检索结果-内蒙古大学图书馆

Robust Training in Multiagent Deep Reinforcement Learning Against Optimal Adversary

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年

作者： Guo, Weiran Liu, Guanjun Zhou, Ziyuan Wang, Jiacun Tang, Ying Wang, Miaomiao Tongji University School of Computer Science and Technology Shanghai201804 China Monmouth University Department of Computer Science and Software Engineering West Long BranchNJ07764 United States Rowan University Department of Electrical and Computer Engineering GlassboroNJ08028 United States Beijing Institute of Control Engineering Space Optoelectronic Measurement and Perception Lab Beijing100190 China

Industry 5.0 enhances manufacturing ability through efficient human-machine interaction, combining human resources and robots to complete tasks more accurately and effectively. Artificial intelligence (AI) plays an essential role in Industry 5.0. As a branch in AI, multiagent deep reinforcement learning (MADRL) attracts vast attention in both academia and industry. However, there is a gap between virtual and physical environments in terms of how clean an observed state is. In addition, state adversarial attacks can seriously impact the performance of MADRL. Hence, how to improve the robustness of MADRL algorithms is an important research topic. In this article, we propose an optimal policy-based state adversary attack method that would make the MADRL algorithm more robust when it is applied in the training process of agents. Two case studies related to Industry 5.0 and a general case study are presented in which robustness training against the optimal adversarial attack is tested. The MADRL algorithms involved in the experiments include centralized training and decentralized execution (CTDE) framework and shared experience actor-critic (SEAC) to demonstrate the universality of our method. © 2013 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Mixture-of-Experts as Continual Knowledge Adapter for Mobile Vision Understanding

引用

IEEE Transactions on Mobile Computing 2025年

作者： Guo, Bicheng Zhou, Conghao He, Shibo Chen, Jiming Shen, Xuemin Zhejiang University College of Control Science and Engineering Zhejiang Hangzhou310027 China Xidian University School of Telecommunications Engineering China University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Continual machine learning in the context of limited computational resources and data availability is critical in the connected digital world. Current intelligent applications predominantly rely on deep learning models requiring labor/computation-intensive training. These models often struggle to adapt effectively to new data while preserving performance on previously learned knowledge. In this paper, we introduce a lightweight method for continual knowledge adaptation that can address these challenges. To prevent disruption of the existing services, we propose a Mixture-of-Experts (MoE) adapter that integrates seamlessly with the existing vision model to encode new data. The weights of the original model are kept fixed during the adaptation process, ensuring the preservation of previously learned knowledge. The MoE technique enables scaling up the parameters of the adapter while maintaining a relatively low computation, making it fit for constrained devices in mobile computation scenarios. Furthermore, to enhance learning efficiency and accelerate convergence with new data, we implement a knowledge fusion mechanism that facilitates interaction between the existing knowledge and the information extracted from new data. The timing of employing the fusion module is further investigated. We find that it is conducive in scenarios where the task's performance requirements are enhanced. The MoE adapter and knowledge fusion module are integrated at each stage with minimal trainable parameters, efficiently optimizing resource usage. Extensive experiments and ablation studies validate the effectiveness of the proposed method. Specifically, the proposed method prevents an accuracy drop of 43.02% on the previous data compared to the continual train method, while achieving an accuracy of 44.81% on the new data, which is even 0.34% higher than fully training a new model. © 2002-2012 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Data Heterogeneity Challenge in Consumer Electronics: A Federated Learning Solution

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Liu, Zhenyu Wu, Yunting Ge, Huanhuan Wang, Jinlong Lyu, Zhihan Qingdao University of Technology School of Information and Control Engineering Shandong Qingdao China School of Information and Control Engineering Innovation Institute for Sustainable Maritime Architecture Research and Technology Shandong Qingdao China School of Computer Science and Technology Xidian University Xi’an 710126 China

