面向机器人抓取位姿估计网络研究  

Research on Robot Grasping Pose Estimation Network

作　　者：杨韧韧 吴炳龙 彭晋民[1,2] 陈昌红 YANG Renren;WU Binglong;PENG Jinmin;CHEN Changhong(Fujian Key Laboratory of Intelligent Machining Technology and Equipment,Fujian University of Technology,Fuzhou 350118,China;School of Mechanical&Automotive Engineering,Fujian University of Technology,Fuzhou 350118,China)

机构地区：[1]福建工程学院福建省智能加工技术及装备重点实验室,福州350118 [2]福建工程学院机械与汽车工程学院,福州350118

出　　处：《机械科学与技术》2024年第11期1929-1936,共8页Mechanical Science and Technology for Aerospace Engineering

基　　金：福建省高校科技创新团队培育计划(闽教科[2020]12号);福建省科技创新重点项目(2022G02007)。

摘　　要：针对工业生产环境中对不同位姿摆放不固定工件的抓取和在机器人分拣中存在的遮挡堆叠、工件大小各异等问题。提出了一种基于PVNet改进的视觉位姿估计网络,在其骨干网络基础上,使用Res2Net替换原残差结构以提高多尺度特征的提取性能,再使用该网络回归得出每个像素指向关键点的单位向量,通过投票算法得出关键点位置,最后使用EPnP算法求解工件位姿。实验使用深度相机采集图像制作数据集进行测试,以2D投影指标和模型点的平均3D距离作为评测标准。实验结果表明:改进的位姿估计网络,有效提高了检测精度和多尺度能力,对遮挡的物体有着良好的鲁棒性,处理速度也可以满足实际生产过程机器人抓取要求。In order to solve the problems of grabbing occluded workpieces with different positions and size in industrial production environment,an improved visual pose estimation network based on PVNet is proposed.On the basis of its backbone network,Res2Net is used to replace the original residual structure to improve the extraction performance of multi-scale features.Then,the unit vector of each pixel pointing to the key point is obtained by using the network regression,and the key point position is calculated by using the voting algorithm.Finally,the workpiece pose is calculated by using EPnP.The experiment uses the depth camera to take photos and create datasets for test.The experiment takes the 2D projection index and the average 3D distance of model points as the evaluation standard.The results show that the improved pose estimation network effectively improves the detection accuracy and multi-scale ability,and has good robustness to occluded objects,and the processing speed can also meet the requirements of robot grasping in the actual production.

关 键 词：机器人分拣 多尺度特征 EPnP 位姿估计 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]