This paper describes experimental results applying artificial neural networks to perform the position control of a real scara manipulator robot. The general control strategy consists of a neural controller that operates in parallel with a conventional controller based on the feedback error learning architecture. The main advantage of this architecture is that it does not require any modification of the previous conventional controller algorithm. MLP and RBF neural networks trained on-line have been used, without requiring any previous knowledge about the system to be controlled. These approach has performed very successfully, with better results obtained with the RBF networks when compared to PID and sliding mode positional controllers.