Adaptive fuzzy logic control of an anti-lock braking system

This work focuses on the design of adaptive fuzzy logic control of an anti-lock braking system. This controller does not know the exact plant model, but knows the input-output relations of the plant (training data). The controller initially employs a priori training data to control the braking system, but continues to train online while continuously updating the confidence parameters and placement of fuzzy sets by employing optimization algorithms. Old data will be slowly forgotten while up-to-date training data are acquired. Thus, changes in road conditions or in the plant itself can be learned