检索结果-内蒙古大学图书馆

2nd International Conference on Computer, control and Robotics, ICCCR 2022

作者： Huang, Lihong Wang, Huaizhi Lu, Yanjun Qiu, Rengao Yang, Longhao Qiu, Hailun College of Mechatronics and Control Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9781665466745

Aiming at the traditional mechanical arm grasping limited to fixed poses, specific shapes of objects, and non-real-time recognition, general object recognition and intelligent grasping system based on deep learning is designed. The system applies the YOLO-V4 object detection model and uses the Intel RealSense D435i depth camera to collect color images of different postures and positions of the general target object, which is used to train the target detection model, and proposes an adaptive labeling best capture the method of location improves the accuracy of crawling. Then, according to the hand-eye calibration result of the robot grasping system and the homogeneous transformation matrix of each joint of the robotic arm, the three-dimensional coordinates of the best grasping point in the image coordinate system are returned;the system then performs inverse kinematics to solve the obtained coordinate information to determine the pending Grasping the position of the object, and finally using the proposed improved RRT-Connect multi-stage motion planning optimization algorithm for motion planning, after obtaining the planned path, the robot arm is guided to efficiently grasp the target object. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Keypoints Estimation on Partial Point Clouds 6

Keypoints Estimation on Partial Point Clouds

引用

6th International Conference on Robotics and Automation in Industry, ICRAI 2024

作者： Saleem, Maryam Zohaib, Mohammad Naqvi, Syed Abbas Zilqurnain UET Human Centered Robotics Lab Department of Mechatronics and Control Engineering Lahore Pakistan SIGMA Clermont University of Clermont Auvergne Aubiere France

ISBN: (纸本)9798350355703

Estimating 3D keypoints of an object has achieved considerable interest, especially in computer graphics and ma-chine vision. The complexity of the problem increases when the object is noisy, decimated, or partially occluded. To this end, we present an approach to estimate 3D keypoints from the partial PCDs such that they also highlight the object's missing parts. It is based on two modules: shape completion and keypoints estimation. The first module computes the object's missing parts and generates a dense shape which is used by the second module to estimate semantically and geometrically consistent keypoints. The approach also estimates confidence scores that allow the selection of valid keypoint considering the object's structure. We evaluate the proposed method for four different backbones and observe that we get better results using PointNet. Furthermore, the presented results show that the Percentage of Correct Keypoints (PCK) and Dual Alignment Score (DAS) for the keypoints estimated from the dense shapes (36.61 and 76.29) are 23.51 % and 12.14% higher, respectively, compared to those estimated from the partial objects (13.10 and 64.15). © 2024 IEEE.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

EMI Noise Reduction with Magnetic Integrated LCL Filter in the Grid-Connected Inverter 49

EMI Noise Reduction with Magnetic Integrated LCL Filter in t...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Liu, Xingyu Liu, Yitao Jiang, Shiqi College of Mechatronics and Control Engineering Shenzhen University Shenzhen China School of Electrical Engineering and Automation Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350331820

This paper presents a magnetic integration scheme of LCL filter with symmetrical structure. This magnetic integration scheme uses EIE core to realize the inductor integration of symmetrical LCL filter, and realizes the decoupling and integration of upper and lower E-cores. The effectiveness of the magnetic integrated symmetrical LCL filter is verified by simulation and experiment. A 600 W single-phase SiC high-frequency inverter was used as the experimental platform to give the output current harmonic analysis results and conducted EMI noise. The symmetrical LCL filter with integrated structure not only has good harmonic suppression effect, but also greatly improves EMI suppression ability. The integrated filter is significantly smaller weight, helping to increase system power density. © 2023 IEEE.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Filtering in Projection-based Integrators for Improved Phase Characteristics 63

Filtering in Projection-based Integrators for Improved Phase...

