检索结果-内蒙古大学图书馆

Robust Practical Stabilization for Complex Dynamical Networks With DoS Attacks and Actuator Saturation

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年第5期55卷 3108-3118页

作者： Shi, Xueya Peng, Zhinan Yu, Junzhi Li, Hongfei Southwest University College of Electronic and Information Engineering Chongqing400715 China Sichuan Artificial Intelligence Research Institute Yibin644000 China University of Electronic Science and Technology of China School of Automation Engineering Chengdu611731 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics College of Engineering Beijing100871 China

This article addresses the problem of designing an attack-resilient adaptive event-triggered (AET) controller for complex dynamical networks (CDNs) under DoS attacks and actuator saturation, with a focus on robust practical stability (RPS). First, considering the impact of DoS attacks on closed-loop systems, an AET controller against DoS attacks is designed. Unlike other event-triggered controllers, the complete timeline is divided, and the AET controller is built with two switching modes based on the intervals of dormant and active periods of DoS attacks in which the system is located. Second, to reconcile AET controller with actuator saturation, a switched system modeling approach is established that explicitly incorporates saturation constraints into the coupled network dynamics. Third, a switched Lyapunov-Krasovskii functional (LKF) is proposed, with which sufficient conditions are provided to ensured the RPS, and a joint design strategy is developed for the desired triggered matrix and feedback gain using linear matrix inequalities (LMIs). Moreover, the results are generalized to the case of actuator faults, indicating that the system is able to achieve RPS with actuator faults. Finally, the proposed method is verified through an example. © 2013 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

InstKD: Towards Lightweight 3D Object Detection With Instance-Aware Knowledge Distillation

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-13页

作者： Zhang, Haonan Liu, Longjun Huang, Yuqi Lei, Xinyu Tong, Lei Wen, Bihan National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong University Beijing China School of Electrical and Electronic Engineering Nanyang Technological University Singapore

Deep neural network (DNN) is extensively explored for LiDAR-based 3D object detection, a crucial perception task in the field of autonomous driving. However, the presence of redundant parameters and complex computations pose challenges for the practical deployment of DNNs. Despite knowledge distillation (KD) is an effective approach for accelerating models, extremely small number of efforts explore its potential on LiDARbased 3D detectors. Besides, existing studies neglect to elaborately investigate 3D voxel-wise features for compression. To this end, we propose instance-aware knowledge distillation (InstKD) for 3D detector compression. The proposed method conducts KD by fully excavating two types of knowledge related to 3D voxelwise features. Firstly, the 3D voxel-wise feature of teacher is transferred to teach the student. In order to prioritize the knowledge with strong guiding capacity, we introduce expanded bounding box (E-Bbox) to distinguish and balance the foreground and background regions. Besides, we generate contribution map (CM) by calculating the gap between the classification response of teacher and student models to further dynamically balance individual instance for distillation. Secondly, we also align the relation-based knowledge of 3D voxel-wise features between the distillation pairs. To avoid incalculable relation on a massive number of 3D voxel-wise features, we distill the relation among instances selected by E-Bboxes, where the intra-relation of homogeneous instances and inter-relation of heterogeneous instances are transferred in a dual-pathway manner. In the experiments, we compress different models on benchmarks with varying scales. The results demonstrate that our method achieves the lightweight 3D detector with slight performance drop. For example, on KITTI dataset, our 2× compressed SECOND (75.5% parameters and 74.5% FLOPs reduction) achieves 66.83% mAP, surpassing its teacher model. The key code is available at https://***/zhnxj

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Landing Area Prediction in Complex Terrains for Walking-assisted Lower-limb Exoskeleton Robot

Landing Area Prediction in Complex Terrains for Walking-assi...

引用

2023 International Conference on Biomimetic Intelligence and robotics

作者： Liu, Yuexun Liu, Du-Xin Ma, Yue Guo, Sheng Wu, Xinyu Robotics Research Center School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing100044 China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

With the expansion of application scenarios, the walking-assisted lower-limb exoskeleton robot urgently needs to improve its walking ability in complex terrains. However, due to the lack of environmental understanding ability and decision-making ability, the exoskeleton can not meet the need of people with lower-limb disability in complex terrains. To improve the walking abillity, this paper proposes a method of predicting the landing area in complex terrains for walking-assisted lower-limb exoskeleton robot. Multiple sensors were used to obtain the terrain information, step length, and stride length of human walking, and a multi-type input convolutional network was built to establish the mapping relationship to learn the decision-making mechanism of human standing in a complex environment. The result shows that the established network effectively predicts the landing area. Under the condition of full training, the predicted position deviation of the landing area is controlled within 6%, and the prediction rationality of the landing area can reach 90%. © 2023 The Authors. Published by Elsevier B.V.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Kinematics Analysis and Singularity Avoidance of a Parallel Mechanism with Kinematic Redundancy

