Recurrent Fuzzy Cerebellar Model Articulation Controller and Its Application on Robotic Tracking Control

Abstract

A kind of recurrent fuzzy cerebellar model articulation controller (RFCMAC) model is presented. The recurrent network is embedded in the RFCMAC by adding feedback connections on the first layer to embed temporal relations in the network. A nonconstant differentiable Gaussian basis function is used to model the hypercube structure and the fuzzy weight. A gradient descent learning algorithm is used to adjust the free parameters. Simulation experiments are made by applying proposed RFCMAC on robotic manipulator tracking control problem to confirm its effectiveness.