brain

  • Guillaume Beslon
  • Hédi Soula
  • Joël Favrel
Conference paper


We propose a model of neural controller, the NeuroReactive controller, which is designed to exhibit both the learning abilities of artificial neural networks and the modular structure of reactive control. This model is based on Asynchronous Spikes Propagation (ASP) in a rank-based neural network. The asynchronous propagation of activity interacts with the internal/external loops in which the animat is involved, leading behavioral modules to emerge in the network, in the form of functional clusters.


Neural Controller Modular Neural Network Neural Assembly Subsumption Architecture Transportation Task 
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]
    G. Beslon, F. Biennier, and J. Favrel. A flexible conveying system based on autonomous vehicles. In proc. of CARs and FoF’95, Colombia, pages 115–120, 1995.Google Scholar
  2. [2]
    R.A. Brooks. Intelligence without reason. In Proc. of IJGAI’91, pages 569–595, 1991.Google Scholar
  3. [3]
    E. Domany, J.L.V. Van Hemmen, and K. Schulten (Eds). Model of Neural Networks II; Temporal Aspects of Coding and Information Processing in Biological Systems. Springer-Verlag, 1994.Google Scholar
  4. [4]
    A.J.C. Sharkey (Eds). Combining Artificial Neural Nets; Ensemble and Modular Multi-Net Systems. Springer-Verlag, 1999.Google Scholar
  5. [5]
    J.J. Hopfield. Pattern recognition computation using action potential timing for stimulus representation. nature, 376(6535):33-36, jul 1995.Google Scholar
  6. [6]
    S. Nolfi. Using emergent modularity to develop control systems for mobile robots. Adaptive Behavior, 5(3/4):343–363, 1997.CrossRefGoogle Scholar
  7. [7]
    M. Samuelides, S. Thorpe, and E. Veneau. Implementing hebbian learning in a rank-based neural network. In Proc. of IGANN’97, Lausanne, pages 145–150, 1997.Google Scholar
  8. [8]
    W. Singer. Synchronization of cortical activity and its putative role in information processing and learning. Annual Review of Physiology, (55):349–374, 1993.Google Scholar
  9. [9]
    T. Ziemke. On parts and wholes of adaptive behavior: Functional modularity and diachronic structure in reccurrent neural robot controllers. In Proc. of Int. Gonf. on Simulation of Adaptive Behavior, Paris, pages 115–124, 2000.Google Scholar

Copyright information

© Springer-Verlag Wien 2001

Authors and Affiliations

  • Guillaume Beslon
  • Hédi Soula
  • Joël Favrel
    • 1
  1. 1.PRISMa Lab.INSA de LyonVilleurbanneFrance

Personalised recommendations