Robot manipulator control with soft computing - application of adaptive friction models

The resolved acceleration control method is one of the most effective and fundamental control methods for robot manipulators. However, friction of each joint of a manipulator impedes control accuracy. Therefore, friction has to be effectively compensated for in order to realize precise control of robot manipulators. Recently, soft computing, such as fuzzy reasoning, neural networks, and genetic algorithms, have been playing an important role in the control of robots. Applying soft computing, learning/adaptation ability and human knowledge can be incorporated into a robot controller. In this paper, we propose an effective robot manipulator fuzzy-neuro control method based on the resolved acceleration control method in which joint friction is effectively compensated for using adaptive friction models.