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Chu, Hoang Van Den Eijnden, S.J.A.M. Heertjes, M.F. Heemels, W.P.M.H. Eindhoven University of Technology Control Systems Technology Section Dept. Mechanical Engineering Netherlands Asml Mechatronics & Measurements Systems Veldhoven Netherlands

ISBN: (纸本)9798350316339

Projection-based integrators are effectively employed in high-precision systems with growing industrial success. By utilizing a projection operator, the resulting projection-based integrator keeps its input-output pair within a designated sector set, leading to unique freedom in control design that can be directly translated into performance benefits. This paper aims to enhance projection-based integrators by incorporating well-crafted linear filters directly into its structure, resulting in a new class of projected integrators that includes the earlier ones, such as the hybrid-integrator gain systems (HIGS), as special cases. The extra design freedom in the form of two filters in the input paths to the projection operator and the internal dynamics allows the controller to break away from the inherent limitations of a linear control design. The enhanced performance properties of the proposed structure are formally demonstrated through i) a describing function analysis, ii) mitigation of the gain-loss problem (occurring in, e.g., HIGS), and iii) numerical case studies showcasing improved time-domain properties. The describing function analysis is supported by rigorously showing incremental properties of the new filtered projection-based integrators, thereby guaranteeing the steady-state responses to be unique and asymptotically stable. © 2024 IEEE.

关键词： Describing functions

来源：评论

学校读者我要写书评

暂无评论

Perception Reinforcement Using Auxiliary Learning Feature Fusion: A Modified Yolov8 for Head Detection

Perception Reinforcement Using Auxiliary Learning Feature Fu...

引用

2023 China Automation Congress, CAC 2023

作者： Chen, Jiezhou Wang, Guankun Liu, Weixiang Zhong, Xiaopin Tian, Yibin Wu, ZongZe College of Mechatronics and Control Engineering Shenzhen University Shenzhen China The Chinese University of Hong Kong Department of Electronic Engineering Hong Kong

ISBN: (纸本)9798350303759

Head detection provides distribution information of pedestrian, which is crucial for scene statistical analysis, traffic management, and risk assessment and early warning. However, scene complexity and large-scale variation in the real world make accurate detection more difficult. Therefore, we present a modified Yolov8 which improves head detection performance through reinforcing target perception. An Auxiliary Learning Feature Fusion (ALFF) module comprised of LSTM and convolutional blocks is used as the auxiliary task to help the model perceive targets. In addition, we introduce Noise Calibration into Distribution Focal Loss to facilitate model fitting and improve the accuracy of detection. Considering the requirements of high accuracy and speed for the head detection task, our method is adapted with two kinds of backbone, namely Yolov8n and Yolov8m. The results demonstrate the superior performance of our approach in improving detection accuracy and robustness. © 2023 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Transient Response Optimization of Bidirectional Dual-Active-Bridge DC/DC Converters Based on Dual-Phase-Shift 14

Transient Response Optimization of Bidirectional Dual-Active...

引用

14th IEEE International Symposium on Power Electronics for Distributed Generation Systems, PEDG 2023

作者： Luo, Lei Liu, Yitao Kang, Li He, Xiaochao Wang, Yun Yin, J. Shenzhen University College of Mechatronics and Control Engineering Shenzhen China Dongguan University of Technology School of Electrical Engineering and Intelligentization Dongguan China

ISBN: (纸本)9798350328233

Bidirectional power conversion plays an important role in sustainable energy generation systems, where dual-active-bridge (DAB) is a highly promising topology. However, DAB converters with traditional dual-phase-shift (DPS) can produce DC bias and hard switching during transients. In this paper, an optimized DPS control strategy for DAB is introduced which can eliminate the transient DC bias well, and can be used to maintain soft switching in the transient state. Plenty of experiments are carried out by establishing a DAB prototype. These experimental results verify the effectiveness of the proposed DPS control strategy. © 2023 IEEE.

