检索结果-内蒙古大学图书馆

2019 IEEE International Conference on Real-Time Computing and robotics, RCAR 2019

作者： Tian, Chaoran Ou, Yongsheng Qu, Yangyang Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University OfChinese Academy of Sciences Beijing100049 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes OfAdvanced Technology Chinese Academy OfSciences Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence Synergic Systems Shenzhen Institutes of Advanced Technology Shenzhen518055 China

ISBN: (纸本)9781728137261

The approach of feature-based visual SLAM is very popular in Micro Aerial Vehicle (MAV) navigation and wheeled mobile robot (WMR) navigation. Most modern feature-based visual SLAM frameworks extract a fixed number of feature points and then match the feature points by brute force or adopt Fast Library for Approximate Nearest Neighbors (FLANN). The features' extracting and matching processes will determine the localization accuracy and mapping quality significantly. In this paper, we propose a feature matching algorithm for the robot equipped with a binocular camera, which provides accurate real-time localization performance and robustness. In our feature matching method, both the geometric relationship of image feature points and the similarity of descriptor are considered. This paper presents a visual SLAM framework based on geometric cluster matching and the effectiveness of the proposed method is verified by practical experiments. © 2019 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Anchor-based spatio-temporal attention 3D convolutional networks for dynamic 3D point cloud sequences

arXiv

引用

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

Corrigendum to “SIAT-WEXv2: A Wearable Exoskeleton for Reducing Lumbar Load during Lifting Tasks”

引用

Complexity 2021年第1期2021卷

作者： Xinyu Ji Dashuai Wang Pengfei Li Liangsheng Zheng Jianquan Sun Xinyu Wu Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen *** CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Shenzhen *** Wuhan University of Technology Wuhan *** Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen China

来源：评论

学校读者我要写书评

暂无评论

Walking Control of Biped Robots on Uneven Terrains Based on SLIP Model

Walking Control of Biped Robots on Uneven Terrains Based on ...

引用

IEEE Workshop on advanced robotics and its Social Impacts, ARSO

作者： Xiang Meng Zhangguo Yu Gao Huang Xuechao Chen Weijie Qi Qiang Huang Bo Su School of Mechatronical Engineering Beijing Institute of Technology Beijing China Beijing Advanced Innovation Center for Intelligent Robotics and Systems Beijing Institute of Technology Key Laboratory of Biomimetic Robots and Systems Ministry of Education Beijing China International Joint Research Laboratory of Biomimetic Robots and Systems Ministry of Education Beijing Advanced Innovation Center for Intelligent Robotics and Systems Beijing Institute of Technology Beijing China China North Vehicle Research Institute Beijing China

Having human-like legged structure, biped robots are regarded as the most promising robots that can take the place of human to work in the environments designed for human beings. To this end, it is the premise for biped robots to achieve stable walking on uneven ground. This paper presents a control strategy for a biped robot based on spring-loaded inverted pendulum (SLIP) model, which controls the joint torque of the robot by obtaining the errors of length and angular position of virtual spring legs. Additionally, this paper proposes a new control method of adjusting the length of legs to enable the robot to achieve stable walking on unstructured terrains, such as staircases. In the end, the simulation results corroborate the effectiveness of the proposed approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of an Adaptive Prosthetic Hand *

Development of an Adaptive Prosthetic Hand *

引用

IEEE International Conference on robotics and Biomimetics

作者： Xu Yong Xiaobei Jing Xinyu Wu Jiang Jiang Hiroshi Yokoi Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences (CAS) CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences (CAS) Shenzhen China Department of Mechanical Engineering and Intelligent Systems The University of Electro-communications

