检索结果-内蒙古大学图书馆

Multi-agent deep reinforcement learning for end—edge orchestrated resource allocation in industrial wireless networks

引用

Frontiers of Information Technology & Electronic Engineering 2022年第1期23卷 47-60页

作者： Xiaoyu LIU Chi XU Haibin YU Peng ZENG State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang110016China Key Laboratory of Networked Control Systems Chinese Academy of SciencesShenyang110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang110169China University of Chinese Academy of Sciences Beijing100049China

Edge artificial intelligence will empower the ever simple industrial wireless networks(IWNs)supporting complex and dynamic tasks by collaboratively exploiting the computation and communication resources of both machine-type devices(MTDs)and edge *** this paper,we propose a multi-agent deep reinforcement learning based resource allocation(MADRL-RA)algorithm for end-edge orchestrated IWNs to support computation-intensive and delay-sensitive ***,we present the system model of IWNs,wherein each MTD is regarded as a self-learning ***,we apply the Markov decision process to formulate a minimum system overhead problem with joint optimization of delay and energy ***,we employ MADRL to defeat the explosive state space and learn an effective resource allocation policy with respect to computing decision,computation capacity,and transmission *** break the time correlation of training data while accelerating the learning process of MADRL-RA,we design a weighted experience replay to store and sample experiences ***,we propose a step-by-stepε-greedy method to balance exploitation and ***,we verify the effectiveness of MADRL-RA by comparing it with some benchmark algorithms in many experiments,showing that MADRL-RA converges quickly and learns an effective resource allocation policy achieving the minimum system overhead.

关键词： Multi-agent deep reinforcement learning End-edge orchestrated Industrial wireless networks Delay Energy consumption

来源：评论

学校读者我要写书评

暂无评论

Resilient Event-Triggered Model Predictive control for Adaptive Cruise control Under Sensor Attacks

引用

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 807-809页

作者： Zhijian Hu Rong Su Kai Zhang Zeyuan Xu Renjie Ma School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore Key Laboratory of Ultra-Precision Intelligent Instrumentation Ministry of Industry and Information Technologyand the Center of Ultra-Precision Optoelectronic Instrument EngineeringHarbin Institute of TechnologyHarbin 150001China Department of Control Science and Engineering Harbin Institute of TechnologyHarbin 150001China Department of Chemical and Biomolecular Engineering National University of SingaporeSingapore 117585Singapore State Key Laboratory of Robotics and Systems Harbin Institute of TechnologyHarbin 150001China IEEE

Dear Editor,This letter addresses the resilient model predictive control(MPC)problems for adaptive cruise control(ACC)systems under sensor *** the light of vulnerabilities of ACC systems to sensor attacks,an intrusion detection mechanism is proposed at the controller side to distinguish abnormal ***,the robust control gains are derived to design the terminal region constraint for MPC.

关键词： Trigger Event constraint

来源：评论

学校读者我要写书评

暂无评论

An Improved Dual Neural Network Method Based on Levy Flight for Multi-Robot Cooperative Area Coverage Search in 3D Unknown Environments

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Zhang, Fangfang Wang, Yongqi Wang, Wenhao Xin, Jianbin Peng, Jinzhu Wang, Yaonan Zhengzhou University School of Electrical and Information Engineering Zhengzhou450001 China State Key Laboratory of Intelligent Agricultural Power Equipment Luoyang471039 China National Engineering Laboratory of Robot Visual Perception and Control Technology School of Robotics Hunan University Changsha410082 China

The research on multi-robot collaborative search in unknown 3D environments, based on bio-inspired neural networks, holds significant value and ***, challenges arise in 3D environments, including excessive turning and vertical movement, as well as the potential for collisions between robots. In response, we propose an improved Glasius Bio-Inspired Neural Network(GBNN) that mitigates decision conflicts among robots and considers the impact of turning and vertical movement on robot decision-making. Furthermore, to address the issue of robots getting trapped in local deadlocks during the search process, we present a dual neural network algorithm based on Levy flights. In the method Dual Glasius Bio-Inspired Neural Network based on Levy Flight(LF-DUAL-GBNN) proposed in this paper, robots obtain random target points through Levy flights and are then guided by a dual neural network to navigate to the vicinity of the target points, thus breaking free from local deadlock states. Finally, we conducted simulation experiments to validate the algorithm's effectiveness. © 2016 IEEE.

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

intelligent electricity consumption forecasting and electricity-theft analysis method based on deep learning 2

Intelligent electricity consumption forecasting and electric...

