Robot control using the feedback-error-learning rule with variable feedback gain

A problem plaguing the application of neural networks in all fields is the difficulty of incorporating prior information to constrain the possible functions that the network can represent. This problem is addressed and solved in a robot control application. The authors present the numerical results of extensive simulations where the main interest is to investigate the generalization ability of the networks when applied to the dynamical robot control problem. They restrict the network weights to a plausible region, obtained from prior information, in order to improve the generalization. They simultaneously reduce the gains of the feedback controller to improve the learning rate