引用

Chinese Journal of Mechanical Engineering 2022年第5期35卷 244-261页

作者： Chaoyu Shen Haibo Qu Sheng Guo Xiao Li Robotics Research Center School of MechanicalElectronic and Control EngineeringBeijing Jiaotong UniversityBeijing 100044China China Waterborne Transport Research Institute Beijing 100088China Key Laboratory of Vehicle Advanced Manufacturing Measuring and Control TechnologyMinistry of EducationBeijing Jiaotong UniversityBeijing 100044China

The kinematic redundancy is considered as a way to improve the performance of the parallel *** this paper,the kinematics performance of a three degree-of-freedom parallel mechanism with kinematic redundancy(3-DOF PM-KR)and the influence of redundant parts on the PM-KR are ***,the kinematics model of the PM-KR is *** inverse solutions,the Jacobian matrix,and the workspace of the PM-KR are ***,the influence of redundancy on the PM-KR is *** there exists kinematic redundancy,the PM-KR possesses fault-tolerant *** locking one actuating joint or two actuating joints simultaneously,the fault-tolerant workspace is *** the position of the redundant part is changed,the workspace and singularity will be *** results show that kinematic redundancy can be used to avoid ***,the simulations are performed to prove the theoretical analysis.

关键词： Parallel mechanism Kinematic redundancy Singularity Simulation analysis

来源：评论

学校读者我要写书评

暂无评论

Landing Area Prediction in Complex Terrains for Walking-assisted Lower-limb Exoskeleton Robot

引用

Procedia Computer Science 2023年 226卷 120-126页

作者： Yuexun Liu Du-Xin Liu Yue Ma Sheng Guo Xinyu Wu Robotics Research Center School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing 100044 China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 China

关键词： Landing area prediction Walking-assisted lower-limb exoskeleton robot Complex terrains

来源：评论

学校读者我要写书评

暂无评论

Community microgrid:an approach towards positive energy community in an urban area of Dhaka,Bangladesh

引用

Clean Energy 2023年第4期7卷 926-939页

作者： Mohammad Zeyad S.M.Masum Ahmed Sayeed Hasan Dewan Mahnaaz Mahmud Energy and Technology Research Division Advanced BioinformaticsComputational Biology and Data Science LaboratoryBangladesh(ABCD LaboratoryBangladesh)House:24Road:01Block:BHalishaharChattogram 4226Bangladesh School of Engineering and Physical Sciences(EPS) Heriot-Watt UniversityCampus The AvenueEdinburghScotland EH144ASUK Department of Energy Engineering University of the Basque Country(UPV/EHU)Ingeniero Torres Quevedo Plaza1BilbaoBiscay 48013Spain Department of Electrical Electronic and Control EngineeringSchool of Industrial EngineeringUniversity of ExtremaduraCampus UniversitarioAv.de Elvass/nBadajozBadajoz 06006Spain Centre for Research on Geography ResourcesEnvironmentEnergy and Networks(Green)Bocconi UniversityVia Roentgen 1MilanoLombardy 20136Italy Control and Robotics(CORO) Ecole Centrale De Nantes1 Rue de la No?44300 NantesFrance

The pollution and toxic greenhouse gases produced by fossil fuel combustion are troubling as global energy demand continues to *** mitigate the consequences of global warming,a transition to sustainable energy sources is *** manuscript presents a feasible community microgrid design in Hazaribagh,Dhaka based on meteorological data that leads to photovoltaic installation on the rooftop of a local community *** study shows a microgrid design of a system with the lowest cost of energy and a large renewable fraction,which is analysed using the HOMER Pro *** real-time data,analysis of the system cost,cost of energy,renewable fraction,unmet load,energy purchased and energy sold is discussed.A suitable case for electrification is also identified and presented for the selected *** proposed case yields a cost of energy of$0.0357/kWh,which is 52%less than the current tariff rate,with a 70%renewable *** study will provide people in this community with more green energy at a lower cost;in addition,this designed microgrid sells additional energy to the grid to avoid possible power *** potential for a positive energy community is also investigated in terms of energy consumption and renewable output of the planned microgrid.

