基于三维点云的机器人跟踪抓取实验设计  

Experimental design of robot tracking and grasping based on a 3D point cloud

作　　者：张倩 代伟 朱美强 张坤 王军 ZHANG Qian;DAI Wei;ZHU Meiqiang;ZHANG Kun;WANG Jun(School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221116,China)

机构地区：[1]中国矿业大学信息与控制工程学院,江苏徐州221116

出　　处：《实验技术与管理》2024年第2期65-72,共8页Experimental Technology and Management

基　　金：国家自然科学基金项目(61973306);自动化教指委教育教学改革研究项目(202144);中国矿业大学教学研究项目(2022ZXKC08,2022KCSZ03,2023KCSZ65);科技部科技创新2030“新一代人工智能”重大项目(2020AAA0107300)。

摘　　要：针对机器人抓取问题进行了综合性教学实验设计,提出了基于物体点云信息的机器人跟踪抓取方法。通过阈值处理保留运动模糊光条中亮度较高的部分,改善了运动模糊情况下光条区域提取困难的问题;利用特征直方图对不同物体的点云进行特征描述,实现了由未知的点云信息查询得到实际的抓取位置的目标;采用基于位置控制的优化算法实时更新跟踪路径,完成抓取操作。通过该完整的实验设计能够帮助学生理解激光三角法、点云信息、位置逼近等基本理论和方法,培养学生理论联系实际的能力和对科学研究的兴趣。[Objective]To obtain three-dimensional information about a moving workpiece economically and enable two-dimensional vision to obtain height information about an object,a three-dimensional scanning system based on a line laser is designed.[Methods]The point cloud acquisition function of a moving workpiece on a conveyor belt was developed and realized using a PCL point cloud library.During point cloud acquisition,the laser stripe on the moving object surface has a motion blur effect,which affects the light stripe center extraction.To accurately extract the two-dimensional coordinates of the center from the motion-blurred light stripe image,a threshold method based on the light stripe theory imaging width is proposed.The higher brightness part of the motion-blurred light stripe is retained through threshold processing,which solves the problem of different light stripe imaging widths in the case of motion blur.The experimental results show that the proposed method can quickly extract the two-dimensional coordinates of the fringe center from the motion-blurred light strip image and meet the accuracy requirement by measuring the three-dimensional information of the standard block.At present,the grasping detection algorithm usually needs an accurate object model and a complex matching algorithm or a large number of annotations of the grasping object posture to train the complex detection network to recognize the object posture.Aiming at the problems of low efficiency and cumbersome data annotation of the above methods,a grab location annotation method based on object point cloud information is proposed,which converts the actual grab detection task to the recognition of point clouds.In this method,the feature histogram of the point cloud is used to describe the characteristics of the point cloud of different objects to connect the attitude and grasping position of the actual object with the information about the point cloud.Through the multilayer description of the cloud,we can grasp the information from the cloud to the

关 键 词：三维点云 激光条纹 抓取 教学实验 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]