On some peculiarities of neural network approximation applied to the inverse kinematics problem

Characteristic features of feedforward artificial neural networks, acting as universal function approximators, are presented. The problem under consideration concerns inverse kinematics of a two-link planar manipulator. As shown in the article, a two-layer, feedforward neural network is able to learn the nonlinear mapping between the end-effector position domain and the joint angle domain of the manipulator. However, the necessary condition for achieving the required approximation quality is the selection of suitable network structure, especially with regard to the number of nonlinear, sigmoidal units in its hidden layer. Effects of learning algorithm and choice of learning data set on the network performance are also demonstrated.