关键词： cost of energy microgrid positive energy community renewable fraction

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Control for Stomach Coverage Scanning of Wireless Capsule Endoscopy

Deep Reinforcement Learning-Based Control for Stomach Covera...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Zhang, Yameng Bai, Long Liu, Li Ren, Hongliang Meng, Max Q.-H. The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong Hong Kong The Shun Hing Institute of Advanced Engineering The Chinese University of Hong Kong Hong Kong Hong Kong The Department of Biomedical Engineering National University of Singapore Singapore Singapore Research Institute Suzhou215000 China The Shenzhen Key Laboratory of Robotics Perception and Intelligence China The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China The Shenzhen Research Institute The Chinese University of Hong Kong at Shenzhen Shenzhen518057 China

ISBN: (纸本)9781665481090

Due to its non-invasive and painless characteristics, wireless capsule endoscopy has become the new gold standard for assessing gastrointestinal disorders. Omissions, however, could occur throughout the examination since controlling capsule endoscope can be challenging. In this work, we control the magnetic capsule endoscope for the coverage scanning task in the stomach based on reinforcement learning so that the capsule can comprehensively scan every corner of the stomach. We apply a well-made virtual platform named VR-Caps to simulate the process of stomach coverage scanning with a capsule endoscope model. We utilize and compare two deep reinforcement learning algorithms, the Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) algorithms, to train the permanent magnetic agent, which actuates the capsule endoscope directly via magnetic fields and then optimizes the scanning efficiency of stomach coverage. We analyze the pros and cons of the two algorithms with different hyperparameters and achieve a coverage rate of 98.04% of the stomach area within 150.37 seconds. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Control for Stomach Coverage Scanning of Wireless Capsule Endoscopy

arXiv

引用

arXiv 2023年

作者： Zhang, Yameng Bai, Long Liu, Li Ren, Hongliang Meng, Max Q.-H. The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong The Shun Hing Institute of Advanced Engineering The Chinese University of Hong Kong Hong Kong Research Institute Suzhou215000 China The Shenzhen Key Laboratory of Robotics Perception and Intelligence China The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China The Shenzhen Research Institute The Chinese University of Hong Kong at Shenzhen Shenzhen518057 China

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Joint Sparse Representations and Coupled Dictionary Learning in Multi-Source Heterogeneous Image Pseudo-color Fusion

arXiv

引用

arXiv 2023年

作者： Bai, Long Yao, Shilong Gao, Kun Huang, Yanjun Tang, Ruijie Yan, Hong Meng, Max Q.-H. Ren, Hongliang The Department of Electronic Engineering The Chinese University of Hong Kong 999077 Hong Kong The Department of Electrical Engineering City University of Hong Kong 999077 Hong Kong Shenzhen Key Laboratory of Robotics Perception and Intelligence Shenzhen China The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China The Key Laboratory of Photoelectronic Imaging Technology and System Ministry of Education of China Beijing Institute of Technology Beijing100081 China The Shun Hing Institute of Advanced Engineering The Chinese University of Hong Kong 999077 Hong Kong Singapore117575 Singapore Research Institute Suzhou215123 China

Considering that Coupled Dictionary Learning (CDL) method can obtain a reasonable linear mathematical relationship between resource images, we propose a novel CDL-based Synthetic Aperture Radar (SAR) and multispectral pseudo-color fusion method. Firstly, the traditional Brovey transform is employed as a pre-processing method on the paired SAR and multispectral images. Then, CDL is used to capture the correlation between the pre-processed image pairs based on the dictionaries generated from the source images via enforced joint sparse coding. Afterward, the joint sparse representation in the pair of dictionaries is utilized to construct an image mask via calculating the reconstruction errors, and therefore generate the final fusion image. The experimental verification results of the SAR images from the Sentinel-1 satellite and the multispectral images from the Landsat-8 satellite show that the proposed method can achieve superior visual effects, and excellent quantitative performance in terms of spectral distortion, correlation coefficient, MSE, NIQE, BRISQUE, and PIQE. Copyright © 2023, The Authors. All rights reserved.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Control for Stomach Coverage Scanning of Wireless Capsule Endoscopy

Deep Reinforcement Learning-Based Control for Stomach Covera...

引用

IEEE International Conference on robotics and Biomimetics

作者： Yameng Zhang Long Bai Li Liu Hongliang Ren Max Q.–H. Meng Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong Hong Kong also with the Department of Biomedical Engineering National Institute of Advanced Engineering The Chinese University of Hong Kong University of Singapore Singapore and NUS (Suzhou) Research Institute Suzhou China Department of Electronic and Electrical Engineering Shenzhen Key Laboratory of Robotics Perception and Intelligence Southern University of Science and Technology Shenzhen China Shenzhen Research Institute The Chinese University of Hong Kong at Shenzhen Shenzhen China

ISBN: (纸本)9781665481106

关键词： Wireless communication Deep learning Stomach Endoscopes Reinforcement learning Gastrointestinal tract Magnetic fields

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：