引用

2nd International Conference on Electronic Information Engineering and Computer Technology, EIECT 2022

作者： Yu, Shimao Song, Chunhe Gao, Pengpei Zheng, Haiyang Chinese Academy of Sciences Key Laboratory of Networked Control Systems Shenyang Institute of Automation Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350399561

Residential electricity consumption data have great mining value for electricity-theft analysis and electricity consumption forecasting. This paper designs an intelligent electricity consumption forecasting and electricity-theft analysis method based on deep learning. Firstly, the power consumption data of a single user is converted into multi-period data through preprocessing, and the data forecasting is realized by designing a deep neural network model. The electricity-theft data are first amplified through user's power data and electricity-theft labels. And then the time series are converted into two-dimensional tensors for classification and recognition by deep CNN. The classification accuracy of electricity-theft reaches 92.2% compared with RNN method. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of Industrial Real-Time Ethernet Scheduling Method Based on Time Slot Reuse

Research and Implementation of Industrial Real-Time Ethernet...

引用

Artificial Intelligence, Networking and Information Technology (AINIT), International Seminar on

作者： Mingxu Gang Bingjun Yan Bo Hu Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

To improve the operation efficiency and real-time scheduling capability of existing industrial control network systems, based on the existing industrial real-time Ethernet communication protocol technology, an industrial real-time Ethernet scheduling method based on time slot reuse is proposed. This method adopts the time-division multiplexing strategy, decomposes the continuous time into different time slots, configures the data of different types of nodes to be transmitted in their respective time slots, uses the peak shift clock synchronization method and timer trigger task mechanism to improve the real-time communication, and uses the time slot multiplexing mechanism to improve the data transmission efficiency; Finally, a test platform is built to verify the proposed method. The experimental results show that the proposed method has high clock synchronization accuracy and real-time scheduling capability.

关键词： Multiplexing Job shop scheduling Protocols Accuracy Industrial control Ethernet Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Focal plane imaging system based on CMOS terahertz detector

Focal plane imaging system based on CMOS terahertz detector

引用

2024 International Conference on intelligent Manufacturing and Mechatronics, IMM 2024

作者： Lin, Yue Zhang, Hui Qi, Feng Liu, Zhaoyang Wang, Guanwen Wang, Ningbo School of Electrical and Control Engineering Shenyang Jianzhu University Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences China The Key Laboratory of Liaoning Province in Terahertz Imaging and Sensing Shenyang China The Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China The Key Laboratory of OptoElectronic Information Processing Chinese Academy of Sciences Shenyang China School of Information Science and Engineering Shenyang University of Technology Shenyang China

Terahertz technology has shown remarkable potential for application in the field of imaging since it offers several particular advantages such as great penetration capabilities, non-ionization and high instantaneous bandwidth. This paper presents a focal plane imging system based on CMOS terathertz detector for forward-looking detection. The focal plane imaging system has several advantages, including fast scanning, simple composition, low cost, and easy integration of a CMOS detector. It is composed of a terahertz radiation source, a Polytetrafluoroethylene (PTFE) lens and a broadband CMOS detector. The detector was fabricated in a 65 nm CMOS process. The operating frequency range of the detector covers 75 GHz to 1000 GHz. Measurement results have shown that the focal plane imaging system is capable of stably imaging at frequencies of 100 GHz and 220 GHz. To address the issue of missing information in measurement images, the morphological closing algorithm is employed to process the original image, successfully filling in the missing information and improving image quality. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Focusing

来源：评论

学校读者我要写书评

暂无评论

Improved Detection of Transmission Tower Equipment Using YOLOv7 with Saliency Data Augmentation

Improved Detection of Transmission Tower Equipment Using YOL...

引用

Clean Energy and Electric Power Engineering (ICCEPE), International Conference on

作者： Yingying Xu Chunhe Song Yong Sun Shimao Yu State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350390315

ISBN: (纸本)9798350390322

Transmission towers are critical infrastructure for power transmission, and the reliable operation of their equipment is essential to ensure electricity supply. However, the detection of transmission tower equipment faces challenges such as target overlap, large variations in size, small targets, and class imbalance due to the characteristics of the equipment. To tackle the identified issues, this study introduces a method based on YOLOv7 for the detection of transmission tower components, utilizing saliency-based data augmentation. Initially, an approach focusing on importance is employed to augment the sample size in categories with limited numbers, thereby enhancing the effectiveness of detection. Secondly, an adaptive adjustment module is introduced into the multi-head self-attention mechanism to dynamically adjust attention allocation based on the actual size of the targets and integrate contextual information, thus better handling targets with large size variations and overlaps. Finally, incorporating dynamic convolution within the backbone network significantly improves the ability to extract features from small objects. The outcomes of the experiments confirm the efficiency of the suggested approach in the smart surveillance of devices within intricate transmission settings, offering a reliable solution for maintaining power supply dependability.