Inspired by biomechanics, an adaptive prosthetic hand which not only considered the function of the motion of the digits but also the palm, is presented in this paper. The human hand consists of different kinds of bones, the phalanges in the digits and the metacarpals in the palm, which cooperate to perform adaptable and dexterous motions. Many existent prosthetic hands focus mainly on the movements of the digits, ignoring the palm. The proposed hand has 15 movable joints in the fingers and the thumb, and 2 movable metacarpals in the palm. The thumb and the four fingers are able to flex independently and adaptively wrap along with the shape of the object. The palm could perform an adaptive holding to some extent through the grasping process, due to the movable metacarpals. Furthermore, the hand design is also considered the weight and size limitations for being used as a prosthesis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Image segmentation method by multi-scale local thresholding based on class uncertainty theory

An Image segmentation method by multi-scale local thresholdi...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Zhou, Likai Jiang, Yuyang Liang, Guoyuan Wu, Xinyu Zhu, Jiafeng Xiang, Huaikun Shenzhen Institutes of Advanced Technology CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences China School of Automotive and Transportation Engineering Shenzhen Polytechnic Shenzhen Guangdong Province China School of Math Sun Yat-sen University Guangzhou Guangdong Province China

ISBN: (纸本)9781728163215

Image segmentation is one of the most important core technologies in the field of image processing and computer vision, which has lots of applications specifically in medical image analysis. Due to medical imaging mechanism, medical images usually suffer from heavy noises, uneven intensity distribution and fuzzy boundaries between biological tissues. That makes classical segmentation methods based on global or local thresholding difficult to get accurate results. This paper proposes an image segmentation method by multi-scale local thresholding based on class uncertainty theory. Firstly, the original image is divided into a set of sub-regions with different scales by using a multi-layer pyramid structure. Secondly, the energy function with inequality constraints is constructed based on class uncertainty and region uniformity. Then by an iterative process, the optimal local threshold for each sub-region are calculated by an optimization algorithm for each layer until the final optimal threshold mask is determined for image segmentation. Experimental results verify that the proposed method can effectively eliminate the interferences caused by image noises, intensity unevenness and fuzzy boundaries, and preserve details of object structure while segmenting the object from the background. Segmentation results demonstrate the superior performance of the proposed method by comparison with supervised range-constrained thresholding methods (RCOtsu), classical global/local Otsu method, and the minimization of homogeneity- and uncertainty-based energy method (MHUE). © 2019 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Depth map inpainting using a fully convolutional network

Depth map inpainting using a fully convolutional network

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Xiong, Rong Liu, Guodong Qu, Yangyang Ou, Yongsheng 1068 Xueyuan Blvd Shenzhen China Shenzhen College of Advanced Tech-nology University of Chinese Academy of Sciences 1068 Xueyuan Blvd Shenzhen China Guangdong Provin-cial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences 1068 Xueyuan Blvd Shenzhen China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology 1068 Xueyuan Blvd Shenzhen China

ISBN: (纸本)9781728163215

Emerging consumer depth cameras, such as Microsoft Kinect and ASUS Xtion Pro, are low-cost depth sensors which can capture the depth maps of the scene, and obtaining color images of the corresponding scenes at the same time. Depth information is very important for computer vision applications, and to acquire the accurate depth information is challengeable. However, due to the limitations of imaging principle, depth maps acquired by such devices are often noisy and will lose depth values for certain areas. In this paper, we present a novel method for depth inpainting problem using a Fully Convolutional Network (FCN). The network has two input branches. One branch is a color image that has been processed by a convoluted hidden layer, and the other one is the missing depth map. Besides, we add a shortcut in order to improve the feature extraction capability of the network. We have validated our method in the Middlebury Stereo Dataset and real-world scenes captured by Kinect 2.0. Experiments show that our method has better applicability and reliability than traditional methods in depth inpainting. © 2019 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Cooperative Carbon Nanotube Nanomanipulation For Field Effect Transistor

Cooperative Carbon Nanotube Nanomanipulation For Field Effec...

