检索结果-内蒙古大学图书馆

Hydrodynamic Analysis and Verification of an Innovative Whale Shark-like Underwater Glider

Journal of Bionic Engineering 2020年第1期17卷 123-133页

作者： Huijie Dong Zhengxing Wu Min Tan Junzhi Yu State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering ScienceBIC-ESATCollege of EngineeringPeking UniversityBeijing 100871China

This paper presents an innovative design for a biomimetic whale shark-like underwater glider aiming at the combination of high maneuverability and long *** a hybrid of the underwater glider and the robotic fish,its pectoral fins and tail can serve as not only the external control surfaces for attitude regulation during gliding but also the propellers for agile fish-like swimming *** verify the gliding capability of the whale shark-like glider and prepare for future dynamic analysis,the hydrodynamic coefficients,including drag,lift,sliding force,and corresponding moments are estimated through computational fluid dynamics *** addition,the hydrodynamic analyses of the proposed glider and an equivalent conventional glider during steady gliding motion are executed for *** experiments are performed to verify the downward gliding *** results reveal that the whale shark-like glider has less drag as well as higher lift-to-drag ratio and a markable gliding capability in *** may offer important inspiration for improving the gliding efficiency and performance of an underwater glider in biomimetic shape design.

关键词： biomimetic robot CFD hydrodynamic analysis underwater glider

来源：评论

学校读者我要写书评

暂无评论

Double Domain Guided Real-Time Low-Light Image Enhancement for Ultra-High-Definition Transportation Surveillance

arXiv

引用

arXiv 2023年

作者： Qu, Jingxiang Liu, Ryan Wen Gao, Yuan Guo, Yu Zhu, Fenghua Wang, Fei-Yue The School of Navigation The State Key Laboratory of Maritime Technology and Safety Wuhan University of Technology Wuhan430063 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Real-time transportation surveillance is an essential part of the intelligent transportation system (ITS). However, images captured under low-light conditions often suffer the poor visibility with types of degradation, such as noise interference and vague edge features, etc. With the development of imaging devices, the quality of the visual surveillance data is continually increasing, like 2K and 4K, which has more strict requirements on the efficiency of image processing. To satisfy the requirements on both enhancement quality and computational speed, this paper proposes a double domain guided real-time low-light image enhancement network (DDNet) for ultra-high-definition (UHD) transportation surveillance. Specifically, we design an encoder-decoder structure as the main architecture of the learning network. In particular, the enhancement processing is divided into two subtasks (i.e., color enhancement and gradient enhancement) via the proposed coarse enhancement module (CEM) and LoG-based gradient enhancement module (GEM), which are embedded in the encoder-decoder structure. It enables the network to enhance the color and edge features simultaneously. Through the decomposition and reconstruction on both color and gradient domains, our DDNet can restore the detailed feature information concealed by the darkness with better visual quality and efficiency. The evaluation experiments on standard and transportation-related datasets demonstrate that our DDNet provides superior enhancement quality and efficiency compared with the state-of-the-art methods. Besides, the object detection and scene segmentation experiments indicate the practical benefits for higher-level image analysis under low-light environments in ITS. The source code is available at https://***/QuJX/DDNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A two-step method for 4-pin form-closure gripper with grasping force optimization

引用

ASIAN JOURNAL OF control 2021年第5期23卷 2079-2086页

作者： Li, Rui Li, Yinlin Su, Xiaojie Chongqing Univ Sch Automat Chongqing 400040 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Grasp planning and the grasping force optimization are challenging issues associated with the dexterous robotic hand grasping problem. To ensure a safe, fast, and stable grasp for robots, careful determination of the grasping points and the grasping forces is required. The former creates an open question because of the availability of multiple solutions. The latter is formulated as a problem for minimizing an objective function subject to form-closure constraints and balance constraints of external forces. In this work, we propose a novel approach for the grasping force optimization of the 4-pin environmental constraint-based form-closure grasp using dynamic neural networks. To find a form-closure grasp, we propose an environmental constraint-based algorithm and convert it to a problem of finding the local minima of a constraint region, resulting in an easy determination of the grasping points with the guarantee of grasping safety. To satisfy the grasping force limit of the contact points, we solve the grasping force optimization problem with friction constraint, which maximize the efficiency of the applied force and power of the dexterous hand. The proposed approach is evaluated with 4-pin gripper, and the result demonstrates that we can plan a safe, fast, and stable grasp from any initial state to a form-closure grasping state.

