Solution to the inverse kinematics problem in robotics by neural networks

The authors use a neural-network model in the solution of the inverse kinematics problem in robotics. It is found that the neural network can be trained to generate a fairly accurate solution which, when augmented with local differential inverse kinematic methods, results in minimal burden on processing load of each control cycle and thus allows real-time robot control. Further benefits are expected from the natural fault tolerance of the neural network and the elimination of the costly derivation and programming of the inverse kinematic algorithm.<>