检索结果-内蒙古大学图书馆

PID-fuzzy switching-based strategy to heading control for remote operated vehicle

Neural computing and Applications 2024年 1-17页

作者： Xie, Baolong He, Shuping Cao, Xiang Wang, Honghai Stojanovic, Vladimir Shi, Kaibo School of Electrical Engineering and Automation Anhui University Hefei230039 China School of Artificial Intelligence Anhui University Hefei230039 China School of Computing and Artificial Intelligence Chaohu University Chaohu238024 China Department of Automatic Control Robotics and Fluid Technique Faculty of Mechanical and Civil Engineering University of Kragujevac Kraljevo36000 Serbia School of Electronic Information and Electrical Engineering Chengdu University Chengdu610106 China

Accurate heading control is the premise for underwater vehicles to complete underwater operations. In order to improve the performance of heading control, this paper proposes a heading control strategy based on PID-fuzzy switching. First, the force analysis of the steering motion was carried out to derive the dynamics model of the steering motion. Then, the whole heading control process is divided into two phases, steering phase and holding phase. Fuzzy control is used in the steering phase, and PID control is used in the holding phase. By setting the automatic switching switch, the control system can switch freely between the two to meet the needs of system adjustment under different errors. Finally, the performance of the established heading control system is verified through motion control simulations and pool experiments, and the proposed control strategy is compared with other methods. The results show that the control strategy can effectively achieve ROV heading control with good steady-state accuracy, and the overall performance has been greatly improved. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Weakly supervised target detection based on spatial attention

引用

Visual Intelligence 2024年第1期2卷 1-11页

作者： Zhao, Wenqing Xu, Lijiao School of Control and Computer Engineering North China Electric Power University Hebei Baoding 071000 China Department of Hebei Key Laboratory of Knowledge Computing for Energy & Power North China Electric Power University Hebei Baoding 071000 China

Due to the lack of annotations in target bounding boxes, most methods for weakly supervised target detection transform the problem of object detection into a classification problem of candidate regions, making it easy for weakly supervised target detectors to locate significant and highly discriminative local areas of objects. We propose a weak monitoring method that combines attention and erasure mechanisms. The supervised target detection method uses attention maps to search for areas with higher discrimination within candidate regions, and then uses an erasure mechanism to erase the region, forcing the model to enhance its learning of features in areas with weaker discrimination. To improve the positioning ability of the detector, we cascade the weakly supervised target detection network and the fully supervised target detection network, and jointly train the weakly supervised target detection network and the fully supervised target detection network through multi-task learning. Based on the validation trials, the category mean average precision (mAP) and the correct localization (CorLoc) on the two datasets, i.e., VOC2007 and VOC2012, are 55.2% and 53.8%, respectively. In regard to the mAP and CorLoc, this approach significantly outperforms previous approaches, which creates opportunities for additional investigations into weakly supervised target identification algorithms. © The Author(s) 2024.

关键词： Erasure concept Multi instance learning Object detection Spatial attention Weakly supervised learning

来源：评论

学校读者我要写书评

暂无评论

User Input Search - Custom Motion Estimation Algorithm Optimized for UAVs

User Input Search - Custom Motion Estimation Algorithm Optim...

引用

Proceedings of the International Convention MIPRO

作者： J. Benjak D. Hofman Department of Control and Computer Engineering Faculty of Electrical Engineering and Computing Zagreb Croatia

Unmanned aerial vehicle technology is growing rapidly as it finds its application in the various industries, including military & defense, agriculture, logistics, transportation, healthcare, entertainment and many others. One of the fastest growing industries including drones is the entertainment industry. More specifically, First Person View (FPV) piloting has become a popular sport which attracts huge masses. In FPV systems, the pilot wears FPV goggles and controls the drone using a controller, and the drone transmits video data to the goggles in real time. Since drones usually fly very quickly, the video quality in terms of resolution, compression artefacts and end-to-end delay must be maintained. This paper explores the idea of optimizing the Motion Estimation (ME) algorithm of existing High Efficiency Video Coding (HEVC) algorithms by utilizing user input from the controller. For example, if the drone is directed to hover to the left, then it would make sense to search for the most similar blocks in the previous video frame only on the left side of the referent block. For the purpose of this research, a HEVC video coder was customized to receive additional input besides the video data – the user input from the controller, or in other words, drone movement directions. We call this ME algorithm User Input Search (UIS). Our UIS algorithm is compared with the standard ME algorithms and its efficiency is tested.

