检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Wang, Guangming Chen, Muyao Liu, Hanwen Yang, Yehui Liu, Zhe Wang, Hesheng The Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Department of Computer Science and Technology University of Cambridge

With the rapid development of measurwement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perception most focus on the image or video, but deep learning methods for dynamic 3D point cloud sequences are underexplored. Therefore, developing efficient and accurate perception method compatible with these advanced instruments is pivotal to autonomous driving and service robots. An Anchor-based Spatio-Temporal Attention 3D Convolution operation (ASTA3DConv) is proposed in this paper to process dynamic 3D point cloud sequences. The proposed convolution operation builds a regular receptive field around each point by setting several virtual anchors around each point. The features of neighborhood points are firstly aggregated to each anchor based on the spatio-temporal attention mechanism. Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points. The proposed method makes better use of the structured information within the local region and learns spatio-temporal embedding features from dynamic 3D point cloud sequences. Anchor-based Spatio-Temporal Attention 3D Convolutional Neural Networks (ASTA3DCNNs) are built for classification and segmentation tasks based on the proposed ASTA3DConv and evaluated on action recognition and semantic segmentation tasks. The experiments and ablation studies on MSRAction3D and Synthia datasets demonstrate the superior performance and effectiveness of our method for dynamic 3D point cloud sequences. Our method achieves the state-of-the-art performance among the methods with dynamic 3D point cloud sequences as input on MSRAction3D and Synthia datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences

End-to-End 3D Point Cloud Learning for Registration Task Usi...

引用

2020 IEEE/RSJ International Conference on intelligent Robots and systems (IROS)

作者： Huanshu Wei Zhijian Qiao Zhe Liu Chuanzhe Suo Peng Yin Yueling Shen Haoang Li Hesheng Wang The Chinese University of Hong Kong T Stone Robotics Institute Hong Kong Shanghai Jiao Tong University China University of Cambridge United Kingdom Carnegie Mellon University Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China

ISBN: (数字)9781728162126

ISBN: (纸本)9781728162133

3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds with partial correspondences, and it's even harder in the absence of any initial estimation information. In this paper, we present an end-to-end deep-learning based approach to resolve the point cloud registration problem. Firstly, the revised LPD-Net is introduced to extract features and aggregate them with the graph network. Secondly, the self-attention mechanism is utilized to enhance the structure information in the point cloud and the cross-attention mechanism is designed to enhance the corresponding information between the two input point clouds. Based on which, the virtual corresponding points can be generated by a soft pointer based method, and finally, the point cloud registration problem can be solved by implementing the SVD method. Comparison results in ModelNet40 dataset validate that the proposed approach reaches the state-of-the-art in point cloud registration tasks and experiment resutls in KITTI dataset validate the effectiveness of the proposed approach in real applications.

关键词： Three-dimensional displays Aggregates Pose estimation Feature extraction Task analysis intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Tool Path Generation Method for Three-dimensional Vibration-assisted Machining 16

Tool Path Generation Method for Three-dimensional Vibration-...

引用

16th IEEE International Conference on Mechatronics and Automation, ICMA 2019

作者： Wang, Guilian Lv, Bingrui Liu, Bin Mu, Haozhi Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology China Tianjin Laboratory of Control Theory and Applications in Complicated System Tianjin300384 China School of Electrical and Electronic Engineering Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9781728116983

In this paper, a new tool path generation method is proposed for the 3D (three-dimensional) vibration-assisted 6-DOF (six degree of freedom) machine tool machining system. The tool feed path is generated by the tangent point method and the coordinate transformation theory. It is worth noting that this method needle is only used when the tool and workpiece surface topography can be mathematically described. Finally, a numeric simulation method is used to simulate the tool path which is required when machining workpiece surfaces with different topography tools. The results show that the tool path generation method is widely applicable to tools and workpieces of various shapes, and it is of great significance to reveal the influences of different tool shapes on the tool path. © 2019 IEEE.

