检索结果-内蒙古大学图书馆

21st International Symposium on Applied Reconfigurable Computing, ARC 2025

作者： Danilowicz, Michal Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031879944

Multi-object tracking (MOT) is one of the most important problems in computer vision and a key component of any vision-based perception system used in advanced autonomous mobile robotics. Therefore, its implementation on low-power and real-time embedded platforms is highly desirable. Modern MOT algorithms should be able to track objects of a given class (e.g. people or vehicles). In addition, the number of objects to be tracked is not known in advance, and they may appear and disappear at any time, as well as be obscured. For these reasons, the most popular and successful approaches have recently been based on the tracking paradigm. Therefore, the presence of a high quality object detector is essential, which in practice accounts for the vast majority of the computational and memory complexity of the whole MOT system. In this paper, we propose an FPGA (Field-Programmable Gate Array) implementation of an embedded MOT system based on a quantized YOLOv8 detector and the SORT (Simple Online Realtime Tracker) tracker. We use a modified version of the FINN framework to utilize external memory for model parameters and to support operations necessary required by YOLOv8. We discuss the evaluation of detection and tracking performance using the COCO and MOT15 datasets, where we achieve 0.21 mAP and 38.9 MOTA respectively. As the computational platform, we use an MPSoC system (Zynq UltraScale+ device from AMD/Xilinx) where the detector is deployed in reprogrammable logic and the tracking algorithm is implemented in the processor system. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Adaptive Online Optimization control Method Based on Reinforcement Learning

Adaptive Online Optimization Control Method Based on Reinfor...

引用

2023 China Automation Congress, CAC 2023

作者： Wang, Zhaolei Yu, Chunmei Lu, Kunfeng Hu, Ruiguang Huang, Xu Wang, Ludi National Key Laboratory of Science and Technology on Aerospace Intelligence Control Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (纸本)9798350303759

Large envelope deformable aircraft pose higher requirements for guidance and control technology, requiring control law parameters to be able to adaptively optimize online based on flight uncertainty and dynamically enhance flight control capabilities. At present, coefficient freezing is commonly used in engineering to design typical feature work points, but in large envelope flight, there are more and more feature work points, and traditional design methods are more complex and highly dependent on manual experience;On the other hand, traditional gain scheduling methods can only switch preset control laws based on flight status. Once the control laws are deployed, their performance is solidified, and their adaptive ability is relatively limited, making it impossible to perform online optimization. This article adopts deep reinforcement learning to design a universal PI state feedback control law parameter self-learning architecture, achieving autonomous learning of control law parameters at different working points;At the same time, the trained parameter adjustment network is deployed together with the control law, and online learning optimization of control law parameters is achieved during flight based on the control effect, enhancing adaptive ability. Finally, the effectiveness of the proposed method was verified using a specific pitch angle tracking control scenario as an example. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on Cooperative Path Planning and Formation control for Multiple UAVs 1

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Shichao, Ma Xianglun, Zhang Qiang, Tang Zhiyu, Li Yukun, Yang AVIC Xi’an Flight Automatic Control Research Institute Xi’an710076 China National Key Laboratory of Science and Technology on Aircraft Control Xi’an710076 China

ISBN: (数字)9789819733361

ISBN: (纸本)9789819733354

Considering the background of Multi-UAVs formation cooperation, a Cooperative Multi-Swarm Particle Swarm Optimization (CMS-PSO) scheme as well as a prescribed performance control (PPC) method is introduced. Firstly, the cost function is developed and a novel CMS-PSO approach is applied to deal with three dimensional (3D) path planning problem. Then, the nonlinear mathematical formation model is given. So as to confine the location differences of the formation system, a PPC algorithm integrated with the backstepping methodology is constructed in details. In the end, the results of mathematical simulations show the validity of the introduced path algorithm and control method. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Research on Longitudinal control Law Design of Thrust Vector Aircraft Based on Dynamic Inverse

Research on Longitudinal Control Law Design of Thrust Vector...

