检索结果-内蒙古大学图书馆

Distributed Identification for Node and Edge Numbers of Time-Varying Anonymous Networks

IEEE Transactions on Control of Network systems 2025年

作者： Liu, Xingjian Zhang, Hai-Tao Cao, Haosen Xing, Ning Xu, Bowen Zou, Jiayu Meng, Haofei Huazhong University of Science and Technology School of Artificial Intelligence and Automation The State Key Laboratory of Digital Manufacturing Equipment and Technology The Engineering Research Center of Autonomous Intelligent Unmanned Systems Wuhan430074 China Xi'an710072 China Southeast University School of Automation Nanjing210096 China

In this paper, a distributed algorithm is proposed to identify the node and edge numbers of anonymous leader-follower networks. The present distributed method works merely by exchanging scalar information by local intercommunication. The merit of the algorithm lies in identifying the required network parameters in time-varying topological networks without special initialization. Sufficient conditions are derived for cascading systems to theoretically guarantee the exponential convergence of the individual estimation to the total number of nodes or edges merely by local information exchanging. Finally, numerical simulations are conducted to substantiate the effectiveness of the present identification algorithm. © 2014 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Cooperative Hierarchical Coverage Control of Multi-Agent systems with Non-holonomic Constraints in Poriferous Environments

引用

IEEE Transactions on Control of Network systems 2025年

作者： Zou, Jiayu Zhang, Hai-Tao Zhai, Chao Xing, Ning Ma, Yong Liu, Xingjian Huazhong University of Science and Technology School of Artificial Intelligence and Automation The MOE Engineering Research Center of Autonomous Intelligent Unmanned Systems The State Key Laboratory of Digital Manufacturing Equipment and Technology Wuhan430074 China China University of Geosciences School of Automation China The MOE Engineering Research Center of Intelligent Technology for Geo-Exploration Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Academician Workstation of China COSCO Shipping Corporation Ltd. Shanghai200120 China Wuhan University of Technology Sanya Science and Education Innovation Park Sanya572000 China Wuhan University of Technology Chongqing Research Institute Chongqing401120 China

It has long posed a challenging task to optimally deploy multi-agent systems (MASs) to cooperatively coverage poriferous environments in real cooperative detection applications. In response to this challenge, this paper proposes a hierarchical coverage control (HCC) protocol for MASs to perform sector-based coverage operations. First, a distributed Voronoi partition-based sweep-and-assign protocol, combined with a sectorial partition method, is developed, enabling the segmentation of a whole poriferous region into multiple sectorial sub-subregions. Following this procedure, an extreme search scheme is developed to determine the optimal amount of agents for each subregion. After this allocation, a distributed controller is proposed to deploy the agents, considering non-holonomic constraints, into designated niche positions. Additionally, sufficient conditions are derived to guarantee the asymptotical stability of the present HCC. The analytical challenge of the present study stems from the non-convex characteristics inherent in the loss function induced by porous environments. This non-convexity renders the task of globally optimizing the assignment of MASs intractable. Finally, numerical simulations are conducted to validate the effectiveness of the present coverage control approach. © 2014 IEEE.

关键词： Nonlinear control systems

来源：评论

学校读者我要写书评

暂无评论

Relative Localization of Asynchronous Agents Based on Hybrid Active-Passive Two-Way Ranging

Relative Localization of Asynchronous Agents Based on Hybrid...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jianing Zhang Wei Wang Shiyu Dong Feng Pan Baoguo Yu Xin Li College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin China State Key Laboratory of Satellite Navigation System and Equipment Technology The 54th Research Institute of China Electronics Technology Group Corporation Shijiazhuang China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

To position agents equipped with ultrawideband (UWB) devices without requiring continuous clock synchronization, the primary measurement currently used is the time of flight between agents, estimated through active two-way ranging (TWR). However, the cumbersome signal exchange mechanism in active TWR imposes a trade-off between the number of agents and the positioning frequency. To address this issue, this paper proposes a relative localization scheme using hybrid active-passive TWR to accommodate more agents without compromising the positioning refresh rate. Additionally, this scheme not only extends passive TWR into a dynamic form, thereby improving localization accuracy of mobile agents, but also presents a two-step relative positioning method to enhance computational efficiency. The feasibility of the scheme is validated through numerical simulations and real-world tests on a prototype system built with consumer-level UWB chips.

