A CONCURRENT LEARNING ALGORITHM OF FORWARD AND INVERSE MODELS USING FEEDBACK ERROR LEARNING IN THE EARLY-STAGE

This paper proposes a concurrent learning algorithm for forward and in verse modeling. The algorithm is consisted of two phases. In the first phase, a feedback controller is used. The forward model is trained us ing the output values of the controller as the input values to the sys tem and the inverse model is trained by the feedback error learning. I n the second phase, the forward model and the inverse model are traine d at the same time. By the simulation experiments in a two-link manipu lator, it is confirmed that our algorithm can converge faster than the ones already proposed.