关键词： Transient analysis

来源：评论

学校读者我要写书评

暂无评论

On‑Ramp Merging for Highway Autonomous Driving:An Application of a New Safety Indicator in Deep Reinforcement Learning

引用

Automotive Innovation 2023年第3期6卷 453-465页

作者： Guofa Li Weiyan Zhou Siyan Lin Shen Li Xingda Qu College of Mechanical and Vehicle Engineering Chongqing UniversityChongqing 400044China Institute of Human Factors and Ergonomics College of Mechatronics and Control EngineeringShenzhen University3688 Nanhai AvenueShenzhen 518060Guangdong ProvinceChina School of Civil Engineering Tsinghua UniversityBeijing 100084China

This paper proposes an improved decision-making method based on deep reinforcement learning to address on-ramp merging challenges in highway autonomous driving.A novel safety indicator,time difference to merging(TDTM),is introduced,which is used in conjunction with the classic time to collision(TTC)indicator to evaluate driving safety and assist the merging vehicle in finding a suitable gap in traffic,thereby enhancing driving *** training of an autonomous driving agent is performed using the Deep Deterministic Policy Gradient(DDPG)*** action-masking mechanism is deployed to prevent unsafe actions during the policy exploration *** proposed DDPG+TDTM+TTC solution is tested in on-ramp merging scenarios with different driving speeds in SUMO and achieves a success rate of 99.96%without significantly impacting traffic efficiency on the main *** results demonstrate that DDPG+TDTM+TTC achieved a higher on-ramp merging success rate of 99.96%compared to DDPG+TTC and DDPG.

关键词： Autonomous driving On-ramp merging Deep reinforcement learning Action-masking mechanism Deep Deterministic Policy Gradient(DDPG)

来源：评论

学校读者我要写书评

暂无评论

DADAN: Dynamic-Augmented and Density-Aware Network for Accurate 3-D Object Detection With 4-D Radar

引用

IEEE Sensors Journal 2025年第6期25卷 10272-10286页

作者： Wang, Xingzheng Li, Jiahui Wu, Jianbin Wu, Shaoyong Li, Lihua Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China Shenzhen Technology University Guangdong-Hongkong-Macao Critical Optical Components Precision Manufacturing Research Center Sino-German College of Intelligent Manufacturing Shenzhen518118 China

The cost-effective automotive 4-D radar is emerging as a feasible solution for 3-D object detection in autonomous driving scenarios. However, point clouds generated by 4-D radar are typically sparse. Current methods encounter challenges in resolving the foreground-background confusion in sparse point clouds due to: 1) the underutilization of the unique dynamic information (velocity and intensity) of 4-D radar points;and 2) the density variations of point clouds where they are near-dense-far-sparse, exacerbating the confusion. Therefore, we propose a dynamic-augmented and density-aware network (DADAN) to address these challenges by: 1) assigning high weights to foreground points based on dynamic information and enhancing their feature encoding to reduce confusion effectively;and 2) utilizing attention mechanisms along with density information to adaptively address exacerbated confusion caused by density variations. The DADAN comprises a dynamic-augmented encoding network, a density-aware backbone, and a detection head. The encoding network incorporates a dynamic-augmented encoding module (DAEM) that assigns high weights to foreground points based on velocity and intensity data to improve their feature encoding. Notably, foreground points typically exhibit distinct dynamic information compared to background points, distinguishing them from the background. The backbone network incorporates an attention mechanism along with density information to generate density-aware features. The detection head is responsible for 3-D bounding boxes and object categories. The experimental results on various public datasets demonstrate the superior performance of the proposed method compared to existing approaches. These results illustrate that the DADAN effectively addresses the issue of confusion, accurately detecting objects in complex scenes. © 2001-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Progress on the glassy-crystal laminates:From design,microstructure to deformation and future solutions