关键词： Location awareness Time-frequency analysis Signal processing algorithms Numerical simulation Distance measurement Time measurement Computational efficiency Synchronization Ultra wideband technology Switching circuits

来源：评论

学校读者我要写书评

暂无评论

Strategies toward carbon neutrality: comparative analysis of China, USA, and Germany

Carbon Neutral Systems

引用

Carbon Neutral systems 2025年第1期1卷 1-26页

作者： Hou, Michael Z. Luo, Jiashun Huang, Liangchao Beck, Hans-Peter Mehmood, Faisal Wang, Qichen Wu, Xuning Wu, Lin Yue, Ye Fang, Yanli Chen, Qianjun Guo, Yilin Zhang, Tian Mao, Jinhua Cai, Nan Xiong, Ying Shi, Tianle Zhang, Ru Institute of Subsurface Energy Systems Clausthal University of Technology Clausthal-Zellerfeld Germany State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation Southwest Petroleum University Chengdu China Energy Research Centre of Lower Saxony Goslar Germany Department of Petroleum & Gas Engineering University of Engineering & Technology Lahore Pakistan State Key Laboratory of Intelligent Construction and Healthy Operation and Maintenance of Deep Underground Engineering Sichuan University Chengdu China

The growing threat of global warming makes it urgent to reduce carbon emissions and combat climate change. Achieving carbon neutrality is a key strategy to address these challenges and move towards a sustainable, low-carbon future. Comparing the carbon neutrality strategies of different countries and learning from each other's strengths and collaborating, nations can tackle shared challenges more effectively. This study provides a comparative analysis of carbon neutrality strategies adopted by China, the USA, and Germany, examining their respective legal frameworks, energy transitions, and technological innovations. While Germany has established strong legislative support and regulatory measures to promote renewable energy and reduce fossil fuel dependency, the USA's approach has been marked by policy fluctuations due to political shifts, impacting long-term climate strategies. In contrast, China's rapid progress in renewable energy, including wind power, photovoltaics, and electric vehicles, underscores its unique institutional efficiency and market-driven dynamics. The study explores how each nation’s path to carbon neutrality and global role, emphasizes the necessity of international cooperation. By leveraging their strengths, these countries can collectively shape the global climate agenda, setting the stage for transformative collaboration towards sustainable energy solutions and carbon reduction. • This study compares the carbon neutrality strategies of China, the USA, and Germany, highlighting their differences and similarities. • It identifies achievements and challenges in the carbon neutrality efforts of the three nations. • It provides insights and recommendations for global carbon neutrality efforts, stressing the need for international cooperation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vehicular Road Crack Detection with Deep Learning: A New Online Benchmark for Comprehensive Evaluation of Existing Algorithms

arXiv

引用

arXiv 2025年

作者： Ma, Nachuan Song, Zhengfei Hu, Qiang Liu, Chuang-Wei Han, Yu Zhang, Yanting Fan, Rui Xie, Lihua College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems the State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China School of Computer Science and Technology Donghua University Shanghai201620 China School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore

In the emerging field of urban digital twins (UDTs), advancing intelligent road inspection (IRI) vehicles with automatic road crack detection systems is essential for maintaining civil infrastructure. Over the past decade, deep learning-based road crack detection methods have been developed to detect cracks more efficiently, accurately, and objectively, with the goal of replacing manual visual inspection. Nonetheless, there is a lack of systematic reviews on state-of-the-art (SoTA) deep learning techniques, especially data-fusion and label-efficient algorithms for this task. This paper thoroughly reviews the SoTA deep learning-based algorithms, including (1) supervised, (2) unsupervised, (3) semi-supervised, and (4) weakly-supervised methods developed for road crack detection. Also, we create a dataset called UDTIRI-Crack, comprising 2, 500 high-quality images from seven public annotated sources, as the first extensive online benchmark in this field. Comprehensive experiments are conducted to compare the detection performance, computational efficiency, and generalizability of public SoTA deep learning-based algorithms for road crack detection. In addition, the feasibility of foundation models and large language models (LLMs) for road crack detection is explored. Afterwards, the existing challenges and future development trends of deep learning-based road crack detection algorithms are discussed. We believe this review can serve as practical guidance for developing intelligent road detection vehicles with the next-generation road condition assessment systems. The released benchmark UDTIRI-Crack is available at https://***/submission/. © 2025, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Behavioral Decision-Making of Mobile Robots Simulating the Functions of Cerebellum, Basal ganglia and Hippocampus

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Wang, Dongshu Liu, Qi Duan, Yihai School of Electrical and Information Engineering Zhengzhou University Henan Zhengzhou450001 China Innovation Center of Intelligent Systems Longmen Laboratory Henan Luoyang471000 China State Key Laboratory of Intelligent Agricultural Power Equipment Henan Luoyang471004 China China Information Technology Design and Consulting Institute Co. Ltd. Henan Zhengzhou450007 China