关键词： 4‐ pin gripper form closure grasping force control

来源：评论

学校读者我要写书评

暂无评论

EK-Net++: Real-time scene text detection with expand kernel distance and Epoch Adaptive Weight

引用

Expert systems with Applications 2025年 267卷

作者： Zhu, Boyuan Chen, Xi Tang, Quan Chen, C.L. Philip Liu, Fagui Computer Science and Engineering South China University of Technology Guangzhou510006 China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen518066 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China

Recently, scene text detection has received significant attention due to its wide applications. Accurate detection in complex scenes of multiple scales, orientations, and curvature remains a challenge. Component-based methods have emerged as the dominant approach for offering a more flexible way to achieve superior performance. However, Component-based methods employ the Vatti clipping algorithm for multi-instance training to handle the difficulty of arbitrary-shaped text. Yet we identify several bias results from these approaches called the "shrinked kernel" leading to decreased accuracy. Additionally, almost all text detection methods fail to consider the characteristics of different datasets and directly assign fixed loss weights to multi-instances. To address these limitations, we propose a new approach named Expand Kernel Network (EK-Net++), which presents the expand kernel distance map to compensate for the previous deficiency and incorporates three-stage regression to complete integral instance detection. Furthermore, we design the Epoch Adaptive Weight algorithm which dynamically distinguishes the characteristics of different datasets. EK-Net++ not only achieves precise positioning of arbitrary-shaped text but also strikes a balance between performance and speed. Evaluation results show that EK-Net++ attains state-of-the-art or competitive performance compared to other advanced methods, e.g., F-measure of 86.72% at 35.42 FPS on ICDAR 2015, F-measure of 85.83% at 40.13 FPS on CTW1500. © 2024 Elsevier Ltd

关键词： Epoch Adaptive Weight Expand kernel distance Real-time Scene text detection

来源：评论

学校读者我要写书评

暂无评论

A real-time semantic segmentation method for autonomous driving in surface mine 25

A real-time semantic segmentation method for autonomous driv...

引用

IEEE 25th International Conference on Intelligent Transportation systems (ITSC)

作者： Wei, Qinggong Song, Ruiqi Yang, Xue Ai, Yunfeng Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Waytous Inc Qingdao 266109 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China

ISBN: (数字)9781665468800

ISBN: (纸本)9781665468800

Semantic segmentation for perception of autonomous vehicles has made great progress with the development of deep learning technique. However, existing related studies mainly focus on urban scenes, thus semantic segmentation for perception of autonomous mining trucks in surface mine remains to be further explored. Considering the importance of dataset in deep learning technique, we first built a semantic segmentation dataset of surface mine. In surface mine environment, it is a fact that the particularity of the dataset brings tremendous challenge for semantic segmentation, for example, the scale variation of objects and long-tail distribution problems. So, we propose a lightweight semantic segmentation framework which consists of a multi-branch feature extraction structure and an adaptive feature fusion module. In addition, we adopt auxiliary supervision strategy to mitigate the side effect of long-tail distribution problem by mining hard samples. Experiments on our dataset show outperforming result compared with existing state-of-the-art lightweight semantic segmentation methods.