Federated learning(FL) enables collaborative model training across consumer electronic devices while preserving data privacy. However, the non-independent and identically distributed nature of data in real-world scenarios significantly impacts personalization performance. To address this challenge, we propose pFedPKD, in this framework, we first employ model pruning to simplify the global model, thereby enhancing its adaptability and improving the efficiency of knowledge transfer between different electronics devices. Moreover, we introduce an attention-based knowledge transfer mechanism, which leverages knowledge distillation to transfer the attention map and predictions of the pruned global model to the local models, thus improving their generalization capability and performance. Extensive experiments on three datasets demonstrate that pFedPKD consistently outperforms state-of-the-art methods, achieving higher personalization accuracy and robustness under heterogeneous data distributions. This work provides an efficient solution for applying FL in consumer electronics, offering improved adaptability and resource efficiency. © 1975-2011 IEEE.

关键词： consumer electronics Federated learning knowledge distillation Non-IID

来源：评论

学校读者我要写书评

暂无评论

Efficient Coordination and Synchronization of Multi-Robot Systems Under Recurring Linear Temporal Logic

arXiv

引用

arXiv 2025年

作者： Peron, Davide Fernandez-Ayala, Victor Nan Vlahakis, Eleftherios E. Dimarogonas, Dimos V. Department of Information Engineering University of Padova Padova35122 Italy Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden

We consider multi-robot systems under recurring tasks formalized as linear temporal logic (LTL) specifications. To solve the planning problem efficiently, we propose a bottom-up approach combining offline plan synthesis with online coordination, dynamically adjusting plans via real-time communication. To address action delays, we introduce a synchronization mechanism ensuring coordinated task execution, leading to a multi-agent coordination and synchronization framework that is adaptable to a wide range of multi-robot applications. The software package is developed in Python and ROS2 for broad deployment. We validate our findings through lab experiments involving nine robots showing enhanced adaptability compared to previous methods. Additionally, we conduct simulations with up to ninety agents to demonstrate the reduced computational complexity and the scalability features of our work. © 2025, CC BY.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Intelligent Construction and Analysis of a Complex Network for Determining Risk-Influencing Factors in Ship Self-Sinking Accidents

引用

ASCE-ASME Journal of Risk and Uncertainty in engineering Systems, Part A: Civil engineering 2025年第3期11卷

作者： Ma, Jun Wang, Liguang Xu, Luhui Zhao, Jiong Lin, Rui School of Computer Science Xijing Univ. Xi'An Key Laboratory of Human-Machine Integration and Control Technology for Intelligence Xi'an710123 China School of Computer Science Xijing Univ. Xi'an710123 China Xi'An Senke Construction Engineering Co. Xi'an710043 China

One of the most effective methods for analyzing risk-influencing factors (RIFs) in maritime accidents is the complex network approach. However, there is limited research specifically focused on RIFs in ship self-sinking accidents. Moreover, challenges remain in the accurate ontology construction of RIFs based on the data set, intelligent extraction of RIF propagation paths, RIF importance ranking, and robustness analysis of complex networks. To address these issues, an intelligent method is proposed to construct a ship self-sinking accident RIF complex network (SSARIFCN) based on 204 accident reports, yielding 247 nodes and 1,872 edges derived from 488 RIF propagation paths. This approach significantly improves the objectivity and accuracy of RIF identification while enhancing the intelligence level of the information extraction process. The three-weight LeaderRank algorithm is applied for node importance ranking and network robustness analysis, outperforming eight traditional ranking models and five attack algorithms, enhancing the accuracy of key RIF identification. Based on this algorithm, the top five RIFs for ship self-sinking accidents were identified, concluding that "unfit for maritime navigation"is a frequently overlooked key RIF. The experiment validates the method's effectiveness in identifying key RIFs, controlling RIF propagation, and enhancing accident prevention and navigational safety. © 2025 American Society of Civil Engineers.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Physics-informed CGAN and multi-scale attention CNN for pipeline leakage diagnosis under imbalanced data

