To fulfill the demands for higher quality,efficiency and flexibility in aviation industry,a multi-functional end effector is designed to automate the drilling and riveting processes in assembling carbon fiber reinforc...To fulfill the demands for higher quality,efficiency and flexibility in aviation industry,a multi-functional end effector is designed to automate the drilling and riveting processes in assembling carbon fiber reinforced polymer(CFRP)and aluminum components for a robotic aircraft assembly system.To meet the specific functional requirements for blind rivet installation on CFRP and aluminum materials,additional modules are incorporated on the end effector aside of the basic processing modules for drilling.And all of these processing modules allow for a onestep-drilling-countersinking process,hole inspection,automatic rivet feed,rivet geometry check,sealant application,rivet insertion and installation.Besides,to guarantee the better quality of the hole drilled and joints riveted,several online detection and adjustment measures are applied to this end effector,including the reference detection and perpendicular calibration,which could effectively ensure the positioning precision and perpendicular accuracy as demanded.Finally,the test result shows that this end effector is capable of producing each hole to a positioning precision within ±0.5 mm,aperpendicular accuracy within 0.3°,a diameter tolerance of H8,and a countersink depth tolerance of±0.01 mm.Moreover,it could drill and rivet up to three joints per minute,with acceptable shearing and tensile strength.展开更多
为了给驾驶员提供实时准确的行人信息、减少交通事故的发生,提出一种检测增强型YOLOv3-tiny(detection of enhanced YOLOv3-tiny,DOEYT)行人检测算法.创建鲁棒的特征提取网络,首先使用非对称最大池化进行下采样,防止随着感受野增大行人...为了给驾驶员提供实时准确的行人信息、减少交通事故的发生,提出一种检测增强型YOLOv3-tiny(detection of enhanced YOLOv3-tiny,DOEYT)行人检测算法.创建鲁棒的特征提取网络,首先使用非对称最大池化进行下采样,防止随着感受野增大行人横向特征的丢失;其次使用Hardswish作为卷积层的激活函数优化网络性能;最后使用GC(globe context)自注意力机制获得全文特征信息.在分类回归网络部分,采用三尺度检测策略,提升小尺度行人目标的检测精度;使用k-means++算法重新生成数据集锚框,提高网络收敛速度.构建行人检测数据集并分为训练集和测试集,对DOEYT算法的性能进行试验验证.结果表明,非对称最大池化、Hardswish函数、GC自注意力机制分别使平均准确率AP提高14.4%、7.9%、10.8%;DOEYT算法在测试集上检测的平均准确率高达91.2%,检测速度为103帧/s,可见该算法可快速准确地检测行人,降低交通事故发生的风险.展开更多
针对无人机图像中由于目标微小且相互遮挡、特征信息少导致检测精度低的问题,提出一种基于改进YOLOv7的无人机图像目标检测算法。在颈部和检测头中加入了坐标卷积,能更好地感受特征图中目标的位置信息;增加P2检测层,减少小目标特征丢失...针对无人机图像中由于目标微小且相互遮挡、特征信息少导致检测精度低的问题,提出一种基于改进YOLOv7的无人机图像目标检测算法。在颈部和检测头中加入了坐标卷积,能更好地感受特征图中目标的位置信息;增加P2检测层,减少小目标特征丢失、提高小目标检测能力;提出多信息流融合注意力机制——Spatial and Channel Attention Mechanism(SCA),动态调整注意力对空间信息流和语义信息流的关注,获得更丰富的特征信息以提高捕获目标的能力;更换损失函数为SIoU,加快模型收敛速度。在公开数据集VisDrone2019上进行对比实验,改进后算法的mAP50值相比YOLOv7提高了4%,达到了52.4%,FPS为37,消融实验验证了每个模块均提升了检测精度。实验表明,改进后的算法能较好地检测无人机图像中的目标。展开更多
基金supported by the National Natural Science Foundations of China(Nos.5157051626,51475225)
文摘To fulfill the demands for higher quality,efficiency and flexibility in aviation industry,a multi-functional end effector is designed to automate the drilling and riveting processes in assembling carbon fiber reinforced polymer(CFRP)and aluminum components for a robotic aircraft assembly system.To meet the specific functional requirements for blind rivet installation on CFRP and aluminum materials,additional modules are incorporated on the end effector aside of the basic processing modules for drilling.And all of these processing modules allow for a onestep-drilling-countersinking process,hole inspection,automatic rivet feed,rivet geometry check,sealant application,rivet insertion and installation.Besides,to guarantee the better quality of the hole drilled and joints riveted,several online detection and adjustment measures are applied to this end effector,including the reference detection and perpendicular calibration,which could effectively ensure the positioning precision and perpendicular accuracy as demanded.Finally,the test result shows that this end effector is capable of producing each hole to a positioning precision within ±0.5 mm,aperpendicular accuracy within 0.3°,a diameter tolerance of H8,and a countersink depth tolerance of±0.01 mm.Moreover,it could drill and rivet up to three joints per minute,with acceptable shearing and tensile strength.
文摘为了给驾驶员提供实时准确的行人信息、减少交通事故的发生,提出一种检测增强型YOLOv3-tiny(detection of enhanced YOLOv3-tiny,DOEYT)行人检测算法.创建鲁棒的特征提取网络,首先使用非对称最大池化进行下采样,防止随着感受野增大行人横向特征的丢失;其次使用Hardswish作为卷积层的激活函数优化网络性能;最后使用GC(globe context)自注意力机制获得全文特征信息.在分类回归网络部分,采用三尺度检测策略,提升小尺度行人目标的检测精度;使用k-means++算法重新生成数据集锚框,提高网络收敛速度.构建行人检测数据集并分为训练集和测试集,对DOEYT算法的性能进行试验验证.结果表明,非对称最大池化、Hardswish函数、GC自注意力机制分别使平均准确率AP提高14.4%、7.9%、10.8%;DOEYT算法在测试集上检测的平均准确率高达91.2%,检测速度为103帧/s,可见该算法可快速准确地检测行人,降低交通事故发生的风险.
文摘针对无人机图像中由于目标微小且相互遮挡、特征信息少导致检测精度低的问题,提出一种基于改进YOLOv7的无人机图像目标检测算法。在颈部和检测头中加入了坐标卷积,能更好地感受特征图中目标的位置信息;增加P2检测层,减少小目标特征丢失、提高小目标检测能力;提出多信息流融合注意力机制——Spatial and Channel Attention Mechanism(SCA),动态调整注意力对空间信息流和语义信息流的关注,获得更丰富的特征信息以提高捕获目标的能力;更换损失函数为SIoU,加快模型收敛速度。在公开数据集VisDrone2019上进行对比实验,改进后算法的mAP50值相比YOLOv7提高了4%,达到了52.4%,FPS为37,消融实验验证了每个模块均提升了检测精度。实验表明,改进后的算法能较好地检测无人机图像中的目标。