关键词： Deep learning Feature extraction Real-time systems Task analysis Autonomous vehicles Intelligent transportation systems

来源：评论

学校读者我要写书评

暂无评论

Modeling and analysis of an underwater biomimetic vehicle-manipulator system

引用

Science China(Information Sciences) 2022年第3期65卷 255-257页

作者： Xuejian BAI Yu WANG Shuo WANG Rui WANG Min TAN Wei WANG School of Artificial Intelligence University of Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology School of Control Science and Engineering Shandong University

In recent years, underwater vehicle-manipulator systems(UVMSs) have captured researchers' attention. Inspired by fish, bionic mechanisms were introduced into a *** underwater biomimetic vehicle-manipulator system(UBVMS) is actuated by two symmetrically arranged biomimetic undulatory fin propulsors [1]. Based on the UBVMS, some topics have been researched, such as freefloating autonomous operation [2, 3], three-dimensional helical path following [4], and underwater video processing [5].

关键词： underwater biomimetic vehicle underwater robots underwater vehicle-manipulator system biomimetic robots hydrodynamic modeling

来源：评论

学校读者我要写书评

暂无评论

Coordinated Cyber Security Enhancement for Grid-Transportation systems With Social Engagement

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2024年第5期8卷 3199-3213页

作者： Zhao, Pengfei Li, Shuangqi Hu, Paul Jen-Hwa Cao, Zhidong Gu, Chenghong Xie, Da Zeng, Daniel Dajun Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Univ Bath Dept Elect & Elect Engn Bath BA2 7AY Avon England Beijing Inst Technol Natl Engn Lab Elect Vehicles Beijing 100081 Peoples R China Univ Utah David Eccles Sch Business Salt Lake City UT 84112 USA Shanghai Jiao Tong Univ Dept Elect Engn Shanghai 200240 Peoples R China

Effective coordination of energy and transportation systems is fundamental and vital to smart city management. Yet, the deeply intertwined information and communication technologies have exposed smart city management to malicious cyberattacks vastly. This study develops a two-stage mitigation strategy for integrated transportation-energy systems (TESs) by coordinating energy and transportation systems to safeguard against false data injection attacks (FDIAs). Our strategy targets social engagements by electric vehicle (EV) users who can be incentivized to alter their regular EV usage patterns for supporting the energy system via vehicle-to-grid actions. We consider a TES that contains a multi-energy system comprised of power and gas systems as well as an urban transportation system. Integrated system operators can take emergency measures to coordinate important system assets (e.g., traditional generators, renewable generators, EV fleets) in a sensible and intelligent way, and thereby mitigate the consequences of FDIAs. Specifically, we take a two-stage distributionally robust approach to cope with uncertain FDIAs, with which a moment-based ambiguity set is employed to yield the worst-case uncertainty distribution. We leverage constraint generation-based relaxation to solve the problem iteratively. To demonstrate our strategy's value and practical utilities, we use a coupled urban TES to conduct case studies. According to the evaluation results, the optimized EV scheduling and energy dispatch scheme produced by the proposed strategy can contain cyberattacks' impacts and enhance cyber resilience in smart city management more effectively.

关键词： Transportation Computer crime Renewable energy sources Smart cities Vehicle-to-grid Uncertainty Turbines Cyber-attack cyber security electric vehicle false data injection attacks multi-energy system smart city manage- ment social effort

来源：评论

学校读者我要写书评

暂无评论

The Potential of Low-Altitude Airspace: The Future of Urban Air Transportation

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第8期9卷 5250-5254页

作者： Hailong Huang Jiangcheng Su Fei-Yue Wang Department of Aeronautical and Aviation Engineering Hong Kong Polytechnic University Hong Kong China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Engineering Macau University of Science and Technology Macau China

Many megacities, such as London, New York, Paris, Tokyo, Beijing, and Shanghai, have been born due to urban- ization. While citizens enjoy the convenience of city life, such cities suffer from drawbacks of transportation: the average commute time has been increasing over the past years. With the maturity of electric vertical take-off and landing (eVTOL) aircraft technology, decision-makers have started to look upward to the low-altitude airspace. This blue space has the potential to reshape the transportation system and shorten the average travel time in daily life. To explore this emerging area, we held a Distributed/Decentralized Hybrid Workshop on Sustain- ability for Transportation and Logistics (DHW-STL), and this letter summarizes the outcomes of our discussion. Here, we first pinpoint the pain issues of conventional transportation. Then, we present the emerging low-altitude airspace transportation option, followed by a discussion on how such a new transportation option can integrate with the conventional ground-based transportation system. Some thoughts about the pathway to further development of the integrated transportation system are shared finally.

