基于机器视觉的机械臂智能抓取系统设计  被引量:11

Intelligent Grasping System Design of Robot Arm Based on Machine Vision

在线阅读下载全文

作  者:姚启才 汪地[1] 廖茂生 YAO Qicai;WANG Di;LIAO Maosheng

机构地区:[1]上海大学上海市机器人与智能制造重点实验室,上海200444

出  处:《计量与测试技术》2020年第10期28-33,共6页Metrology & Measurement Technique

摘  要:智能抓取搬运机器人能够高效、可靠地完成各种搬运任务,降低工作人员的劳动强度,精准的目标物体定位是机器人执行抓取搬运任务的基础。本文研究了基于机器视觉的机器人智能抓取系统,可以实现物体的类别检测、物体定位及机器人抓取搬运任务。智能抓取系统由三个子系统组成(目标识别系统、目标定位系统及机器人抓取系统)。首先利用深度相机采集图像信息,并通过基于轮廓特征的匹配算法对目标物体进行匹配获得目标物体的中心坐标,接着通过机器人手眼标定法将像素坐标和深度信息转换到机器人基坐标系下,完成对目标物体的定位,最后通过机器人逆运动学求解各关节角姿态,驱动机器人运动完成抓取搬运任务。实验系统以对场景中多个目标物体识别抓取作业为例,实现以目标物体为导向的机器人自适应抓取。实验结果表明,该基于机器视觉的机械臂智能抓取系统具有较高的定位精度,能够有效地完成抓取搬运任务。Intelligent grasp and handling robot can complete various handling tasks efficiently and reliably,and reduce the labor intensity of staff.Precise target object positioning is the basis of robot to perform grasp and handling tasks.This paper studies the robot intelligent grasp system based on machine vision,which can realize object category detection,object positioning and robot grasping and carrying tasks.Intelligent capture system consists of three subsystems(target recognition system,target positioning system and robot grasping system).First,use the depth camera to collect image information,and use the matching algorithm based on contour feature matching of target object for the center of the target object coordinate,and then use the robot hand-eye calibration method transfer pixel coordinates and depth information to robot base coordinates,to complete the target positioning of the object,at last,use the inverse kinematic solution of each joint angle,grab handle task driven robot movement.The experimental system takes the recognition and grasping of multiple objects in the scene as an example to realize the adaptive grasping of the robot guided by the object.The experimental results show that the robot arm intelligent grasping system based on machine vision has high positioning accuracy and can complete the task of grasping and handling effectively.

关 键 词:机器视觉 机械臂 轮廓特征匹配算法 

分 类 号:TB9[一般工业技术—计量学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象