引用

Advanced engineering Informatics 2025年 66卷

作者： Zhu, Yongqiang Li, Shuaiyong Lang, Xianming Liu, Liang School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Industrial Internet of Things and Networked Control Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China School of Information and Control Engineering Liaoning Petrochemical University Fushun113001 China

In industrial pipeline condition monitoring, class-imbalanced data distributions and multi-physics coupling effects significantly constrain the engineering applicability of intelligent diagnostic models. Class-imbalanced data lead to a scarcity of fault samples, making model training challenging. Meanwhile, complex multi-physics coupling effects complicate the prediction of equipment operating conditions. Generating synthetic data that are consistent in both statistical distribution and physical mechanism has become an effective solution to these issues. In this article, a hybrid framework that integrates a physics-informed data augmentation method with an intelligent fault diagnosis model is proposed. Within this framework, a novel physics-informed conditional generative adversarial network (PI-CGAN) is developed, where a physics-informed network (PIN) converts equipment behavior equations into implicit constraints for the generator, ensuring dual consistency in both statistical distributions and physical mechanisms. Subsequently, a hybrid attention module (HAM) is proposed to enhance data diversity and quality through cross-channel feature correlation and critical temporal segment localization. Furthermore, a multi-scale attention convolutional neural network (MSACNN) is developed to effectively decouple coupled features under complex operating conditions via a multi-scale attention mechanism. Experimental results demonstrate that under extreme data imbalance conditions, the proposed hybrid diagnostic framework can generate industrially viable synthetic data while achieving accurate fault identification. © 2025

关键词： Leak detection

来源：评论

学校读者我要写书评

暂无评论

Improved PBFT Algorithm Based on Reputations Synchronization and Group Consensus

引用

International Journal of High Speed Electronics and Systems 2025年第3期34卷

作者： Wang, Yongli Dou, Jing Yang, Peng Guo, Huijie Liu, Yang Hu, Junwei Co. Ltd Hohhot010000 China Co. Ltd Ordos017004 China School of Control and Computer Engineering North China Electric Power University Baoding071003 China

Introducing a reputation mechanism to improve the practical Byzantine fault-tolerant algorithm (PBFT) can effectively increase the security of the system, but the lack of a proper reputation synchronization method can easily lead to malicious behaviors such as node reputation fraud. To solve the above problems, this paper proposes an improved PBFT algorithm (RS-PBFT) which can synchronize node reputation. Firstly, node types are distinguished by node behaviors. The node types represent node reputation status. Secondly, the management node, which summarizes node behavior, judges node type and synchronizes node reputation, is selected by voting method. Finally, the grouping idea is used to optimize the consistency protocol. The consensus between consensus groups is parallel. Furthermore, the consensus within consensus groups is co-dominated by multiple subgroup master nodes, which reduces the communication overhead and solves the problems such as the lack of limit of a single master node. The experimental results show that when the number of consensus nodes is 12, the throughput of RSPBFT algorithm is 5.98 times that of PBFT algorithm. The consensus delay is reduced to 27.5% of PBFT algorithm, and the communication cost is reduced by 72.6%. © 2025 World Scientific Publishing Company.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Enhancing parameter prediction in gas-fired boiler systems through node similarity-based feature aggregation

引用

Energy 2025年 328卷

作者： Xiao, Guolin Lang, Qi Gao, Xiaori Lu, Wei Liu, Xiaodong School of Control Science and Engineering Dalian University of Technology Dalian116024 China School of Computer Science and Information Technology Northeast Normal University Changchun130117 China Navigation College Dalian Maritime University Dalian116026 China

