摘要
以MOTOMAN-SV3X机器人、摄像机和传动带为基础,构建了一个基于机器视觉的机器人目标抓取系统。本系统中摄像机和机器人分别布置在传动带两端,其工作原理为:利用视觉定位和系统标定结果,经过坐标系转换将位姿信息转化到机器人基础坐标系中,然后根据位姿信息进行运动学逆解得相应的控制文件,最终实现摄像机在一端拍摄,机器人在另外一端对目标进行抓取。抓取实验结果验证了此系统的可行性和实用性,为提高生产线的自动化程度提供了一种新的方法,对后续的相关研究做了铺垫。
Based on MOTOMAN-SV3X robot, camera and conveyor belt, an object grasping system founded on robot vision is built. In this system, the camera and robot are installed separately in both ends of the belt. The operational principles are that using the vision orientation and camera calibration results, the objects＇ poses are transformed into robot base coordinate after coordinate system transformation. Then the robot control files are generated based on pose information through inverse kinematic solution, and finally control the robot grasping the objects on the other end of belt. The grasping experiment results prove the reliability and practicability of the system, providing a new method to improve the automation of production line, and paving the way for subsequent related research.
出处
《组合机床与自动化加工技术》
北大核心
2012年第12期37-40,44,共5页
Modular Machine Tool & Automatic Manufacturing Technique