关键词：

来源：评论

学校读者我要写书评

暂无评论

One solution of a Distributed System intended for communication between ADAS and IVI Systems

One solution of a Distributed System intended for communicat...

引用

2023 IEEE Zooming Innovation in Consumer Technologies Conference, ZINC 2023

作者： Cabrilo, Vuk Kenjic, Dusan Zlatkovic, Radomir Antic, Marija University of Novi Sad Faculty of Technical Sciences Department of Computing and Control Engineering Novi Sad Serbia RT-RK Institute of Computer Based Systems Novi Sad Serbia

ISBN: (纸本)9798350347722

Current trends of digitalization and automation in the automotive industry have increased the complexity of computer clusters in different domains of vehicular ecosystems, which are required to support new features. This has led to redundancy in resource usage in specific use cases, resulting in increased production costs and manufacturer suggested retail price (MSRP) markups for the finalized products. The average retail price of a new vehicle in the United States increased by 13.4% between 2015 and 2020. Considering the global chip shortage of 2020 and current global inflation, the average price of a new vehicle in the United States reached 49,500 in 2023 [1]. With the electrification of current automotive platforms underway, as well as the move to centralized system architectures, new approaches to inter-domain communication are expected. This paper proposes a solution of a distributed AUTOSAR Adaptive system that can establish communication with the In-Vehicle Infotainment (IVI) domain. The proof of concept implemented in a controlled environment proves viable for inter-domain communication, as it provides good scalability and adaptability to different scenarios. The use of a distributed approach facilitates the applicability of distributed system principles, allowing for the implementation of a stable system. © 2023 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Improving finite-difference time-domain memory bandwidth by using block floating-point arithmetic 31

Improving finite-difference time-domain memory bandwidth by ...

引用

31st Telecommunications Forum, TELFOR 2023

作者： Pijetlovic, Stefan Kastelan, Ivan Subotic, Milos Pjevalica, Nebojsa RT-RK Institute for Computer Based Systems Novi Sad Serbia University of Novi Sad Faculty of Technical Sciences Department of Computing and Control Engineering Novi Sad Serbia

ISBN: (纸本)9798350303131

Finite-difference time-domain is a numerical method used for modelling of computational electrodynamics. The method is resource intensive, especially regarding memory usage since multiple memory accesses are required per single computation. In other words, memory, or more precisely its speed, is a limiting factor for the overall performance. Existing solutions focus either on structures with great parallelism such as graphical processing units or custom designs. The former have issues with underutilized resources, while the latter require significant time and effort to achieve similar or slightly better performances. The approach taken during this research was to target the memory itself and find a way to improve the efficiency of memory usage across multiple platforms. The main contribution of the paper is using block floating-point in a novel way regarding the finite-difference time-domain method. The presented solution is a verification of earlier research, proving that the performance of this algorithm can indeed be improved using the suggested methods. © 2023 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Modification of the PSO Algorithm: Variable Population Size and Hybridization with the Nelder-Mead Method 24

Modification of the PSO Algorithm: Variable Population Size ...

引用

24th International Symposium INFOTEH-JAHORINA, INFOTEH 2025

作者： Topalov, Stefan Radović, Mirna University of Novi Sad Faculty of Technical Sciences Department of Computing and Control Engineering Novi Sad Serbia

ISBN: (纸本)9798331515799

This paper presents a modified Particle Swarm Optimization (PSO) algorithm designed to enhance computational efficiency without compromising solution quality. Two approaches are proposed: the first emphasizes the advantages of incorporating a variable population size to optimize both computational efficiency and solution quality. The second integrates this adaptive population strategy with the Nelder-Mead method to refine local search capabilities. By combining these techniques, the hybrid algorithm achieves a balance between global exploration and local exploitation, while also improving the algorithm's speed without sacrificing solution quality. The performance of both approaches is evaluated through numerical experiments, demonstrating their ability to deliver high-quality solutions with reduced computational resources. © 2025 IEEE.

关键词： Local search (optimization)

来源：评论

学校读者我要写书评

暂无评论

Design of adaptive controllers by means of PPO algorithm using MATLAB

Design of adaptive controllers by means of PPO algorithm usi...

