Walking motion design of humanoid robots in RoboCup3D simulation platform

Abstract

Quick and agile walking is indispensable for humanoid robots in the RoboCup soccer competition. So, this paper presented a walking motion design of humanoid robot soccer team called Apollo3D. In this paper, we employed a model which is based on double linear inverted pendulum with a predictive control to generate a motion trajectory of the robot’s trunk in the premise of keeping dynamic balance of robots. Parameters for walk are optimized for maximum speed through an approach of Q-learning algorithm. Then, the cerebellar model articulation controller method is employed to optimize the walking parameters to keep dynamic balance of robots. With this walking skill, ultimately, we realized rapidly and stably omnidirectional walk of biped robot in complex and dynamic environment. Experimental results have revealed Our team Apollo3D employed this walking skill, and won the first place in RoboCup 2013 3D simulation competition by winning 53 goals.