A neural network based positional tracking controller for servo systems

Abstract

Most neural network (NN) based trajectory tracking controllers for servo systems are built on learning explicit inverse dynamics of the system to be controlled. However, due to various complexities in these systems, the learning process may require a large amount of training data to obtain the exact dynamics of the system. To overcome this problem a novel NN based trajectory tracking controller is introduced which neither requires a priori knowledge of the dynamics nor learning of system dynamics. The proposed control scheme incorporates expert knowledge and is decentralized to deactivate the coupled dynamics associated with certain systems like robotic manipulators. The NN is employed to classify the system input-output measurements into several patterns depending on the displacement and velocity deviations from the respective desired trajectories. A proportional plus derivative gain control action is determined from a look-up table corresponding to the classification from the NN. Furthermore, an integrator is applied to enhance system performance. Several PD gains are introduced in a staggered format relative to the magnitudes of the displacement and velocity tracking errors, resulting in a controller that is robust to both structured and unstructured uncertainties.