检索结果-内蒙古大学图书馆

Design and Realization of Unmanned Vehicle Autonomous Navigation System Based on Binocular Camera 3

Design and Realization of Unmanned Vehicle Autonomous Naviga...

3rd International Conference on computer Science, Electronic Information engineering and Intelligent control Technology, CEI 2023

作者： Guo, Tianxing Lin, Lianlei Liu, Huanyu Li, Junbao School of Electronics and Information Engineering Harbin Institute of Technology Department of Automatic Test and Control Harbin China Information Countermeasure Technique Institute School of Computer Science and Technology Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350372052

Aiming at the navigation problem of unmanned vehicles in extreme environments such as communication interference and limited GPS signals, this study proposes an autonomous navigation method based on binocular cameras. The method enables the unmanned vehicle to complete the task of localization and map building using only binocular images, without the need for other sensors or signal sources. Meanwhile, this study also proposes a local path planning obstacle avoidance method based on depth map, which, when combined with global localization information, can take into account both local obstacle avoidance and global path navigation, and can cope with random environmental changes. The system uses a single sensor for autonomous obstacle avoidance and navigation, which reduces the computational requirements and ensures the low cost of the navigation system. In order to verify the reliability and effectiveness of the system under signal-constrained conditions, the system is evaluated in a simulation environment and a real field scenario, respectively. The experimental results show that the system is able to achieve reliable localization and path planning under signal-constrained conditions. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

The Emergence of Artificial Intelligence in Education and its Impact on Individual Literacy in Higher Education 7

The Emergence of Artificial Intelligence in Education and it...

引用

7th IEEE International Conference and Workshop Obuda on Electrical and Power engineering, CANDO-EPE 2024

作者： Farkas, Imre Kovari, Attila Rajcsanyi-Molnar, Monika Institute of Computer Engineering University of Dunaujvaros Department of Computer Systems and Control Technology Dunaujvaros Hungary Eszterházy Károly Catholic University Institute of Digital Technology Faculty of Computer Science Eger Hungary Institute of Electronics and Communication Systems Kandó Kalmán Faculty of Electrical Engineering Obuda University Budapest Hungary John Von Neumann University GAMF Faculty of Engineering and Computer Science Kecskemét Hungary Institute of Social Sciences University of Dunaujvaros Department of Economics and Management Dunaujvaros Hungary

ISBN: (纸本)9798331531119

In the last three years, a new partner has emerged for teachers and educators in the field of education. The mushrooming of applications based on large language models has greatly shaped the educational development fields of the present era. The use of various AI applications has become commonplace among students and teachers alike. Many questions are being raised by researchers in this field. What does the rapid development of AI applications bring to the field of pedagogy? Should the products of such applications be compared with human performance? The form presented in this thesis seeks to answer similar questions. What is the impact of frequent use of these applications on the literacy level of individuals? In which areas do students tend to use these applications? The results indicate that half of the students believe their literacy levels will decrease with the mass emergence of AI applications, while 36% feel it will not change. However, 88 % of students have already dealt with AI-based applications, with 64 % using them several times or more, suggesting a high level of integration into their educational processes. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

The Impact of the Digital Transformation of Education on Literacy 7

The Impact of the Digital Transformation of Education on Lit...

引用

7th IEEE International Conference and Workshop Obuda on Electrical and Power engineering, CANDO-EPE 2024

作者： Farkas, Imre Kovari, Attila Rajcsanyi-Molnar, Monika Institute of Computer Engineering University of Dunaujvaros Department of Computer Systems and Control Technology Dunaujvaros Hungary Eszterházy Károly Catholic University Institute of Digital Technology Faculty of Computer Science Eger Hungary Obuda University Institute of Electronics and Communication Systems Kandó Kálmán Faculty of Electrical Engineering Budapest Hungary John Von Neumann University GAMF Faculty of Engineering and Computer Science Kecskemét Hungary Institute of Social Sciences University of Dunaujvaros Department of Economics and Management Dunaujvaros Hungary

ISBN: (纸本)9798331531119

During the COVID19 epidemic, people of all ages from all walks of life around the world have become inevitably familiar with and almost dependent on the digital tools of the age and the opportunities they offer. A change had to take place very quickly that was unprecedented. This process has also affected education. During the time of the reading lock-in, there was a proliferation of digital curricular content. The second time around, online education came to the fore, thanks to less or well-functioning online platforms, and has since become part of everyday teaching. What is the effectiveness and usefulness of sharing knowledge in this way? Is literacy still needed at all? Can online and hybrid (a controlled mix of face-to-face and online) education replace the well-established contact and face-to-face education? The study show that the respondents believe that online education has had an impact on literacy and that it is perceived to have a positive impact. The results indicate that online education has a positive impact on the literacy levels of students, as it facilitates knowledge acquisition and enhances digital literacy skills. © 2024 IEEE.

关键词： digital education digital literacy digital-informatics literacy

来源：评论

学校读者我要写书评

暂无评论

Research on the measurement device of UAV firearm unlocking force 4

Research on the measurement device of UAV firearm unlocking ...