关键词： Machine tools

来源：评论

学校读者我要写书评

暂无评论

Supersolid and pair correlations of the extended Jaynes-Cummings-Hubbard model on triangular lattices

引用

Physical Review A 2019年第3期100卷 033614-033614页

作者： Lijuan Guo Sebastian Greschner Siyu Zhu Wanzhou Zhang College of Physics and Optoelectronics Taiyuan University of Technology Taiyuan 030024 China Department of Quantum Matter Physics University of Geneva 1211 Geneva Switzerland Key Lab of Advanced Transducers and Intelligent Control System of Ministry of Education Taiyuan University of Technology Taiyuan 030024 China

We study the extended Jaynes-Cummings-Hubbard model on triangular cavity lattices and zigzag ladders. By using density-matrix renormalization-group methods, we observe various types of solids with different density patterns and find evidence for light supersolids, which exist in extended regions of the phase diagram of the zigzag ladder. Furthermore, we observe strong pair correlations in the supersolid phase due to the interplay between the atoms in the cavities and atom-photon interaction. By means of cluster mean-field simulations and a scaling of the cluster size extending our analysis to two-dimensional triangular lattices, we present evidence for the emergence of a light supersolid in this case also.

关键词： Supersolids Cold gases in optical lattices Hubbard model

来源：评论

学校读者我要写书评

暂无评论

Real-world Robot Reaching Skill Learning Based on Deep Reinforcement Learning

Real-world Robot Reaching Skill Learning Based on Deep Reinf...

引用

第32届中国控制与决策会议

作者： Naijun Liu Tao Lu Yinghao Cai Rui Wang Shuo Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced TechnologyChinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology of the Chinese Academy of Sciences

Traditional programming method can achieve certain manipulation tasks with the assumption that robot environment is known and ***,with robots gradually applied in more domains,robots often encounter working scenes which are complicated,unpredictable,and *** overcome the limitation of traditional programming method,in this paper,we apply deep reinforcement learning(DRL) method to train robot agent to obtain skill *** policy trained with DRL on real-world robot is time-consuming and costly,we propose a novel and simple learning paradigm with the aim of training physical robot ***,our method train a virtual agent in an simulated environment to reach random target position from random initial ***,virtual agent trajectory sequence obtained with the trained policy,is transformed to real-world robot command with coordinate transformation to control robot performing reaching *** show that the proposed method can obtain self-adaptive reaching policy with low training cost,which is of great benefits for developing intelligent and robust robot manipulation skill system.

关键词： Robot reaching skill learning deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on Feedforward control Based on Robot Dynamics Parameters Identification

Research on Feedforward Control Based on Robot Dynamics Para...

引用

IEEE International Conference on Mechatronics and Automation

作者： Xingmao Shao Shoujun Wang Liusong Yang Nan Liu Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin China CITIC Heavy Industries Company Ltd. Luoyang China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

Accurate robot dynamics model can effectively improve the motion control performance of robot, and accurate dynamics parameters are the basis for establishing dynamics model. This paper discusses the parameter identification method of the tandem manipulator and the feedforward control scheme based on dynamics. First, we deduced the basic parameters of the first three joints of the UR5 manipulator, and identified the parameters through experimental sampling and calculation. Secondly, we established a feedforward control mechanism based on dynamics using the Simulink platform, and simulated and verified the feedforward control of the robot three-axis system. The experimental results show that the feedforward control scheme based on robot dynamics can effectively improve the error convergence performance, which proves the effectiveness of the method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Swimming Characteristics of Soft robot with Magnetoelastic Material

Swimming Characteristics of Soft robot with Magnetoelastic M...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Hongbiao Xiang Mengwei Li Tilei Zhang Shoujun Wang Xiuping Yang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China

Cable-less micro-robots have exhibit great capabilities for remote applications in small and constrained environments, especially in biotechnology and healthcare. This paper presents a swimmer propelled by its undulatory deformation using magnetoelastic composite material. The robot can move freely on water surface driven through a function of magnetic field, such as forward, backward and steering with different velocity. The magnetic field is generated by 3D Helmholtz coils, and the locomotion of the micro swimming robot is controlled by different applied magnetic field. To understand the characteristics of the swimmer, the force balance equation is established, and the morphologies of swimmer with different magnetic field are analyzed and described through finite element analysis method. Furthermore, we discuss and analyze relationship between the parameters of magnetic field and the speed of the swimmer. The experimental results verified the speed model of the swimming robot, which is influenced by the frequency and strength of magnetic field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SI-YOLO: A Deep Learning Algorithm Suitable for Surgical Instrument Detection