引用

IEEE International Conference on Nano/Micro Engineered and Molecular systems

作者： Donglei Chen Lining Sun Zhan Yang Toshio Fukuda Tao Chen Provincial Jiangsu Key Laboratory for Advanced Robotics and Collaborative Innovation Center of Suzhou Nano Science and Technology soochow university Suzhou China Department of Micro-Nano Systems Engineering Nagoya University Janpan

In this paper, based on the operating environment of scanning electron microscope (SEM), the cooperative control of carbon nanotubes by controlling multi-operator hand was realized by controlling the robot operator with multiple degrees of freedom. Firstly, the carbon nanotube was picked up from the bulk by the nano manipulations. Then the nanotube was transferred on the surface of the metal electrode of the chip using the two nano manipulations and fixed on by electron beam induced deposition (EBID). In this robotics manipulation system, operation and assembly of carbon nanotube were successfully realized. The voltage-current property of the carbon nanotube was also evaluated in the SEM.

关键词： Carbon nanotubes Electrodes Scanning electron microscopy Metals Robots Probes Electron beams

来源：评论

学校读者我要写书评

暂无评论

Motion control of nanomanipulation platform based on feedforward compensation inside SEM

Motion control of nanomanipulation platform based on feedfor...

引用

IEEE International Conference on Nano/Micro Engineered and Molecular systems

作者： Mingyu Wang Lining Sun Zhan Yang Toshio Fukuda Tao Chen Provincial Jiangsu Key Laboratory for Advanced Robotics and Collaborative Innovation Center of Suzhou Nano Science and Technology soochow university Suzhou China Department of Micro-Nano Systems Engineering Nagoya University Japan

With the rapid development and wide application of nanotechnology, nanodevice manufacturing with nanotechnology as its core has become one of the key research areas in nanotechnology. Micro-nano operating system based on scanning electron microscope (SEM) is one of the methods to realize nanodevice manufacturing. SmarAct nanomanipulation platform is an important component of micro-nano operating system, which can realize linear motion in three-dimensional space. However, due to mechanical structure and assembly errors, the SmarAct nanomanipulation platform cannot meet the stable requirements during motion. In this paper, the visual feedback and image processing are used to describe the motion trajectory of SmarAct operator. Based on the motion mechanism of SmarAct operator, the error source is analyzed, at the same time, the motion error is modeled according to the motion trajectory. The feedforward compensation is used to realize the stable linear motion of SmarAct operator, and the interpolation algorithm is used to realize the trajectory motion control of the SmarAct nanomanipulation platform.

关键词： Trajectory Scanning electron microscopy Operating systems Carbon nanotubes Interpolation Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A lightweight soft exoskeleton in lower limb assistance

A lightweight soft exoskeleton in lower limb assistance

引用

Chinese Automation Congress (CAC)

作者： Yu Zhang Zhuo Wang Chunjie Chen Tao Fang Ruimei Sun Yanjie Li School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Shenzhen China ShenZhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen China BeiJing Aerospace Wanyuan Science Technology Co. Ltd. Beijing China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

The soft exoskeleton is a wearable robot which is functioned to improve the capacity of human walking or loading. The metabolic of human is increase with the additional load, one integrated design method is used to reduce this effect in this paper. Meanwhile, in order to enhance the convenience and decrease the disturbance to wearer, the wireless module is used to replace the signal line. The nonlinear characteristics and uncertainty of flexible material make the control of soft exoskeleton system be a challenge, a switching controller is proposed to deal with this problem in this paper. It consists of Iterative learning control (ILC) based stable controller and admittance control based unstable controller, functioned with wearers walking stable and not. An experiment of force tracking is conducted to verify the controller performance in this paper, and the result demonstrate that the tracking is well after 20 iteration. In order to evaluate the performance of assistance of soft exoskeleton, five health adult male take part in metabolic experiment By compare the metabolic rate between the wear soft exoskeleton and not wear, the metabolic rate are decrease 7.33%, 14.56% and 10.45% with the walking speed of 3km/h, 5km/h and 7km/h, which are corresponding absolute values decrease of 0.46W/kg, 1.60W/kg and 1.21W/kg respectively.

关键词： AC motors Mechanical cables Wireless communication Pulleys Microprocessors Micromechanical devices Germanium

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：