Adaptive Motor Primitive and Sequence Formation in a Hierarchical Recurrent Neural Network

Abstract

This study describes how complex goal-directed behavior can be obtained through adaptation in a hierarchically organized recurrent neural network using a genetic algorithm. Robot simulations showed that different types of dynamic structures self-organize in the lower and higher levels of the network for the purpose of achieving complex navigation tasks. Behavior primitives are switched in a top-down way through lower level parametric bifurcation structures. 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. The biological plausibility of the model's essential principles is discussed.