In this paper, the pitch angle control for a lab model helicopter is discussed. This problem has some specific features. As a main unusual feature, it is observed that the steady state control command is completely dependent on the setpoint, so error-based controllers do not suit this problem. Moreover, the system is of a highly oscillating dynamic. In order to solve this control problem, two controllers are designed, an artificial neural network, whose input is the setpoint, is used to provide steady state control command, and a fuzzy inference system ,whose input is error, is used to provide transient control command. The total control command is the sum of two aforementioned control commands. The system's robustness is also checked against any probable disturbance and parameter change. It is shown that the system is likely to be completely robust against any possible disturbance or parameter change in lab environment. In order make the system robust against a special kind of parameter change which is impossible to happen in the lab, a setpoint modification algorithm is offered to vanish the steady state error and provide a rather short settling time.