智能机器人英文文档.docVIP

Obstacle Avoidance Design for Humanoid Robot Based on Four Infrared Sensors Ching-Chang Wong1*, Chi-Tai Cheng1, Kai-Hsiang Huang1, Yu-Ting Yang1, Hsiang-Min Chan1 and Chii-Sheng Yin2 1Department of Electrical Engineering, Tamkang University, Tamsui, Taiwan 251, R.O.C. 2Metal Industries Research Development Centre, Kaohsiung, Taiwan 811, R.O.C. Abstract Abehavior strategy of humanoid robot for obstacle avoidance based on four infrared sensors is proposed and implemented on an autonomous humanoid robot. A mechanical structure with 26 degrees of freedom is design so that an implemented small-size humanoid robot named TWNHR-III is able to accomplish five walking motions. Three walking experiments are presented to illustrate that the proposed biped structure lets TWNHR-III can move forward, turn, and slip. One electronic compass and four infrared sensors are mounted on TWNHR-III to obtain the head direction of the robot and detect obstacles, respectively. Based on the obtained information from these sensors, a decision tree method is proposed to decide one behavior from five movements: walk forward, turn right and left, and slip right and left. Two MATLAB simulations and one real experiment are presented to illustrate that the robot can avoid obstacles autonomously and go to the destination effectively. Key Words: Humanoid Robot, Autonomous Mobile Robot, Obstacle Avoidance, Decision Tree 1. Introduction Although the robot has been investigated for many years, there are still many issues to be studied, especially in the humanoid robots [1?4]. Hardware and software architectures,walking gait generation, and artificial intelligence are the main research fields of humanoid robots.Robot soccer games are used to encourage the researches on robotics and artificial intelligence (AI). Two international robot soccer associations, RoboCup [5] and FIRA[6], advance this research and hold the international competitions and the international symposiums. Robot soccer games are two tea