引用

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Liu, Hengyu Zhang, Ning Chen, XiaoLong Ma, YueLong National Key Laboratory of Science and Technology on Integrated Technology Control Flight Automatic Control Research Institute AVIC Xi’an100083 China

ISBN: (纸本)9789811966125

In order to improve the maneuvering control ability at high angle of attack, this paper designs the commonly used thrust vector aircraft model. Based on the model, the longitudinal control law design of aircraft is studied by combining the dynamic inversion method with the incremental dynamic inversion method. This paper uses the dynamic inversion and incremental dynamic inversion method in the inner loop and outer loop of the model design of the new control system. Compared with the traditional dynamic inverse control method, the longitudinal control method proposed in this paper has better control performance and is more stable. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Longitudinal control

来源：评论

学校读者我要写书评

暂无评论

Influence of Primary and Secondary Path Estimation Accuracy on Active Noise control Performance

Influence of Primary and Secondary Path Estimation Accuracy ...

引用

2025 systems of Signals Generating and Processing in the Field of on Board Communications, SOSG 2025

作者： Djigan, Victor I. Institute of Microdevices and Control Systems National Research University of Electronic Technology Moscow Russia

ISBN: (纸本)9798331532635

An Active Noise control (ANC) system based on a modified architecture is considered. This architecture allows to accelerate the convergence of the adaptive filtering algorithms in use. Besides, it allows to use the most efficient Recursive Least Squares adaptive filtering algorithms which provide the fastest convergence comparing to the gradient search-based adaptive algorithms. The architecture of the ANC system and its mathematic description are presented. The simulation results demonstrate the ANC system performance. It is shown, that the number of the adaptive filter weighs can be decreased about 30% of the theoretically required value without any observable loss of the ANC performance. This is possible because of fading shape of the primary and secondary path acoustic impulse responses. As the result, the contribution of the impulse response 'tails' to the signals at the error microphone of the ANC system is comparable with that of the ambient noise. This also allows to decrease the required number of the adaptive filter weights and to decrease the computational resources required to the implementation of the ANC system. © 2025 IEEE.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Photovoltaic,thermoelectric and electromagnetic generation technologies applied in power systems for mobile unmanned systems

引用

Science China(Technological Sciences) 2023年第3期66卷 599-629页

作者： DING Ning WANG XiangYang XIAN XiaoYang CAI YeYun LIU DaoMing DENG Fang Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of TechnologyBeijing 100081China Beijing Institute of Technology Chongqing Innovation Center Chongqing 401120China

Unmanned systems are increasingly adopted in various fields,becoming an indispensable technology in daily *** systems are the lifeblood of unmanned systems,and affect the working time and task ***,traditional power systems,such as batteries and fuels have a fixed ***,once the power supply is exhausted and cannot be replenished in time,the unmanned systems will stop ***,researchers have increasingly begun paying attention to renewable energy generation *** principles,advantages,and limitations of renewable energy generation technologies are different,and their application effects in different unmanned systems are also *** paper presents a comprehensive study of the application and development status of photovoltaic,thermoelectric,and magnetoelectric generation technologies in four kinds of unmanned systems,including space,aviation,ground,and water,and then summarizes the adaptability and limitations of the three technologies to different ***,future development directions are predicted to enhance the reliability of renewable energy generation technologies in unmanned *** is the first study to conduct a comprehensive and detailed study of renewable energy generation technologies applied in unmanned *** present work is critical for the development of renewable energy generation technologies and power systems for unmanned systems.

关键词： unmanned system renewable energy generation technology photovoltaic generation thermoelectric generation electromagnetic generation

来源：评论

学校读者我要写书评

暂无评论

PCB-Net: An Effective Deep Learning-Based Approach to PCBA Detection 50

PCB-Net: An Effective Deep Learning-Based Approach to PCBA D...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Li, Tingxin Liu, Weihua Liu, Xinpeng Yang, Xianqiang Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin China Research Center of Intelligent Control and Systems Zhejiang University Yongjiang Laboratory Hangzhou China School of Control Science and Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9781665464543

Modern surface mount circuit board assemblies require more advanced defect detection methods. While deep learning algorithms have great potential for PCBA inspection, their detection accuracy in complex background situations is still limited. To overcome this problem, we propose a deep learning-based PCBA detection model (PCB-Net) to achieve accurate classification and localization of components on PCB. Firstly, for similar objects under complex background interference, this paper proposes a backbone network consisting of a generalized efficient aggregation network and a context converter to effectively extract local and global information. This integration aims to enhance the expressiveness of the network. Secondly, a multi-scale attention mechanism is designed to improve the feature extraction ability of the network on the target and suppress the interference of complex backgrounds. Finally, a C2fHB lightweight module was designed to improve the model's extraction of component features using the HorNet structure. Experimental results show that our proposed model is an effective PCBA detection method, as it can accurately detect tiny components in complex backgrounds, efficiently obtain component class and location information, and remain detection efficiency. © 2024 IEEE.

