基于双目视觉的双臂协作教学机器人研究与设计

Design of dual-arm cooperative teaching robot based on binocular vision

为弥补智能制造、机器人工程等新专业实验装置短缺、学生创新实践能力亟待提升等问题,本文设计了一种基于双目视觉的双臂协作教学机器人.双臂机械部分设计呈对称结构,底座大而稳定,可以降低制造成本及协作抓取难度;研究设计的示教动作还原算法和重投影误差最小化算法,可以提升机器人末端位姿数据采集精度,使双臂协作抓取更准确稳定.该系统不仅能够通过上位机拖动控制双臂运动完成示教编程及动作组实验,而且还能够进行基于视觉引导的图像处理及单臂抓取实验、运动分析实验、在线编程与协调抓取开放实验.该系统成本低、功能丰富、综合性强,且兼具拖动示教与开放性特点,有助于提升学生创新实践能力,非常适合在智能制造、机器人工程等专业实验教学过程中推广应用.

To make up for the shortage of experimental devices for the emerging majors such as intelligent manufacturing and robot engineering,as well as the urgent needs in improving students innovative and practical ability,we design a dual-arm cooperative teaching robot based on binocular vision.The mechanical part of the two arms is a symmetrical structure mounted on a big stable base to reduce manufacturing cost and coordinated grasping difficulty.In order to increase the accuracy of the robot terminal pose acquisition and thus improve the dual-arm cooperative grasp in both accuracy and stability,we design a teaching motion restoring algorithm and a reprojection error minimization algorithm.The upper computer of the system can drag and control the two arms to do programming teaching and action group experiments;and the robot can not only process images and conduct single-arm grabbing experiments under visual guidance,but also carry out motion analysis experiments,online programming,and open experiments of coordinated grabbing.The proposed system is cost-effective,rich in functions,highly integrative,and able of both drag teaching and open experiments,which is helpful to improve students innovative and practical ability,therefore it is very suitable for promotion and application in the experimental teaching courses for intelligent manufacturing,robot engineering and other related majors.