引用

4th International Conference on Mechanical engineering, Intelligent Manufacturing, and Automation Technology, MEMAT 2023

作者： Yang, Mo Lin, Jing Li, Jiahao Cai, Zizhuo Ren, Haiyue Liu, Qiang School of Mechanical Engineering Nanjing University of Science and Technology 200 Xiaolingwei Street Nanjing210094 China Department of Automatic Control Systems Bauman Moscow State Technical University ul. Baumanskaya 2-ya 5/1 Moscow105005 Russia

ISBN: (纸本)9781510674820

In the current firearms dynamics research, the majority of studies focus on the extraction resistance and subsequent recoil forces, with relatively fewer studies on the unlocking force. This study focuses on the measurement of firearm unlocking force by analyzing the previously designed measurement device. By employing theoretical and dynamic simulation analyses, the variations of unlocking force over time were determined. A comparison of two sets of curves showed a high degree of coincidence, indicating the feasibility of the device in principle. Subsequently, to verify the accuracy of the measurements obtained by the device, a specific firearm was studied through simulation and experimental analysis, demonstrating the precision of the device's measurements. This structural device not only can be effectively used for measuring firearm unlocking force but also provides a new approach for experimental research on this force in firearms. © 2024 SPIE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Findings of the Study of the Time to Saturation of Current Transformer Magnetic Circuits Located at Electric Power Facilities

Analysis of the Findings of the Study of the Time to Saturat...

引用

International Ural Conference on Measurements (UralCon)

作者： Andrey Yablokov Anton Panashchatenko Department of Electric Power Systems Automatic Control Ivanovo State Power Engineering University “ISPU” Ivanovo Russian Federation

ISBN: (数字)9798350386028

ISBN: (纸本)9798350386035

Emergencies associated with incorrect operation of relay protection and automation (RPA) devices due to saturation of current transformers (CTs) can lead to great economic damage. The article presents an analysis of regulatory and technical documentation containing requirements for the quality of CT functioning in transient modes, statistical data on the results of calculations performed in accordance with the requirements of GOST R 58869–2019, as well as an analysis of the correctness of the assumptions introduced by it. To calculate the time to CTs saturation a special program was developed that automates the calculation methods, taking into account the assumptions focused on performing the manual calculations. The program takes into account the variation of the short circuit switching angle, the phase difference of the short circuit currents flowing through the branches feeding the short circuit point, the calculation of all CTs of a three-phase group with automatic selection of the worst result. The results obtained allow us to conclude about the relative number of CTs that do not meet the requirements of GOST R 58869–2019, the need to modernize existing methods and possible directions for such modernization. In addition, the article provides recommendations on the creation of automatic specialized software systems that can be used in the work of design, operating and research entities when they calculate the time to saturation of the CT magnetic circuits.

关键词： Current transformers Short-circuit currents Protective relaying Time measurement Power grids Circuit faults Transient analysis Protection Magnetic circuits Fault currents

来源：评论

学校读者我要写书评

暂无评论

Tuning the Feedback controller Gains is a Simple Way to Improve Autonomous Driving Performance

Tuning the Feedback Controller Gains is a Simple Way to Impr...

引用

UKACC International Conference on control (control)

作者： Wenyu Liang Pablo R. Baldivieso Ross Drummond Donghwan Shin Dept. of Automatic Control and Systems Engineering University of Sheffield Sheffield UK Dept. of Computer Science University of Sheffield Sheffield UK

ISBN: (数字)9798350374261

ISBN: (纸本)9798350374278

Typical autonomous driving systems are a combination of machine learning algorithms (often involving neural networks) and classical feedback controllers. Whilst significant progress has been made in recent years on the neural network side of these systems, only limited progress has been made on the feedback controller side. Often, the feedback control gains are simply passed from paper to paper with little re-tuning taking place, even though the changes to the neural networks can alter the vehicle's closed loop dynamics. The aim of this paper is to highlight the limitations of this approach; it is shown that re-tuning the feedback controller can be a simple way to improve autonomous driving performance. To demonstrate this, the PID gains of the longitudinal controller in the TCP autonomous vehicle algorithm are tuned. This causes the driving score in CARLA to increase from 73.21 to 77.38, with the results averaged over 16 driving scenarios. Moreover, it was observed that the performance benefits were most apparent during challenging driving scenarios, such as during rain or night time, as the tuned controller led to a more assertive driving style. These results demonstrate the value of developing both the neural network and feedback control policies of autonomous driving systems simultaneously, as this can be a simple and methodical way to improve autonomous driving system performance and robustness.

关键词： Machine learning algorithms Neural networks control systems Robustness Feedback control control theory Adaptive control

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap Between engineering and Cybersecurity to Better Protect Critical Infrastructures

引用

computer 2025年第7期58卷 157-160页

作者： Joseph Weiss James Bret Michael Applied Control Systems LLC Cupertino CA USA Department of Computer Science and Department of Electrical and Computer Engineering Naval Postgraduate School Monterey CA USA

This article addresses the need to bridge the gap between engineering and cybersecurity to better protect critical infrastructures such as electric power grids.

