On-line training solution to modify the inverse kinematic approximation of a robot manipulator

Tác giả: Dinh B.H.

Abstract: This paper describes a new practical approach for approximating the inverse kinematics of a manipulator using an RBFN (Radial Basis Function Network). In fact, sometimes a well-trained network cannot work effectively in the operational phase because the initial network training occurs in an environment that is not exactly the same as the environment where the system is actually deployed. In this paper, an online retraining solution using a “free interference rule” is presented for systems whose characteristics change due to environmental variations. It helps the learning process avoiding the interference where a new training point may upset some of the weights which were trained with previous points. The simulation results prove that the proposed approach is effective.