基于改进YOLOv2的无标定3D机械臂自主抓取方法  

3D uncalibrated robotic grasping method based on improved YOLOv2

作　　者：余玉琴 魏国亮 王永雄[1] Yu Yuqin;Wei Guoliang;Wang Yongxiong(School of Optical-Electrical&Computer Engineering,University of Shanghai for Science&Technology,Shanghai 200093,China;College of Science,University of Shanghai for Science&Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海200093 [2]上海理工大学理学院,上海200093

出　　处：《计算机应用研究》2020年第5期1450-1455,共6页Application Research of Computers

基　　金：国家自然科学基金资助项目(61673276);上海市科委地方能力建设项目(15550502500)。

摘　　要：提出了一种多物体环境下基于改进YOLOv2的无标定3D机械臂自主抓取方法。首先为了降低深度学习算法YOLOv2检测多物体边界框重合率和3D距离计算误差,提出了一种改进的YOLOv2算法。利用此算法对图像中的目标物体进行检测识别,得到目标物体在RGB图像中的位置信息;然后根据深度图像信息使用K-means++聚类算法快速计算目标物体到摄像机的距离,估计目标物体大小和姿态,同时检测机械手的位置信息,计算机械手到目标物体的距离;最后根据目标物体的大小、姿态和到机械手的距离,使用PID算法控制机械手抓取物体。提出的改进YOLOv2算法获得了更精准的物体边界框,边框交集更小,提高了目标物体距离检测和大小、姿态估计的准确率。为了避免了繁杂的标定,提出无标定抓取方法,代替了基于雅克比矩阵的无标定估计方法,通用性好。实验验证了提出的系统框架能对图像中物体进行较为准确的自动分类和定位,利用Universal Robot 3机械臂能够对任意摆放的物体进行较为准确的抓取。This paper proposed an uncalibrated 3D robotic arm grabbing method based on improved YOLOv2 in a multi-object environment.Firstly,in order to reduce the depth learning algorithm YOLOv2 detection multi-object bounding box overlapping rate and 3D distance calculation error,it proposed an improved algorithm for YOLOv2.It used this algorithm to detect and identify the target object in the image,obtained the position information of the target object in the RGB image,and then used the K-means++clustering algorithm to quickly calculate the distance from the target object to the camera according to the depth image information,and estimate the target object size and pose.Simultaneously,it used the improved YOLOv2 to get the bounding box of the gripper and calculated the distance from the robot to the target object.Then the system estimated the distance between the fixture,camera and object in the manipulator coordinate system.Finally,the system used the PID algorithm to control the gripper to grab the object according to the size and posture of the object and the distance from the object to the gripper.The detected boundary boxes of the target object was more accurate based on the improved YOLOv2 than on old one.It also enhanced the distance from the fixture to the object and the size of the object as well as the accuracy of the pose estimation.In addition,in order to avoid complicated calibration,this paper proposed a non-calibration method.The learning scheme was different from the traditional uncalibrated estimation method based on Jacobian matrix,because it had good universality.A simulation experiment shows that the proposed method can accurately classify and locate the objects in the image.The Universal Robot 3 robotic arm uses this framework to verify the effectiveness of capturing objects in a cluttered environment.

关 键 词：改进YOLOv2 无标定 PID控制 机械臂抓取 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]