引用

International Symposium on INFOTEH-JAHORINA (INFOTEH)

作者： Veljko Radojičić Milan R. Rapaić Department of Computing and Control Engineering Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia

ISBN: (数字)9798331515799

ISBN: (纸本)9798331515805

This paper investigates reinforcement learning (RL) as a practical framework for achieving optimal adaptive control across several simple dynamical system models. All experiments were conducted using the Proximal Policy Optimization (PPO) algorithm, implemented within the MATLAB Reinforcement Learning Toolbox. The primary focus of this study is to explore how the learning process can be empirically designed to sufficiently excite the system dynamics and obtain a sufficiently robust controller.

关键词： Adaptation models System dynamics Heuristic algorithms Process control Reinforcement learning MATLAB Dynamical systems Adaptive control Optimization

来源：评论

学校读者我要写书评

暂无评论

Optimal control of Systems with Fractional Dynamics and Algebraic Constraints

Optimal Control of Systems with Fractional Dynamics and Alge...

引用

International Symposium on INFOTEH-JAHORINA (INFOTEH)

作者： Nikolina Živanović Zoran D. Jeličić Department of Computing and Control Engineering Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia

ISBN: (数字)9798331515799

ISBN: (纸本)9798331515805

This study investigates optimal control problems described by fractional differential equations, with the control vector components subject to algebraic constraints. Two case studies are analyzed: an illustrative example designed to test the algorithm’s effectiveness and a biologically significant model of acute myeloid leukemia (AML), which applies optimal control theory to design therapeutic strategies under medical constraints. The methodology transforms fractional differential equations into equivalent ordinary differential equations using the framework of Atanacković and Stanković. L.S. Pontryagin’s maximum principle is then applied to derive control functions that satisfy the algebraic constraints, followed by numerical optimization of the Hamiltonian function. We formally parsed the problem of dynamic optimization into a static optimization problem using the Forward-Backward Sweep Method (FBSM). The approach is validated through comprehensive numerical simulations, demonstrating its robustness and applicability to real-world problems.

关键词： Systematics Refining Optimal control Leukemia Transforms Mathematical models Robustness Vectors Reproducibility of results Optimization

来源：评论

学校读者我要写书评

暂无评论

Modification of the PSO Algorithm: Variable Population Size and Hybridization with the Nelder-Mead Method

Modification of the PSO Algorithm: Variable Population Size ...

引用

International Symposium on INFOTEH-JAHORINA (INFOTEH)

作者： Stefan Topalov Mirna Radović Department of Computing and Control Engineering Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia

ISBN: (数字)9798331515799

ISBN: (纸本)9798331515805

This paper presents a modified Particle Swarm Optimization (PSO) algorithm designed to enhance computational efficiency without compromising solution quality. Two approaches are proposed: the first emphasizes the advantages of incorporating a variable population size to optimize both computational efficiency and solution quality. The second integrates this adaptive population strategy with the Nelder-Mead method to refine local search capabilities. By combining these techniques, the hybrid algorithm achieves a balance between global exploration and local exploitation, while also improving the algorithm’s speed without sacrificing solution quality. The performance of both approaches is evaluated through numerical experiments, demonstrating their ability to deliver high-quality solutions with reduced computational resources.

关键词： Heuristic algorithms Stochastic processes Switches Linear programming Robustness Computational efficiency Optimization Standards Tuning Convergence

来源：评论

学校读者我要写书评

暂无评论

Evaluating Extended Kalman Filter and Unscented Kalman Filter for accurate trajectory estimation

Evaluating Extended Kalman Filter and Unscented Kalman Filte...

引用

International Symposium on INFOTEH-JAHORINA (INFOTEH)

作者： Anastasija Golić Mirna Radović Department of Computing and Control Engineering Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia

ISBN: (数字)9798331515799

ISBN: (纸本)9798331515805

This paper evaluates two common methods for trajectory estimation: the Extended Kalman Filter (EKF), the Unscented Kalman Filter (UKF). The EKF and UKF are well-established recursive filtering techniques commonly used for nonlinear state *** performance of these methods is compared through their implementation on a standard trajectory estimation problem, with a focus on assessing their accuracy.

关键词： Accuracy Linear approximation Trajectory Computational efficiency Kalman filters Reliability Nonlinear systems State estimation Tuning Standards

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：