Integration of fuzzy controller with adaptive dynamic programming

Adaptive dynamic programming (ADP) is an effective method for learning while fuzzy controller has been put into use in many applications because of its simplicity and no need of accurate mathematic modeling. The combination of ADP and fuzzy control has been studied a lot. Before this paper, we have studied using ADP to learn the fuzzy rules of a Monotonic controller, which shows good performance. In this paper, a hyperbolic fuzzy model is adopted to make an improvement. In this way, both membership function and fuzzy rules are learned. With ADP algorithm, fuzzy controller has the capacity of learning and adapting. Simulations on a single cart-pole plant and a rotational inverted pendulum are implemented to observe the performance, even with uncertainties and disturbances.