In unknown environments, behavioral decision-making of mobile robots is a crucial research topic in the field of robotics applications. To address the low learning ability and the difficulty of learning from the unknown environments for mobile robots, this work proposes a new learning model which integrates the supervised learning of the cerebellum, reinforcement learning of the basal ganglia, and memory consolidation of the hippocampus. Firstly, to reduce the impact of noise on inputs and enhance the network's efficiency, a multi-neuron winning strategy and the refinement of the top-k competition mechanism have been adopted. Secondly, to increase the network's learning speed, a negative learning mechanism has been designed, which allows the robot to avoid obstacles more quickly through weakening the synaptic connections between error neurons. Thirdly, to enhance the decision ability of cerebellar supervised learning, simulating the hippocampal memory consolidation mechanism, memory replay during the agent's offline state enables autonomous learning in the absence of real-time interactions. Finally, to better adjust the roles of cerebellar supervised learning and basal ganglia reinforcement learning in robot behavioral decision-making, a new similarity indicator has been designed. Simulation experiments and real-world experiments validate the effectiveness of the proposed model in this work. © 2020 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Study on static and dynamic characteristics of the electro-hydraulic proportional directional valve

引用

Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science 2025年

作者： Yang, Meisheng Kun, Lian Shuang, Luo Jiahan, Bao Huaizhi, Zong Anhui Province Engineering Laboratory of Intelligent Demolition Equipment Anhui University of Technology Maanshan China State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University Hangzhou China Anhui Key Laboratory of Mine Intelligent Equipment and Technology Anhui University of Science and Technology Huainan China Anhui Province Key Laboratory of Advanced Numerical Control & Servo Technology AnHui Polytechnic University Wuhu China Engineering Technology Research Center of Hydraulic Vibration Technology Anhui University of Technology Maanshan China

Electro-hydraulic proportional directional valves are widely used in precision engineering fields, where their operational stability and reliability are critical to the performance of hydraulic systems. However, high pressure and high-frequency responses significantly affect the hydraulic forces acting on the spool, while deformations caused by pressure and thermal loads may further compromise its performance. Therefore, analyzing and compensating for hydraulic forces, as well as investigating the deformation behavior of the spool under pressure and thermal loads, are essential for enhancing its stability and reliability. Based on CFD numerical calculation methods and fluid-thermal-solid multi-physics coupling technology, the study systematically investigates the characteristics of hydraulic forces and the deformation behavior of the spool. First, Fluent was used to simulate the fluid domain under steady-state and transient conditions, obtaining pressure and velocity contour maps, flow rate curves, and the hydraulic forces acting on the spool in different structural cavities formed by the valve sleeve and spool at different valve opening degrees. The analysis identified the best cavity configuration for compensating hydraulic forces between the valve sleeve and spool. Secondly, orthogonal experimental design and numerical simulation were conducted for the arc-shaped transition cavity, followed by multi-objective optimization using a genetic algorithm. The optimized structure reduced the steady-state hydraulic force to varying extents, with a maximum reduction of 23%. Finally, the fluid-thermal-solid multi-physics coupling technology was employed, selecting the optimal structure with the best hydraulic force compensation effect for analysis. The results show that the deformation of the spool in both radial directions increase as the valve opening increases. At a valve opening of 1 mm, the maximum radial deformation in the Z direction is 7.0471 μm. Additionally, with

关键词： Precision engineering

来源：评论

学校读者我要写书评

暂无评论

Perceptual Uncertainty-Aware Motion Planning for Autonomous Driving Based on Adaptive Heuristic Reinforcement Learning

引用

IEEE Transactions on intelligent Transportation systems 2025年

作者： Hu, Chuan Du, Baiyu Wang, Zhidong Zhang, Qichao Zhang, Ronghui Gao, Hongbo Shanghai Jiao Tong University School of Mechanical Engineering Shanghai200240 China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Sun Yat-sen University Guangdong Provincial Key Laboratory of Intelligent Transport System School of Intelligent Systems Engineering Guangzhou510275 China University of Science and Technology of China School of Information Science and Technology Department of Automation Hefei230026 China

Autonomous driving has become an inevitable trend in automotive development. Reinforcement Learning (RL) is extensively used in autonomous vehicle motion planning, demonstrating good generalization but facing challenges of long training times and lack of consideration of uncertainty. To address these challenges, an Adaptive Heuristic Reinforcement Learning (AHRL) approach is proposed. First, this study improves upon the Dueling Double Deep Q Network (D3QN) algorithm by proposing the Adaptive Heuristic Dueling Double Deep Q Network (Adapt-HD3QN) algorithm. Specifically, heuristic functions from search-based planning algorithms are incorporated into the RL reward terms to guide heuristic learning and enhance learning efficiency. Additionally, considering the uncertainties in real-world driving environments, such as the movement of other traffic participants and building occlusions, a Mixed Artificial Potential Field (Mix-APF) is implemented to address static and dynamic obstacle avoidance. Furthermore, potential collisions between the autonomous vehicle and other vehicles in occluded areas are modeled as a zero-sum game, with a Dynamic Bayesian Network (DBN) used for prior modeling of potential vehicles, aiding in constructing the potential vehicle’s forward hidden set. Finally, a signal-free intersection scenario, a typical crash-prone road type, is constructed on CARLA, incorporating static obstacles and other traffic participants. Experimental results demonstrate that the proposed Adapt-HD3QN algorithm exhibits superior safety, training efficiency, and traffic efficiency in scenarios with road environment perception uncertainties caused by occlusion. © 2000-2011 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Four-dimension efficient pixel-frequency transformer for light field spatial and angular super-resolution

