In terms of Unmanned Powered Parafoil Aircraft（UPPA）always flight in the low level sky and on top of the city’s hight rise.It often gets hight frequency disturb by all kinds of wind.It’s velocity and course angle or wind all affect the response characteristic of UPPA gesture. Then it will induce controlled rules be unsuitable with switch parameters. The PID algorithms can not reach satisfactory controlled effect. A fuzzy controller for UPPA gesture based on RBF networks and genetic algorithms is designed. A new method is also proposed for the self-tuning of scaling factors and genetic algorithm is employed to optimize the parameters used in tuning process in order to keep good controlling performance in case of time varying and uncertainties. Finally, with the nonlinear UPPA model of a mariner level vessel, simulation tests are carried out and results are satisfactory.