Compensation of unmodeled friction in manipulators using neural networks

A neural network compensator augmented computed torque control scheme for the compensation of unmodeled frictional effects in manipulators is proposed. The proposed compensator is implemented by a three layer network structure. A weight adaptation methodology based on the extended Kalman filter algorithm is used. Computer simulations are performed to verify and study the stability, convergence and trajectory tracking performance of the proposed control architecture. Results from the simulations show that the training algorithm derived from the extended Kalman filter is stable. Convergence is also verified. The simulations also show the stability of the computed torque control law augmented by the neural network compensator approximating the unmodeled frictional terms