摘要
现实场景中物体种类多样、摆放位置随机,会导致智能机器人物体识别困难,抓取成功率不高。针对这一问题,提出一种在遮挡、同类多目标、堆叠等复杂情况下机器人抓取的方法。基于通道注意力机制ECA(Efficient Channel Attention)和残差网络ResNet(Residual Network),设计了编解码器结构的单视图6维位姿估计网络;利用合成数据集制作方法生成了6维位姿估计和抓取训练数据集;机器人抓取控制模块根据6维位姿估计网络的输出以及手眼标定结果,控制UR5机器人实现智能抓取。在Linemod、YCB-Video以及本文合成数据集上的实验结果表明,所提方法的平均抓取成功率达到95%。
In real-world scenarios,the diversity of object types and random placement can lead to diffi-culties in object recognition for intelligent robots,resulting in a low success rate in grasping.A method for robot grasping in complex situations such as occlusion,multiple targets of the same type,and stacking is proposed to address this issue.A single view 6D pose estimation network with encoder decoder structure is designed based on channel attention mechanism ECA and residu-al network ResNet;A 6D pose estimation and grasping training dataset is generated using a syn-thetic dataset production method;The robot grasping control module controls the UR5 robot to a-chieve intelligent grasping based on the output of the 6D pose estimation network and the results of hand eye calibration.The experimental results on Linemod,YCB-Video,and the synthesized data-set show that the average grasping success rate of our method reaches 95%.
作者
白素琴
顾健
吕宗磊
史金龙
於跃成
钱强
BAI Suqin;GU Jian;LYU Zonglei;SHI Jinong;YU Yuecheng;QIAN Qiang(Key Laboratory of Smart Airport Theory and System,Civil Aviation University of China,Tianjin 300300,China;School of Electrical&Information Engineering,Jiangsu University of Science and Technology,Suzhou 215600,China;School of Computer Science,Jiangsu University of Science and Technology,Zhenjiang 212000,China)
出处
《信息与控制》
北大核心
2025年第4期583-594,共12页
Information and Control
基金
国家自然科学基金项目(51875270)
中国民航大学民航智慧机场理论与系统重点实验室开放基金项目(SATS202207)。
关键词
机器人抓取
卷积神经网络
6维位姿估计
单视图
robotic grasping
convolutional neural network
6D pose estimation
single view
作者简介
通信作者:史金龙,jsjxy_sjl@just.edu.cn;白素琴(1976-),女,硕士,副教授。研究领域为机器学习,计算机视觉等。;顾健(1998-),女,硕士生。研究领域为机器视觉,机器人应用。;吕宗磊(1981-),男,博士,副教授。研究领域为机器学习,计算机视觉,智能感知。