关键词： Critical infrastructure Power systems computer security

来源：评论

学校读者我要写书评

暂无评论

Lyapunov-Inspired Deep Reinforcement Learning for Robot Navigation in Obstacle Environments

SSRN

引用

SSRN 2024年

作者： Kayacan, Erdal Ugurlu, Halil Ibrahim Redder, Adrian Department of Electrical and Computer Engineering Aarhus University Aarhus C Denmark Department of Automatic Control Paderborn University Paderborn Germany

After its success in games and simulated control tasks, deep reinforcement learning (DRL) has gained prominence in robotics for developing neural network-based planning and control algorithms. However, the inherent black-box nature of neural network controllers poses challenges in ensuring safety, prompting the need for innovative, explainable solutions. This research paper introduces a DRL algorithm design inspired by Lyapunov stability theory to solve safe robot navigation problems in the presence of obstacles. The robot planning problem is formulated as a state-space control problem with obstacle locations integrated into the state representation. To ensure a high probability of obstacle avoidance and, hence, safety, we introduce a reward-shaping strategy utilizing a Lyapunov function tailored for obstacle avoidance. Additionally, an early episode termination is employed to constrain exploration and add more valuable samples to the DRL training replay memory. Simulation results demonstrate the effectiveness of the method in achieving superior exploration and learning with higher mission completion rates while maintaining speeds closer to a desired target speed. Real-world experiments conducted with a quadrotor in a laboratory environment validate the applicability of our method. The findings underscore the potential of incorporating Lyapunov stability theory into DRL approaches for advancing safe and efficient robot navigation. © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multilingual web traffic forecasting for network management using artificial intelligence techniques

Results in Engineering

引用

Results in engineering 2025年 26卷

作者： Samaan, Sama Salam Korial, Ayad E. Sarra, Raniya R. Humaidi, Amjad J. Computer Engineering Department University of Technology- Iraq Baghdad10001 Iraq Control and Systems Engineering Department University of Technology- Iraq Baghdad10001 Iraq

Web traffic forecasting is critical for ensuring an effective allocation of network resources for websites to avoid potential congestion and maintain service quality. Analyzing traffic forecasts helps network operators plan for future capacity needs to accommodate unexpected traffic loads. Multilingual web platforms present unique challenges due to varying traffic patterns across several languages. In this paper, modular architecture is proposed for multilingual web traffic forecasting using deep learning models. The architecture consists of multiple processes, from collecting the traffic data of the targeted website to preparing the data to be in a suitable form to feed the deep learning models. This study explores time-series forecasting methods using three deep learning models: long short-term memory (LSTM), gated recurrent units (GRU), and convolutional neural networks (CNN). A comprehensive dataset was collected from the BBC World Service websites in three languages—English, Arabic, and Persian—spanning the period from January 2017 to July 2024. The performance of the employed deep learning models is evaluated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), relative root mean square error (RRMSE), and R-squared (R²). Results show that the CNN model outperformed the GRU and LSTM models in accuracy and variance explanation across all three language datasets. The CNN model demonstrated superior performance, achieving R² scores of 0.980, 0.989, and 0.994;MAE values of 47,195, 5090, and 6714;RRMSE values of 1.43 %, 1.90 %, and 1.86 %;and RMSE values of 61,372, 6342, and 9376 for the English, Arabic, and Persian websites, respectively. These results highlight the potential of deep learning models in capturing complicated patterns of multilingual web platforms, making them suitable for real-world network management. © 2025

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Carbon-Aware Computing in a Network of Data Centers: A Hierarchical Game-Theoretic Approach

Carbon-Aware Computing in a Network of Data Centers: A Hiera...

引用

European control Conference (ECC)

作者： Enno Breukelman Sophie Hall Giuseppe Belgioioso Florian Dörfler Division of Decision and Control Systems KTH Royal Institute of Technology School of Electrical Engineering and Computer Science Stockholm Sweden Department of Electrical Engineering and Information Technology Automatic Control Laboratory ETH Zurich Zürich Switzerland

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

Over the past decade, the continuous surge in cloud computing demand has intensified data center workloads, leading to significant carbon emissions and driving the need for improving their efficiency and sustainability. This paper focuses on the optimal allocation problem of batch compute loads with temporal and spatial flexibility across a global network of data centers. We propose a bilevel game-theoretic solution approach that captures the inherent hierarchical relationship between supervisory control objectives, such as carbon reduction and peak shaving, and operational objectives, such as priority-aware scheduling. Numerical simulations with real carbon intensity data demonstrate that the proposed approach success-fully reduces carbon emissions while simultaneously ensuring operational reliability and priority-aware scheduling.

关键词： Data centers Processor scheduling Computational modeling Carbon dioxide Games Supervisory control Resource management

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：