Neural and neurofuzzy FELA adaptive robot control using feedforward and counterpropagation networks

In this paper, the application of neural networks and neurofuzzy systems to the control of robotic manipulators is examined. Two main control structur es are presented in a comparative manner. The first is a Counter propagatio n Network-based Fuzzy Controller (CPN-FC) which is able to self-organize an d correct on-line its rule base. The self-tuning capability of the fuzzy lo gic controller is attained by taking advantage of the structural equivalenc e between the fuzzy logic controller and a counterpropagation network. The second control structure is a more familiar neural adaptive controller base d on a feedforward (MLP) network. The neural controller learns the inverse dynamics of the robot joints, and gradually eliminates the model uncertaint ies and disturbances. Both schemes cooperate with the computed torque contr ol algorithm, and in that way the reduction of their complexity is achieved . The ability of adaptive fuzzy systems to compete with neural networks in difficult control problems is demonstrated. A sufficient set of numerical r esults is included.