摘要： 在传统基于固定视觉的排爆机器人抓取系统中，相机视觉易被遮挡且不能保证拍摄清晰度。基于随动视觉技术，提出一种将深度相机置于机械手末端并随机械手运动的排爆机器人自主抓取系统。利用深度相机计算目标物体的三维坐标，采用坐标转换方法将目标物体的位置坐标信息实时转换至机器人全局坐标系，并研究相机坐标系、机器人全局坐标系与末端执行器手爪工具坐标系三者的动态映射关系，实现排爆机器人的自主抓取。实验结果表明，与传统固定视觉方法相比，随动视觉方法可在误差2 cm内，使得机器人机械手爪准确到达目标物体所在位置，且当机器人距离目标物体100 cm~150 cm时，抓取效果最佳。

关键词: 排爆机器人, 随动视觉, 三维坐标, 坐标转换, 自主抓取系统

Abstract: In the traditional EOD robot grasping system based on fixed vision,camera vision is easy to be blocked and can not guarantee the shooting clarity.On the basis of follow-up vision technology,this paper proposes an autonomous grasping system of EOD robot,in which the depth camera is placed at the end of the manipulator and moves with it.The three-dimensional coordinates of the target are calculated by using the depth camera,and then converted to the global coordinate system of the robot by using the coordinate transformation method.The dynamic mapping relationships between the camera coordinate system,the global coordinate system of the robot and the tool coordinate system of the end effector gripper is studied to realize the autonomous grasping of the EOD robot.The experimental results show that compared with the traditional fixed vision method,the follow-up vision method can enable the manipulator to accurately reach the position of the target object within the error of 2 cm,and the grasping effect is the best when the distance between the robot and the target object is 100 cm~150 cm.

Key words: EOD robot, follow-up vision, three-dimensional coordinate, coordinate conversion, autonomous grasping system

中图分类号: 

• TP391.9