关键词： Surveillance Poles and towers Data enhancement Power transmission Object detection Manuals Data augmentation Feature extraction Reliability Saliency detection

来源：评论

学校读者我要写书评

暂无评论

Trajectory Planning for Formation Variation of UGVs in Cluttered Environment

Trajectory Planning for Formation Variation of UGVs in Clutt...

引用

International Conference on intelligent Transportation

作者： Jie Cheng Ruishuang Chen Zhihui Liang Shuan Ding Zaiyue Yang Shenzhen Key Laboratory of Control The-ory and Intelligent Systems School of System Design and Intelligent Manufacturing Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology (SUSTech) Shenzhen China

The problem of trajectory planning for formation variation of unmanned ground vehicles (UGVs) is challenging due to the coupled non-collision constraints that apply to multiple vehicles. To address this issue, an innovative frame-work based on the alternating direction method of multipliers (ADMM) is proposed in this paper. The framework decouples complex constraints into two categories: individual constraints and mutual constraints. The former category involves dynamic, formation, and static obstacle constraints, which can be solved in parallel by each vehicle. Convex feasible set (CFS) algorithm is employed in this paper to simplify the static obstacle constraints. The latter category deals with collision avoidance among vehicles during the variation process and can be solved by nonlinear solvers. The convergence of the ADMM for the optimization problem is proved in this paper. Compared with solving the entire problem directly, the proposed framework reduces computation time and improves the quality of solution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Fast-trained and Generalized Spiking Neural Network for Robotic Gas Source Localization

A Fast-trained and Generalized Spiking Neural Network for Ro...

引用

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Chiyang Liu Xinxing Chen Jian Huang Hubei Key Laboratory of Brain-inspired Intelligent Systems and the Key Laboratory for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Mobile robots for Gas Source Localization (GSL) tasks are a safer alternative than human and animal rescuers in hazardous scenarios. Existing research primarily concentrates on rule-based algorithms or conventional artificial neural networks (ANNs). However, these approaches are either inapplicable in cluttered environments or undeployable due to their high energy consumption and the demand for substantial computational resources. This paper introduces the application of energy-efficient spiking neural networks (SNNs) to address robotic GSL tasks. A pipeline is proposed to train SNNs with deep Q learning and a pretrain-finetune paradigm. To facilitate the training process, a small dataset of gas dispersion is generated utilizing openFoam and GADEN, a high-fidelity simulator for gas dispersion. Data from a simplified plume model are leveraged to pretrain an ANN, the activation function of which gradually transitions from a bounded rectified linear unit (bReLU) to a step function. Subsequently, an SNN initialized with the ANN parameters undergoes finetuning on the GADEN-based dataset. The training pipeline significantly reduces training time compared to direct training of SNNs. The trained SNN is validated within the GADEN simulation environment and compared to three different models, demonstrating promising performance and superior generalization despite limited training data.

关键词： Training Location awareness Q-learning Mechatronics Pipelines Training data Spiking neural networks Data models Mobile robots Dispersion

来源：评论

学校读者我要写书评

暂无评论

Method of Forming Paths for Uniform Surface Treatment for Objects of Complex Shape

Method of Forming Paths for Uniform Surface Treatment for Ob...

引用

Annual Siberian Russian Workshop on Electron Devices and Materials (EDM)

作者： Ivan Grigorev Eduard Mursalimov Laboratory of Intelligent Information Systems for Marine Robots M.D. Ageev Institute of Marine Technology Problems FEB RAS Vladivostok Russia Laboratory of Robotics and Intelligent Control Systems Sevastopol State University Laboratory of Intelligent Information Systems for Marine Robots M.D. Ageev Institute of Marine Technology Problems FEB RAS Vladivostok Russia

ISBN: (数字)9798350389234

ISBN: (纸本)9798350353051

In most cases, tool impact paths for surface treatment (painting, milling, laser hardening, etc.) represent a set of continuous spatial curves lying on the surface to be treated. For uniform processing, adjacent curves from this set must be equidistant from each other. This paper presents a new method for covering a given polygonal mesh with equidistant lines based on given initial lines (in the form of a set of vertices on this mesh) and a given distance between adjacent lines, that is measured by Euclidean distance. The method is based on constructing spheres from each vertex of the initial line and removing the vertices of the mesh that fall into at least one of the spheres: the desired equidistant line will be represented by not removed vertices lying on the spheres. To construct each subsequent equidistant line, the last constructed line is used as the initial one: thus, the entire mesh is covered along the surface, despite the fact that the distance between adjacent lines is measured in space. Due to this, the proposed method, unlike the existing ones, works with surfaces of any complexity and requires less computing resources. Ordering the points of the constructed lines, to obtain the reference points of the paths that can be executed by the manipulator, is also presented.

关键词： Solid modeling Shape Surface emitting lasers Milling Kinematics Magnetic heads Mobile robots

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：