A Uniform Gait Generation Method for RoboCup Humanoid Robot Based on Genetic Algorithms

Walking straight, turning around, sidling and penalty kicking (PK) are four basic walking patterns for the current humanoid soccer competition. This work is concerned with a uniform gait generation method for all these walking patterns. Each statically stable walking pattern is divided into five key posture phases (PP). The third-order spline is applied to achieve smooth trajectory. In RoboCup, it is also important to make a smooth and optimal gait for saving the electric power, by optimizing the time intervals between two successive key posture phases, we can obtain energy-efficient walking patterns. Two genetic algorithms are employed to obtain the five key posture phases and optimal time intervals. The proposed gait generation method has been tested on our soccer-playing humanoid robot, TH-MOS, which got First Place in 2005 China Soccer Robot Competition