Online Path Planning for SURENA III Humanoid Robot Using Model Predictive Control Scheme

In this paper, two online path planning methods are presented for SURENA III humanoid robot by using model predictive control scheme. The methods are general control schemes which can generate the online motions for walking of a humanoid robot. For lowering computational costs a three dimensional linear inverted pendulum model is used instead of the full dynamical model of the robot. The generated trajectories are then used for computing the zero-moment point (ZMP) of the robot and the joint torques. The resulted joint torques of the two methods are compared to torques obtained from Genetic Algorithm (GA) path planning method presented for SURENA III humanoid robot in previous studies. The comparison is made with emphasize on the knee joint since it is the joint with highest consumed torque. The results show that predictive control method reduces the knee joint torque by 13% compared to GA offline path planning method.