Neural network solution for the forward kinematics problem of a Stewart platform

A multiple neural network structure called cascaded CMAC (cerebella model arithmetic computer) is proposed to solve the forward kinematics problem of a (parallel link manipulator, called a Stewart platform. The cascaded CMAC networks can provide faster learning and the ability to capture both general trends and fine details of unknown nonlinear mapping. The performance of the cascaded CMAC network is compared with the backpropagation network for the same problem, and the results show that the proposed network is able to learn much faster than the backpropagation net