检索结果-内蒙古大学图书馆

第40届中国控制会议

作者： Xiaoxing Ren Dewei Li Yugeng Xi Haibin Shao Department of Automation Shanghai Jiao Tong UniversityKey Laboratory of System Control and Information ProcessingMinistry of Education of ChinaShanghai Engineering Research Center of Intelligent Control and Management

This paper studies distributed optimization over the multi-agent network. We develop and analyze a novel accelerated distributed gradient descent method, termed as G-DGDlm, for gossip communication protocol. G-DGDlm uses gradient tracking technique and local memory. Specifically, each agent stores two past variables, namely, an estimate of the average gradient and an estimate of the optimal solution. G-DGDlm achieves linear convergence for strongly convex and smoot√h functions when the related works, we remove the dependence of θ on global parameters and G-DGDlm is applicable to gossip communication protocol. Numerical experiments of distributed estimation in sensor networks show the faster convergence speed of G-DGDlm in comparison with the state-of-the-art methods.

关键词： Distributed convex optimization gossip communication first-order methods

来源：评论

学校读者我要写书评

暂无评论

A Real-time Framework of Multi-Camera Vehicle Tracking system*

A Real-time Framework of Multi-Camera Vehicle Tracking Syste...

引用

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Hanyang Zhuang Xingyuan Chen Jianglin Lan Ying Wang Zhaoxuan Lu Chunxiang Wang Ming Yang University of Michigan - Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai China James Watt School of Engineering University of Glasgow Glasgow United Kingdom School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China Shanghai Intelligent and Connected Vehicle R&D Center Co. LTD Shanghai China Department of Automation Shanghai Jiao Tong University Shanghai Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (数字)9798350372601

ISBN: (纸本)9798350372618

Multi-camera vehicle tracking (MCVT) system is a key technology to build an intelligent city and intelligent transportation system. The MCVT system utilizes roadside monitoring devices and computing platforms to achieve city-level road traffic perception at a finer scale by tracking each vehicle on the road to obtain the trajectory. The existing MCVT system mainly focuses on dealing with the algorithm modules separately, without studying the real-time performance and system architecture of the entire pipeline. However, in real-world applications, many of the tricks in improving evaluation metrics are not applicable since there is endless traffic flow running all the time. Therefore, this paper proposes a real-time framework of the MCVT system to streamline all the algorithm modules with proper data flow. Firstly, a multi-threaded multi-vehicle tracking (MVT) module is developed to detect vehicles in each camera. Re-identification is implemented during MVT to provide the feature for tracking in the same camera and across different cameras. Then, after the vehicle leaves the camera field of view, the feature of vehicle trajectory is calculated by averaging the feature at each frame. Meanwhile, a background thread runs continuously to match the incoming feature of vehicle trajectory with past features by conducting a topology searching method. In the end, the vehicle trajectories with well-matched features are considered to be the same vehicle. The entire pipeline has been validated on two different datasets, the precision is 0.64 in the CityFlow dataset which uses 6 cameras simultaneously. In the customized dataset, the same method can still reach real-time when using 16 cameras at the same time with smaller network modules.

关键词： Visualization Target tracking Roads Human-machine systems Pipelines Urban areas Cameras

来源：评论

学校读者我要写书评

暂无评论

Model-Free Nonlinear Feedback Optimization

arXiv

引用

arXiv 2022年

作者： He, Zhiyu Bolognani, Saverio He, Jianping Dörfler, Florian Guan, Xinping Automatic Control Laboratory ETH Zürich Zürich8092 Switzerland Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

Feedback optimization is a control paradigm that enables physical systems to autonomously reach efficient operating points. Its central idea is to interconnect optimization iterations in closed-loop with the physical plant. Since iterative gradient-based methods are extensively used to achieve optimality, feedback optimization controllers typically require the knowledge of the steady-state sensitivity of the plant, which may not be easily accessible in some applications. In contrast, in this paper, we develop a model-free feedback controller for efficient steady-state operation of general dynamical systems. The proposed design consists of updating control inputs via gradient estimates constructed from evaluations of the nonconvex objective at the current input and at the measured output. We study the dynamic interconnection of the proposed iterative controller with a stable nonlinear discrete-time plant. For this setup, we characterize the optimality and stability of the closed-loop behavior as functions of the problem dimension, the number of iterations, and the rate of convergence of the physical plant. To handle general constraints that affect multiple inputs, we enhance the controller with Frank-Wolfe-type updates. © 2022, CC BY-SA.

