ON THE COMPUTATION OF THE DIRECT KINEMATICS OF PARALLEL MANIPULATORS USING POLYNOMIAL NETWORKS

Polynomial learning networks are proposed in this paper to solve the f orward kinematic problem for a planar three-degree-of-freedom parallel manipulator with revolute joints, These networks rapidly learn comple x nonlinear functions based on a database mapping. The networks learn the forward kinematics of the manipulator based on examples of the tra nsformation. The obtained networks are then used to follow a test traj ectory, For comparison purposes, a neural network approach using backp ropagation is also used for this problem. The results show that, in th is application, polynomial networks learn much faster and exhibit less error than neural networks.