Adaptive neural network control system inspired from the cerebro-cerebellar network for manipulation

The present neural network approach for controlling any arbitrary nonlinear plant is based on a model of the cerebro-cerebellar interaction during learning of the new visuomotor transformation. Four main prerequisites are required: the columnar organization of the cerebral cortex, the Marr-Albus-Ito theory of cerebellar learning, the equilibrium point theory of motor control and the differential neurocontroller theory. The convergence of the learning procedure is proved for the linear plant, and is confirmed for nonlinear plants by computer simulation for arm reaching movements in the horizontal plane.