A Novel Hybrid Adaptive Nonlinear Controller Using Gaussian Process Prior and Fuzzy Control

Control of an unknown nonlinear time-varying plant has always been a great concern for control specialists, thus an appealing subject in this discipline. Many efforts have been dedicated to explore the various aspects of this problem. This research has led into introducing many new fields and methods. These methods can be categorized into two general classes as: data-driven and model-driven. Model driven methods in spite of having rigorous analytical basis are not employed as frequently as data-driven ones. On the other hand data-driven methods are suitable to be employed in nonlinear and dual controller design; however they are slightly unsuccessful in handling missing data, moreover these methods are in need of considerable amount of computation. This paper introduces a novel hybrid nonlinear controller which aggregates Gaussian Process Prior as a data-driven and a Fuzzy Controller as a model-driven method .This special structure brings model-driven and data-driven advantages altogether, thus naturally lead into a robust and adaptive controller. Since no prior knowledge of the plant is used to issue the control law, the proposed hybrid controller can also be regarded as a dual controller.