The reason for the present upsurge of interest in intelligent control is that the present generation of control systems are incapable, to a greater or lesser extent, of dealing with problems of a certain complexity. Fortunately, the human operator (HO) is often expert in keeping the complex control systems on the right track. In this paper a method for controller design has been investigated based on a concept of developing a mathematical model for HO behaviour. The method treats HO behaviour as a dynamic process by itself, transformed from the unknown dynamics of the ship to be controlled. The method of controller design entails observing the human controller, constructing a model of the human controller, and using that model as a basis for an automatic control system. During the observation phase the HO controls the ship and the data representing the state of the ship and human actions are registered. During the modelling phase, a human operator behaviour model (HOBM) is constructed as a neural network and its parameters are estimated. During the testing phase, the HOBM controls the ship and its performance is evaluated under the observation phase conditions and completely different conditions. The method has been successfully applied using computer simulation for the ship steering problem.