检索结果-内蒙古大学图书馆

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

GC-IGTG: A rehabilitation gait trajectory generation algorithm for lower extremity exoskeleton

GC-IGTG: A rehabilitation gait trajectory generation algorit...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： He, Yong Wu, Xinyu Ma, Yue Cao, Wujing Li, Nan Li, Jinke Feng, Wei Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen518055 China Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781728163215

It is important to offer a natural and personalized rehabilitation gait trajectory, especially in the early stages of walking rehabilitation, for the patients with lower limb disability. Lower extremity exoskeleton has been proven to be efficient to provide highly repeatable and accurate rehabilitation exercise, but most existing exoskeletons' gait trajectories won't vary with the users. This paper proposes an algorithm, named as gait cell based individualized gait trajectory generation (GC-IGTG), for the purpose of offering a natural and personalized gait trajectory reference for the lower extremity exoskeleton based on the body parameters of the patients. The GC-IGTG is based on extreme learning machine and AutoEncoder, which makes it achieve fast training speed and suitable for small sample training conditions. The gait cell concept is proposed to improve the efficiency and safety of the algorithm. The experimental results indicate that the generated trajectories with GC-IGTG are almost identical to the original ones. © 2019 IEEE.

关键词： Patient rehabilitation

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

BTI Aging Monitoring based on SRAM Start-up Behavior

BTI Aging Monitoring based on SRAM Start-up Behavior

引用

Asian Test Symposium (ATS)

作者： Shengyu Duan Peng Wang Gaole Sai School of Computer Engineering and Science Shanghai University Shanghai China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology China

ISBN: (数字)9781728174679

ISBN: (纸本)9781728174686

Bias Temperature Instability (BTI) is one of the dominant CMOS aging mechanisms. It causes time-dependent variation, threatening circuit lifetime reliability. BTI-induced circuit errors are not detectable at the fabrication stage. On-line monitoring schemes are therefore necessary to capture the degradations during the operational time. Traditional aging monitoring techniques exhibit high implementation complexity and low stability. In this paper, we propose a BTI monitoring approach by simply tracking the start-up behavior of SRAM cells. SRAM is a widely used on-chip device in many applications. We study the impact of BTI for SRAM start-up values and age some cells in a manipulated manner. The BTI degradation is evaluated based on the number of SRAM cells starting with a certain value. This technique can be used to estimate the degradation for on-chip logic circuits without introducing additional circuitry, and thus has very low implementation complexity. We use an SRAM array with 1024 cells to estimate the degradations for multiple logic circuits, and show the average mean absolute percentage error as 8.48%. In addition, this technique is robust considering process, voltage and temperature variations.

关键词： Degradation Monitoring Logic circuits Transistors SRAM cells Aging System-on-chip

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

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

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

A registration-aided domain adaptation network for 3D Point cloud based place recognition

arXiv

引用

arXiv 2020年

作者： Qiao, Zhijian Hu, Hanjiang Shi, Weiang Chen, Siyuan Liu, Zhe Wang, Hesheng Department of Automation 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 Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Mechanical Engineering Carnegie Mellon University United States Department of Computer Science and Technology University of Cambridge United Kingdom

In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance. However, it is time-consuming and effort-costly to obtain high-quality point cloud data for place recognition model training and ground truth for registration in the real world. To this end, a novel registration-aided 3D domain adaptation network for point cloud based place recognition is proposed. A structure-aware registration network is introduced to help to learn features with geometric information and a 6-DoFs pose between two point clouds with partial overlap can be estimated. The model is trained through a synthetic virtual LiDAR dataset through GTA-V with diverse weather and daytime conditions and domain adaptation is implemented to the real-world domain by aligning the global features. Our results outperform state-of-the-art 3D place recognition baselines or achieve comparable on the real-world Oxford RobotCar dataset with the visualization of registration on the virtual dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

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

Research on landing collision experiment of gecko robot with bio-inspired dry adhesive foot

Research on landing collision experiment of gecko robot with...

引用

2018 IEEE International Conference on Information and Automation, ICIA 2018

作者： Yu, Zhiwei Shi, Ye Luo, Ao Tao, Jielian Yang, Simon X. Institute of Bio-inspired Structure and Surface Engineering Nanjing University of Aeronautics and Astronautics Nanjing China Advanced Robotics and Intelligent Systems University of Guelph Guelph Canada

ISBN: (纸本)9781538680698

The adhesion robot has better adhesion performance in a vacuum than others, such as magnetic absorption robot and vacuum adsorption robot. It has broad application prospect and far-reaching practical significance in the field of space On-Orbit Servicing Robots. The stability motion of the adhesion robot on a flat surface has been studied in depth, but the problem of the impact force between the adhesion robot and the flat surface when landing on the surface, which is an inevitable problem that the adhesion robot lands on the flat surface and achieve stable, has been researched little. Therefore, this article has researched about the impact process between adhesion robots and flat surfaces. An impact experiment about the bionic foot was performed on a self-built experimental platform. It reveals the state of motion and the changes of the force between the bionic foot and the flat surface at the moment of impact. The conclusions have been verified on the gecko-inspired robot, and are of great significance for the future adhesion robot to achieve a stable landing on a target surface. © 2018 IEEE.

关键词： Adhesives

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：