An Advanced Matrix Algorithm for Robot Global Localization
Robot localization is the core technique in robotics. A localization process could be divided into 2 phases, global localization and tracking. Global localization is expensive in computation. For that reason, if a robot fails to track his position, it would takes hundreds of milliseconds to recover. The method presented in this paper achieves global localization by the improved Matrix Algorithm. The original Matrix Algorithm is used to track the robot. We change the way it builds the force field, so that it can converge to the right place from any initial point with a higher possibility, which means it can be used in global localization phase.
robot localization Matrix Algorithm genetic programing force field
Zong Jie Xiang Wanmi Chen
Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai,China School of Mechatronics Engineering and Automation,Shanghai University Shanghai,China Shanghai Key La
国际会议
太原
英文
463-466
2011-02-26（万方平台首次上网日期，不代表论文的发表时间）