Humanoid biped robots are typically complex in design, having numerous degrees-of-freedom (DOF) due to the ambitious goal of mimicking the human gait. This thesis describes walking control algorithm for the stable walking of a lower-limb exoskeletons of a fifteen DOF (six for each leg and three for the support point). First of all, the gait locomotion, the human foot and the zero moment point (ZMP) get studied from an anatomical and kinesiological point of view. Input variables are imported from the big dataset of the University of Dallas. These are used for the computation of ZMP and, according to the Linear Inverted Pendulum Model (LIPM), the COG pattern is generated.