Neurofuzzy modeling of manual control system with a human operator

A practical intelligent modeling method, based on a fuzzy inference model with neural network compensator, is applied to the manual control system with human operator. It is known that human operator as a part of controller is difficult to be modeled because of variations of individual characteristics and operational environments. So in these situations, a fuzzy model developed relying on the expert experiences and/or trials-and-errors may not be acceptable. To supplement the fuzzy modeling errors, a neural network compensator based on feedback error learning is incorporated. The feasibility of the present neurofuzzy modeling scheme has been investigated for the real human based target tracking system.