Inverse kinematic neuro-control of robotic systems

The emergence of the theory of dynamic neural computing has made it possible to develop neural learning and adaptive schemes that can be used to obtain feasible solutions to complex control problems, such as inverse kinematic control for robotic systems. In this paper, such a neural learning scheme using a multilayered dynamic neural network (MDNN) is proposed. The basic dynamic computing element of the MDNN is a dynamic neural unit (DNU), developed in this paper. The learning and adaptive capabilities of the dynamic neural unit can be used for developing complex dynamic structures. In this paper, the DNU has been used for developing a multilayered dynamic neural network for the inverse kinematic control of a two-linked robot. The validity of the proposed scheme is demonstrated through computer simulation studies. # 1998 Elsevier Science Ltd. All rights reserved.