融合改进YOLO和语义分割的遮挡目标抓取方法  

Grasp method for occlusion method by fusing improved YOLO with semantic segmentation

作　　者：林哲 潘慧琳 陈丹[1] Lin Zhe;Pan Huilin;Chen Dan(School of Electrical Engineering and Automation,Fuzhou University,Fuzhou 350108,China)

机构地区：[1]福州大学电气工程与自动化学院,福州350108

出　　处：《电子测量与仪器学报》2024年第12期190-201,共12页Journal of Electronic Measurement and Instrumentation

基　　金：国家自然科学基金(61973085);福建省自然科学基金面上项目(2022J01114)资助。

摘　　要：针对遮挡目标的机器人抓取存在的遮挡干扰问题,提出了改进的YOLO-CA-SD和语义分割的遮挡目标检测模型及抓取方法,完成多目标及非目标物互相遮挡干扰情况下的抓取。首先,该模型在YOLOv5l中添加坐标注意力,在损失函数基础上考虑检测框匹配方向的问题,增加框之间的角度信息,并对原模型检测部分进行解耦,减少耦合造成的信息丢失。其次,提出了改进的DeeplabV3+目标分割模型,用MobileNetV2替换DeeplabV3+原主干网络,减小模型复杂度,在空洞空间金字塔池化结构中添加CA模块融合像素坐标信息提高分割精度,解决了遮挡干扰问题。最后,利用点云配准得到目标姿态相对于模板姿态的末端旋转角及最优抓取点。在2750张自主构建的常用工具遮挡数据集上进行性能测试,结果表明:改进后的模型在m AP@0.5,m AP@0.5:0.95、60%目标物体遮挡率数据集及60%非目标物体遮挡率数据集上的检测精度分别提高了0.052%、0.968%、6.000%、7.400%。此基础上改进的语义分割模型分割速度和MIOU分别提升了33.45%和0.625%,并且通过ABB IRB1200机械臂实现遮挡目标的抓取实验,验证了该方法的可行性与实用性。For the problem of occlusion interference in robot grasping of occluded targets,an improved YOLO-CA-SD and semantic segmentation occluded target detection model and grasping method are proposed to complete the grasping when multiple targets and nontarget objects occlude and interfere with each other.Firstly,the model adds a coordinate attention to YOLOv5l,considers the problem of detection frame matching direction based on the loss function,adds angle information between frames,and detects the original model decoupling is partially performed to reduce information loss caused by coupling.Secondly,an improved DeeplabV3+target segmentation model was proposed.The original DeeplabV3+backbone network was replaced by MobileNetV2 to reduce the model complexity.A CA module was added to the Atrous Spatial Pyramid Pooling structure to fuse pixel coordinate information to improve segmentation accuracy and solve the occlusion interference problem.Finally,the end rotation angle of the target poses relative to the template pose and the optimal grasping point are obtained by point cloud registration.The performance test is carried out on the self-built 2750 commonly used tool occlusion data set.The experimental results show that the improved model improves the detection accuracy by 0.052%,0.968%,6.000%,and 7.400%on mAP@0.5,mAP@0.5:0.95,60%target object occlusion rate and 60%non-target object occlusion rate datasets.The improved semantic segmentation model on this basis improves the segmentation speed and MIOU by 33.45%and 0.625%,and the ABB IRB1200 robotic arm is used to realize the experiments on the grasping of obscured targets,which verified the feasibility and practicality of the method.

关 键 词：遮挡目标检测 目标抓取 YOLO DeeplabV3+模型 点云配准 

分 类 号：TP242.2[自动化与计算机技术—检测技术与自动化装置] TN919.5[自动化与计算机技术—控制科学与工程]