SSRN

引用

SSRN 2022年

作者： Liu, Zhenzhong Zhou, Yifan Sun, Qiyuan Wang, Yan Polat, Kemal Nour, Majid Alenezi, Fayadh Alhudhaif, Adi Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China Tianjin300384 China Department of Electrical and Electronics Engineering Bolu Abant Izzet Baysal University Bolu14280 Turkey Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia Department of Electrical Engineering College of Engineering Jouf University 72238 Saudi Arabia Department of Computer Science College of Computer Engineering and Sciences in Al-kharj Prince Sattam bin Abdulaziz University P.O. Box 151 Al-Kharj 11942 Saudi Arabia

Surgical instrument detection and tracking is one of the core technologies of surgical robots, which can assist clinicians in completing operations. However, existing methods need further improvement in terms of real-time performance and accuracy. We propose a deep learning algorithm, SI-YOLO, for detection of surgical instruments. SimAM attention mechanism is used to improve the feature extraction ability of YOLOv5. Replacing PANet with BiFPN in the neck network improves the feature fusion strategy. The α-IoU loss function is used to improve the regression accuracy of detection boxes. The mAP and FPS of the SI-YOLO reach 99.2% and 120 frames/sec, respectively. Aiming at the problem of ID transformation in the disappearance and occlusion of surgical instruments, the Inception-ResNet-v2 structure is added on the basis of the appearance feature extraction network Cosine of the DeepSort tracking algorithm. Combining SI-YOLO with the improved DeepSort implements the Tracking by Detection (TBD) algorithm. In the case of device disappearance or occlusion, the frequency of ID transitions is reduced by approximately 30%. Finally, we built a simulated surgery experimental platform, established our own data set, and realized the preliminary application of the proposed algorithm. © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Ultra-wideband terahertz absorber based on graphene modulation: retraction

引用

Applied optics 2021年第30期60卷 9379页

作者： Xiaogang Li Guang Feng Suben Lin Lyncwell Innovation Intelligent System (Zhejiang) Co. Ltd. Ocean Science and Technology Innovation Park No. 19 Binhai 3rd Road Wenzhou 325024 China Key Lab of Advanced Transducers and Intelligent Control System Ministry of Education and Shanxi Province College of Physics and Optelectronics Taiyuan University of Technology Taiyuan 030024 China

The referenced paper [Appl. Opt.60, 3170 (2021)APOPAI0003-693510.1364/AO.420143] has been retracted by the authors.

关键词： Finite difference time domain Graphene Microwaves Modulation Ultrawideband signals

来源：评论

学校读者我要写书评

暂无评论

Robust Tensor Principal Component Analysis Based on F-norm

Robust Tensor Principal Component Analysis Based on F-norm

引用

IEEE International Conference on Mechatronics and Automation

作者： Weimin Ge Jinxiang Li Xiaofeng Wang National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Binshui Xidao 391 Xiqing District Tianjin China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Binshui Xidao 391 Xiqing District Tianjin China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

Tensor principal component analysis (TPCA) has been widely used to extract appearance features of colour objects or colour scenes presented in tensor form. Using L 1 -norm as the distance metric, the existing TPCA-L 1 with its greedy (TPCA-L 1 -G) and non-greedy (TPCA-L 1 -NG) algorithms were proposed to reduce the sensitivity to outliers. The two algorithms, however, only derived TPCA solution in a form of two-dimensional matrix without actually extending them to the tensor subspaces and without performing experimental verification for tensor data. Simultaneously, the spatial correlations between pixels of the raw tensor data cannot be effectively preserved. To solve the problems, a robust tensor principal component analysis algorithm based on F-norm distance metric is proposed in this paper, which not only preserves the spatial structure of the raw data, but also reduces the sensitivity to outliers in tensor data. Experiments on reconstruction error and classification rate show that the proposed algorithm is effective and superior to other tensor algorithms in performances.

关键词：

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：