In this paper, we propose an autonomous gait pattern for a dynamic biped walking based on a soft-computing approach. Our control strategy takes simultaneously advantage from a Fuzzy-CMAC based computation of robot’s swing leg’s desired trajectory and a high level control strategy allowing regulating the robot’s average velocity. The main interest of this approach is to proffer to the walking robot autonomy and adaptability involving only one parameter: the average velocity. We present results about transition of velocities and we show that the presented control strategy allows to increase robustness of the walking robot according to perturbation forces.