引用

Engineering Applications of Artificial Intelligence 2025年 154卷

作者： Wang, Sizhe Sheng, Hao Cong, Ruixuan Yang, Da Chen, Rongshan Cui, Zhenglong State Key Laboratory of Electromechanical Integrated Manufacturing of High-Performance Electronic Equipments School of Mechano-Electronic Engineering Xidian University Shannxi Xi'an710071 China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Key Laboratory of Data Science and Intelligent Computing International Innovation Institute Beihang University Zhejinag Hangzhou311115 China Faculty of Applied Sciences Macao Polytechnic University 999078 China

Super-resolution plays an important role in optical engineering, which can offer high-quality image information for vision applications. The light field camera can capture the intensity and direction information of light, providing abundant scene information. However, it faces the trade-off problem of spatial and angular resolution. Benefiting from global context modeling by self-attention mechanism, transformer-based artificial intelligence methods for the light field (LF) super-resolution (SR) provide superior performance. However, in these methods, the four-dimensional (4D) LF is reshaped into a large one-dimensional (1D) sequence to be processed, which leads to a significant increase in computation and memory and raises difficulties of 4D structure reconstruction for LF spatial and angular SR. This paper presents a 4D efficient pixel-frequency transformer (4DEPFT) for spatial and angular SR, which models 4D correlation in the pixel and frequency domains based on the proposed inner-outer transformer with 4D position encoding. Specifically, two parallel branches separately handle LF images and their corresponding frequency maps in 4DEPFT. In the pixel branch, sub-patch-based inner-outer pixel transformers are proposed to extract 4D pixel features inside and outside local windows, which deal with pixels with small and large disparity shifts separately. In the frequency branch, a multi-band-based inner-outer frequency transformer is proposed to reconstruct 4D frequency features from different frequency bands. Finally, an attention-based pixel and frequency feature fusion module is presented to acquire the high-resolution LF. Experimental results on real-world and simulated public datasets indicate that 4DEPFT outperforms other methods with less computational cost and graphics processing unit (GPU) consumption. © 2025 Elsevier Ltd

关键词： Photonics

来源：评论

学校读者我要写书评

暂无评论

A multi-source physiological data-driven method for evaluating the mental workload of operators in remote control environment

引用

Safety Science 2025年 187卷

作者： Li, Zhihong Zhang, Di Lyu, Wenchen Nazir, Salman Mao, Zhe Wan, Chengpeng State Key Laboratory of Maritime Technology and Safety Wuhan University of Technology China Intelligent Transportation Systems Research Center Wuhan University of Technology China School of Transportation and Logistics Engineering Wuhan University of Technology China Training and Assessment Research Group Department of Maritime Operations Faculty of Technology Natural Sciences & Maritime Sciences University of South-Eastern Norway

With the continuous development of Maritime Autonomous Surface Ships (MASS), remote control ship will become into reality in the near future. However, the mental behaviours of remote-control seafarers and their effects on navigation safety remain unclear, particularly in the context of emerging "multi-human multi-ship" operational patterns. In view of this, experimental research for the assessment of mental workload in remote control environment was conducted, addressing the critical gap in understanding the cognitive demands of remote maritime operations. A novel experimental setup is developed to closely simulate inland waterway navigation of varying degrees of difficulty, incorporating realistic challenges such as ferry crossings and buoy avoidance. The design uniquely considers the transition from traditional seafaring to remote operations, providing insights into the behavioural differences between remote operators and onboard crew members. A fusion of heart rate variability and skin conductance were employed to achieve a highly precise classification of mental workload levels through a low-invasive method, which is suitable for continuous monitoring in operational settings. Three machine learning models are employed for classifying the physiological signals into distinct workload levels, with the K-Nearest Neighbours (KNN) achieving an accuracy of 93.1%. The statistical analysis validates the effectiveness of this assessment approach across different workload conditions. The integration of physiological data and machine learning models enables real-time detection of cognitive overload and stress in working condition. These findings provide foundational reference for designing personnel suitability monitoring systems and task allocation strategies in future remote control centres, contributing to maritime safety and operational effectiveness. © 2025

关键词： Data fusion

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：