摘要
针对机器人示教编程方法导致的工件位置固定、抓取效率低下的问题,研究神经网络在机器人视觉识别与抓取规划中的应用,建立了视觉引导方案,通过YOLOV5神经网络模型开发视觉识别系统,识别物体的种类,同时获取待抓取物体定位点坐标;提出了机器人六点手眼标定原理并进行标定实验,提出了针对俯视图为圆形或长方形物体的定位方法;最后针对3种物体进行了180次的抓取实验,实验的综合平均抓取成功率约为92.8%,验证了视觉识别和抓取机器人系统具备实际应用的可能性,有效提高了抓取效率。
Aiming at the problems of fixed workpiece position and low grasping efficiency caused by robot teaching programming method,this paper studies the application of neural network in robot vision recognition and grasping planning,establishes a vision guidance scheme,develops a vision recognition system through the YOLOV5 neural network model,identifies the types of objects,obtains the coordinates of the positioning points of the objects to be grasped,puts forward the robot six-point hand-eye calibration principle,carries out the calibration experiment,and proposes the positioning method for objects with circular or rectangular top view.Finally,the grabbing experiment is completed 180 times for three kinds of objects,and the overall average success rate of the experiments is about 92.8%,which verifies the possibility of practical application in the vision recognition and grabbing robot system and effectively improves the grabbing efficiency.
作者
燕硕
李建松
唐昌松
YAN Shuo;LI Jiansong;TANG Changsong(School of Mechatronic Engineering,Xuzhou College of Industrial Technology,Xuzhou 221140,China)
出处
《计算机测量与控制》
2024年第4期201-209,共9页
Computer Measurement &Control
基金
江苏高校“青蓝工程”项目(苏教师函(2022)29号)。
关键词
神经网络
目标定位
机器人抓取
机器人标定
视觉引导
neural network
target location
robot grasping
robot calibration
visual guidance
