 |
    |
Evolved Motor Primitives and Sequences in a Hierarchical Recurrent Neural Network
Rainer W. Paine and Jun Tani
RIKEN Brain Science Institute, Laboratory for Behavior and Dynamic Cognition, 2-1 Hirosawa, Wako-shi, Saitama, 351-0198, Japanrpaine@brain.riken.jp
tani@brain.riken.jp
Abstract. This study describes how complex goal-directed behavior can evolve in a hierarchically organized recurrent neural network controlling a simulated Khepera robot. Different types of dynamic structures self-organize in the lower and higher levels of a network for the purpose of achieving complex navigation tasks. The parametric bifurcation structures that appear in the lower level explain the mechanism of how behavior primitives are switched in a top-down way. In the higher level, a topologically ordered mapping of initial cell activation states to motor-primitive sequences self-organizes by utilizing the initial sensitivity characteristics of nonlinear dynamical systems. A further experiment tests the evolved controller’s adaptability to changes in its environment. The biological plausibility of the model’s essential principles is discussed.
LNCS 3102, p. 603 ff.
lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2004