Accurate sensor network prediction is crucial for improving industrial boiler efficiency and safety. While existing predictive models show promise, they are constrained by several limitations: (i) insufficient integration of interpretable multi-level spatiotemporal information, (ii) over-reliance on static topologies and shallow features, and (iii) limited continuity and adaptability in complex environments. To address these challenges, we propose a novel framework to improve parameter prediction in gas-fired boiler systems through node similarity-based feature aggregation. First, we apply a node similarity-based multi-level aggregation strategy for interpretable multi-scale integration. Next, dynamic graph learning, utilizing a higher-order graph convolutional network, captures the evolving relationships between sensors and time steps. Additionally, continuous modeling is facilitated by a spatiotemporal ordinary differential equation solver, which overcomes the limitations of discretized time steps. Real-world evaluations show our approach improves accuracy and robustness, even with sensor failures. Furthermore, the continuous model supports predictions at any time step. This approach provides a foundation for data-driven parameter prediction and the modeling of interacting industrial components. © 2025 Elsevier Ltd

关键词： Network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

A third-party platoon coordination service: Pricing under government subsidies

A third-party platoon coordination service: Pricing under go...

引用

作者： Bai, Ting Johansson, Alexander Li, Shaoyuan Johansson, Karl Henrik Mårtensson, Jonas School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden KTH Royal Institute of Technology Stockholm Sweden Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China Digital Futures Stockholm Sweden

This paper models a platooning system consisting of trucks and a third-party service provider (TPSP), which performs platoon coordination, distributes the platooning profit in platoons, and charges trucks in exchange for the services. Government subsidies used to incentivize platooning are also considered. We propose a pricing rule for the TPSP, which keeps part of the platooning profit including the subsidy each time a platoon is formed. In addition, a platoon coordination solution based on the distributed model predictive control (MPC) is proposed, in which the pricing rule under government subsidies is integrated. We perform a realistic simulation over the Swedish road network to evaluate the impact of the pricing rule and subsidies on the achieved profits and fuel savings. Our results show that subsidies are an effective mean to boost fuel savings from platooning. Moreover, the simulation study indicates that high pricing corresponds to a low platooning rate of the system, as trucks' incentives for platooning decrease. © 2023 The Authors. Asian Journal of control published by John Wiley & Sons Australia, Ltd on behalf of Chinese Automatic control Society.

关键词： Trucks

来源：评论

学校读者我要写书评

暂无评论

Structure design and analysis of a rigid-soft robotic hand with large load capacity 3

Structure design and analysis of a rigid-soft robotic hand w...

引用

3rd International Conference on Electrical, Electronics, and Information engineering, EEIE 2024

作者： Wu, Peichen Lan, Fuming Hong, Wen Chen, Xiaoping Shuai, Wei Cui, Guowei Gao, Yang Institute of Intelligent Manufacturing Guangdong Academy of Sciences Guangdong Key Laboratory of Modern Control Technology Guangzhou510070 China Shanghai Institute of Aerospace System Engineering Shanghai201100 China Intelligent Manufacturing Institute of HFUT HeFei230041 China School of Computer Science and Technology University of Science and Technology of China Hefei230026 China

ISBN: (纸本)9781510688179

In recent years, soft grippers have gained significant attention due to their adaptability and safety. However, when performing horizontal object grasping, their limited structural stiffness prevents them from withstanding the torque generated by friction between the gripper and the object, leading to a loss of contact and limiting their horizontal load capacity. To address this limitation while preserving the adaptability of soft grippers, this paper proposes a gripper structure called the rigid-soft robotic hand, which incorporates lateral rigid connecting rods outside the soft joints. The paper analyzes the bending capacity of the rigid-soft joint using kinematic methods and investigates the influence of link design parameters on maximum bending angle. Subsequently, a finite element analysis is conducted to study the finger structure with the added connecting rods, aiming to optimize the link design parameters. Experimental results demonstrate the grasping capabilities of the rigid-soft gripper in both vertical and horizontal orientations. The findings show that the rigid-soft gripper significantly improves the load-carrying capacity during horizontal object grasping while maintaining the adaptability of the soft gripper. © The Authors.

关键词： Robotic arms

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：