关键词： Aircraft Transportation Urban areas Air traffic control Traffic congestion Meters Aircraft propulsion Motors Logistics Indexes

来源：评论

学校读者我要写书评

暂无评论

Webly Supervised Knowledge-Embedded Model for Visual Reasoning

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systems 2024年第7期35卷 9829-9843页

作者： Zheng, Wenbo Yan, Lan Zhang, Wenwen Wang, Fei-Yue Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan 430070 Peoples R China Wuhan Univ Technol Sanya Sci & Educ Innovat Pk Sanya 572000 Peoples R China Hunan Univ Coll Informat Sci & Engn Changsha 410082 Peoples R China Natl Supercomp Ctr Changsha 410082 Hunan Peoples R China Shaanxi Normal Univ Sch Comp Sci Xian 710119 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Visual reasoning between visual images and natural language remains a long-standing challenge in computer vision. Conventional deep supervision methods target at finding answers to the questions relying on the datasets containing only a limited amount of images with textual ground-truth descriptions. Facing learning with limited labels, it is natural to expect to constitute a larger scale dataset consisting of several million visual data annotated with texts, but this approach is extremely time-intensive and laborious. Knowledge-based works usually treat knowledge graphs (KGs) as static flattened tables for searching the answer, but fail to take advantage of the dynamic update of KGs. To overcome these deficiencies, we propose a Webly supervised knowledge-embedded model for the task of visual reasoning. On the one hand, vitalized by the overwhelming successful Webly supervised learning, we make much use readily available images from the Web with their weakly annotated texts for an effective representation. On the other hand, we design a knowledge-embedded model, including the dynamically updated interaction mechanism between semantic representation models and KGs. Experimental results on two benchmark datasets demonstrate that our proposed model significantly achieves the most outstanding performance compared with other state-of-the-art approaches for the task of visual reasoning.

关键词： Attention model knowledge embedding visual reasoning Webly supervised learning

来源：评论

学校读者我要写书评

暂无评论

A novel software framework for magnetic particle imaging reconstruction

引用

INTERNATIONAL JOURNAL OF IMAGING systems AND TECHNOLOGY 2022年第4期32卷 1119-1132页

作者： Shen, Yusong Hu, Chaoen Zhang, Peng Tian, Jie Hui, Hui Southeast Univ Sch Comp Sci & Engn Nanjing 211189 Peoples R China Inst Automat CAS Key Lab Mol Imaging State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Beijing Key Lab Mol Imaging Beijing Peoples R China Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing Peoples R China Beihang Univ Beijing Adv Innovat Ctr Big Data Based Precis Med Sch Med Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

Magnetic particle imaging is a novel tomographic imaging technique that enables noninvasive and highly sensitive imaging of superparamagnetic iron oxide nanoparticles distributed in living subjects. Several studies have reported on the development of reconstruction algorithms;however, a unified software framework for magnetic particle imaging reconstruction has yet to be developed. Herein, we propose a high-performance, flexible, and easy-to-use magnetic particle imaging reconstruction framework using the Python programming language. The magnetic particle imaging reconstruction framework consists of the data access, preprocessing, image reconstruction, and postprocessing phases. We used the proposed framework to simulate the x-space and system matrix-based reconstruction methods with Cartesian and Lissajous scan trajectories. The reconstruction results of an open magnetic particle imaging dataset and a numerically simulated phantom demonstrated that the magnetic particle imaging reconstruction framework provides a reliable and accessible environment for magnetic particle imaging reconstruction, which can be extended and customized.

关键词： magnetic particle imaging Python toolkit reconstruction scan simulation software framework

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：