CMAC neural network method with application to kinematics control of a redundant manipulator

The inverse kinematics problems of redundant manipulators have been investigated for many years. The conventional method of solving this problem is through applying the Jacobian Pseudoinverse Algorithm, which is effective and able to resolve the redundancy for a redundant manipulator. However, computational effort makes it not suitable for real time control. Recently, neural networks have been widely used in robotic control because they are fast, fault-tolerant and able to learn. In this paper, we will present the application of CMAC (Cerebellar Model Articulation Controller) neural network for solving the inverse kinematics problems in real time. Simulations have been carried out for a five-link manipulator in order to evaluate the performance of the CMAC neural network. Through computer simulation, we found CMAC NN method is especially suitable for real time control of robots and solving nonlinear function approximation problem.