Study on Vision-Guided Grasping Tasks by Humanoid Robotswith a Compound-like Eye

• Main Authors: Wei-LunKao, 高偉倫
• Other Authors: Tsing-Iuan Tsay
• Format: Others
• Language: zh-TW
• Published: 2012
• Online Access: http://ndltd.ncl.edu.tw/handle/symex9

碩士 === 國立成功大學 === 機械工程學系碩博士班 === 100 === The robot technology is becoming more advanced and is continuing the challenge towards solution of several problems of mankind, such as security, welfare, and medical care. Several humanoid robots are being developed successively to solve the problems. In this study, a wheeled humanoid robot that was constructed in our laboratory is used as a research platform for vision-guided grasping tasks. The robot consists of a wheeled mobile base, a torso with a 3 degrees of freedom (DOF) waist mounted on the mobile base, two 7 DOF robot arms, one 7 DOF robotic right hand, one 2 DOF robotic left hand and a 7 DOF robotic binocular head. In the robotic binocular head, each fully assembled eye comprises two color CCD cameras, the upper lipstick camera containing a wide-angle lens and the lower camera containing a narrow-field foveal lens. Therefore, three cameras of the robotic head are arranged to be a coplanar compound-like eye. The objective of this thesis is to propose a vision-guided control strategy to equip the humanoid robot with the ability to grasp the material by the robot arm using the compound-like eye of the robotic head. The proposed control strategy is based on geometric camera models and the relative location of three cameras, and the least squares technique. Finally, one experiment is conducted to verify the effectiveness of vision-guided grasping task by a humanoid robot with a compound-like eye.