引用

Journal of Materials Science & Technology 2024年第5期172卷 113-144页

作者： Yu Chen Ronggao Cui Jun Shen Gang Wang College of Mechatronics and Control Engineering Shenzhen UniversityShenzhen 518060China College of Physics and Optoelectronic Engineering Shenzhen UniversityShenzhen 518060China Department of Motor Design Business Weichai New Energy Technology Co.Ltd.Weifang 261061China Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots Shenzhen UniversityShenzhen 518060China Laboratory for Microstructures Institute of MaterialsShanghai UniversityShanghai 200444China

The development of new design strategies to create innovative structural materials,refine existing ones,and achieves compatible combinations of strength and plasticity remains a worldwide *** alloys,such as shape memory alloys(SMAs),bulk metallic glasses(BMGs),high entropy alloys(HEAs),and heterogeneous pure metals such as Cu,have excellent mechanical responses,but they still fall short of meeting all the requirements of structural materials due to specific flaws,such as lack of tensile de-formation for BMGs and low yielding strength for *** address these shortcomings,proposals such as integrating glassy matrices and crystallized alloys,such as HEAs/SMAs,have been ***,these solutions have unresolved issues,such as the challenging control of B2 phase formation in BMG ***,glass-crystal(A/C)laminated alloys with alternating layers have been reported to exhibit improved mechanical properties and activated work-hardening behaviors,but they still face press-ing issues such as bonding interfaces and unknown deformation *** review focuses on design routes such as the selection of alloy components and processing techniques,exploration of micro-structural evolution and deformation modes with an increase in strain,and future solutions to address pressing and unsolved *** prominent advantages include diversified deformation mechanisms,such as deformation twinning,martensitic phase transformation,and precipitation hardening,as well as tuned interactive reactions of shear bands(SBs)near the A/C ***,this review provides a promising pathway to design and develop structural materials in the materials field community.

关键词： Glassy-crystal laminates Bulk metallic glasses High entropy alloys Shape memory alloys Microstructure Deformation mechanisms Future solutions

来源：评论

学校读者我要写书评

暂无评论

A mixed-coordination electron trapping-enabled high-precision touch-sensitive screen for wearable devices

引用

Bio-Design and Manufacturing 2024年第4期7卷 413-427页

作者： Xi Zhang Junchi Ma Hualin Deng Jinming Zhong Kaichen Xu Qiang Wu Bo Wen Dongfeng Diao Guangdong Provincial Key Laboratory of Micro/Nano Optomechatronics Engineering College of Mechatronics and Control EngineeringShenzhen UniversityShenzhen 518060China State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical EngineeringZhejiang UniversityHangzhou 310058China Shenzhen University General Hospital Shenzhen 518055China Research Center of Medical Plasma Technology Shenzhen UniversityShenzhen 518060China

Touch-sensitive screens are crucial components of wearable *** such as reduced graphene oxide(rGO),carbon nanotubes(CNTs),and graphene offer promising solutions for flexible touch-sensitive ***,when stacked with flexible substrates to form multilayered capacitive touching sensors,these materials often suffer from substrate delamination in response to deformation;this is due to the materials having different Young’s modulus *** results in failure to offer accurate touch screen *** this work,we demonstrate an induced charge-based mutual capacitive touching sensor capable of high-precision touch *** is enabled by electron trapping and polarization effects related to mixed-coordinated bonding between copper nanoparticles and vertically grown graphene ***,we used an electron cyclotron resonance system to directly fabricate graphene-metal nanofilms(GMNFs)using carbon and copper,which are firmly adhered to flexible *** being subjected to 3000 bending actions,we observed almost no change in touch *** screen interaction system,which has a signal-to-noise ratio of 41.16 dB and resolution of 650 dpi,was tested using a handwritten Chinese character recognition trial and achieved an accuracy of 94.82%.Taken together,these results show the promise of touch-sensitive screens that use directly fabricated GMNFs for wearable devices.

关键词： Flexible touch-sensitive screen Graphene-metal nanofilms Mixed coordination Wearable device

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：