Behavior-based Person following and Obstacle Avoidance of Omni-directional Wheeled Robots Using a Laser Range Finder and a Panoramic Camera

• Main Authors: Wei-zhi Gu, 古偉志
• Other Authors: Tsing-Iuan Tsay
• Format: Others
• Language: zh-TW
• Published: 2008
• Online Access: http://ndltd.ncl.edu.tw/handle/03953742968846192296

碩士 === 國立成功大學 === 機械工程學系碩博士班 === 96 === Mobile robots have been applied extensively in daily environments such as in home, offices and hospitals. Demand for a mobile robot to follow a person is increasing. The objective of this thesis is to propose a navigation strategy for a mobile robot to follow a person and avoid obstacles in an object-laden environment. In the proposed behavior-based strategy, a genetic fuzzy logic controller is applied to generate individual command action and a context-dependent blending is utilized to coordinate the commands to produce final control action. An omni-directional wheeled robot integrated with a laser range finder and a panoramic camera is employed to verify the theoretical results of the proposed method. The experimental results reveal that the proposed approach ensures that the robot can not only reach a static goal without any collision with wall or obstacles but also follow a person closely.