关键词： Surface mount technology

来源：评论

学校读者我要写书评

暂无评论

A type-independent unknown parameters estimation method for lead component 50

A type-independent unknown parameters estimation method for ...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Yang, Hong Liu, Xinpeng Liu, Weihua Yang, Xianqiang Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin China School of Control Science and Engineering Dalian University of Technology Dalian China Research Center of Intelligent Control and Systems Yongjiang Laboratory Zhejiang University Ningbo China

ISBN: (纸本)9781665464543

To meet the growing demands in the electronics manufacturing industry for smaller, more reliable, and flexible component packages, this research introduces a novel algorithm designed to automatically measure the geometric parameters of lead components. The algorithm can address the challenges associated with measuring these parameters in surface mount technology (SMT), overcoming the inefficiencies and inaccuracies of traditional manual measurement methods. This innovative approach combines an adaptive threshold segmentation algorithm with a multilevel grayscale range, enabling robust binary segmentation that adapts to variations in illumination. Additionally, by employing conditional filtering and state tracking, the algorithm facilitates the extraction of lead groups and individual leads, allowing for precise evaluation of component parameters through sub-pixel interpolated fitting. Extensive testing under various illumination conditions across multiple types of packaged and standard components has confirmed the algorithm's high accuracy and robustness. These results highlight its efficacy as a measurement solution suitable for industrial-grade applications. © 2024 IEEE.

关键词： Surface mount technology

来源：评论

学校读者我要写书评

暂无评论

Trust-Based Identity Privacy for Edge Computing 24

Trust-Based Identity Privacy for Edge Computing

引用

14th International Conference on Communication and Network Security, ICCNS 2024

作者： Dong, Jie Wen Kang, Xi Nai Peng, Jin Jiang, Xuan Ming Zhu, Tao Jun Information Technology Department National Key Laboratory of Seience and Technology on Aerospace Intelligence Control Beijing Aerospace Automatic Control Institute BeiJing China School of Computer Science Beijing University of Technology BeiJing China

ISBN: (纸本)9798400717994

College of Computer Science Beijing University of technology, Beijing 100124, China, 1374622525@*** This paper proposes a trust collaboration technology for edge computing, addressing trust isolation and security issues through a unified trust value calculation method and blockchain technology. The designed trust management model evaluates the identity, capability, and behavior of terminal nodes using static and dynamic trust measurements. A consortium blockchain stores trust information to ensure immutability and efficient sharing. Simulation experiments validate the scheme's effectiveness in countering malicious node attacks, improving task completion rates, and reducing system risks. This solution offers an efficient and secure approach to trust management in edge computing environments. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Trust Collaboration for Edge Computing 24

Trust Collaboration for Edge Computing

引用

14th International Conference on Communication and Network Security, ICCNS 2024

ISBN: (纸本)9798400717994

As edge computing becomes an increasingly important computing model, trust management and security issues are becoming more severe. Problems such as malicious node attacks and trust isolation pose threats to the security and stability of edge computing environments. Therefore, designing an efficient and secure trust management mechanism is imperative. This paper proposes a trust collaboration technology for edge computing, addressing trust isolation and security issues through a unified trust value calculation method and blockchain technology. The designed trust management model evaluates the identity, capability, and behavior of terminal nodes using static and dynamic trust measurements. A consortium blockchain stores trust information to ensure immutability and efficient sharing. Simulation experiments validate the scheme's effectiveness in countering malicious node attacks, improving task completion rates, and reducing system risks. This solution offers an efficient and secure approach to trust management in edge computing environments. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Mobile edge computing

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：