Robot control using neural networks

Abstract

Neural network theory is applied to theoretical robot kinematics to learn accuracy transforms. The network is trained on accuracy data that characterize the actual robot kinematics. The network learns the differences in the joint angles to improve the accuracy between the effector endpoint resulting from the theoretically calculated joint angles and the desired endpoint. The trained network generalizes a stationary vector field of accuracy data in a two-dimensional planar region. Results show that a neural network can increase both the accuracy and the positional repeatability of robots. Application of a neural network reduces required computational power, calibration time, maintenance cost, and engineering time when developing controllers for new robots by its emergent generalization, fault-tolerant, and self-organization properties.