关键词： Feedback control

来源：评论

学校读者我要写书评

暂无评论

QMIX Algorithm for Coordinated Welding of Multiple Robots

QMIX Algorithm for Coordinated Welding of Multiple Robots

引用

作者： Liangchuang Liao Yang-Yang Chen School of Electronic Science & Engineering Southeast University Robot Department Jiangsu Automation Research Institute School of Automation Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University

This paper considers the coordinated welding control based on deep multi-agent reinforcement *** discrete-time states and actions with local observation for the welding robots and the characteristics of the weld lines(e.g.,the starting points of the weld lines and the ending points of the weld lines) are defined,which is suitable to use the monotonic value function factorisation for deep multi-agent reinforcement learning(QMIX) algorithm.A novel reward composed of trajectory optimization,collision avoidance and the task done is designed,which is proved by the simulation in the grid-world environment.

关键词： Deep multi-agent reinforcement learning Welding robots QMIX

来源：评论

学校读者我要写书评

暂无评论

Text Recognition for Automated Test Execution in Interlocking: A Deep Learning Approach

Text Recognition for Automated Test Execution in Interlockin...

引用

1st International Conference on Robotics and Rehabilitation Intelligence, ICRRI 2020

作者： Xie, Dong Chai, Ming Liu, Hongjie Bai, Chen Wang, Qi Lv, Jidong Department of Electronic Engineering Beijing Jiaotong University Beijing China The National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University Beijing China

ISBN: (纸本)9789813349285

In this paper, we present a deep learning character recognition algorithm based on multi-level segmentation. It can improve the accuracy of recognition of button characters in the interlocked upper computer interface, which is of great significance to the design of the automatic test execution in the interlocking system. We first analyze the characteristics of characters in the interlocked upper computer interface and combine various methods to segment characters at multiple levels. Then, we build a deep learning character recognition model based on CNN to accurately recognize characters. Finally, we applied our algorithm to recognize the characters of the interfaces in a real interlocked upper computer software and made a comparison with other algorithms. The obtained results show the feasibility and advantage of our approach. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

A Model Predictive Current control for a Three-Phase Modular Matrix Converter

A Model Predictive Current Control for a Three-Phase Modular...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Maryam Sarebanzadeh Mohammad Ali Hosseinzadeh Ralph Kennel Ebrahim Babaei Marco Rivera Patrick Wheeler Chair of High-Power Converters System Technical University of Munich Munich Germany Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran Department of Electrical and Electronic Engineering Faculty of Engineering Chair of Power Electronics Machines and Control (PEMC) Research Group University of Nottingham Nottingham UK Laboratorio de Conversión de Energías y Electrónica de Potencia (LCEEP) Vicerrectoría Academica Universidad de Talca Talca Chile

ISBN: (数字)9798350376067

ISBN: (纸本)9798350376074

The modular matrix converter (MMC) integrates a multi-winding transformer with a three-phase-to-single-phase matrix converter for each phase, making it suitable for high-power, high-voltage applications. Predictive control is an advanced control technique widely applied to power converters due to its numerous advantages, including fast dynamic response, the elimination of the need for proportional gain, and straightforward implementation. This study proposes a model predictive control (MPC) strategy to regulate load currents, reactive power, and common-mode voltage in a three-phase modular matrix converter. The proposed MPC algorithm selects the optimal switching states from all valid options for the modular matrix converter to apply in the next control step. A cost function is then used to minimize the error between the predicted system variables and their reference values, ensuring that the best states are applied to the modular matrix converter. The proposed MPC technique effectively controls the load currents to follow the desired reference signals, maintains sinusoidal source current waveforms by regulating reactive power, and reduces the magnitude of the common-mode voltage. The performance of the proposed approach is demonstrated through simulation results obtained in the MATLAB/Simulink environment.

关键词： Current control Reactive power Total harmonic distortion Simulation Switches Cost function Transformers Matrix converters Voltage control Predictive control

来源：评论

学校读者我要写书评

暂无评论

Computing Optimal Resilience-Oriented Operation of Distribution systems Considering Heterogenous Consumer-Side Microgrids

引用

IEEE Transactions on Consumer electronics 2024年

作者： Bai, Ziyi Xu, Da Zhou, Bin Yang, Xiaodong Yang, Hanyu Liu, Ju Hubei University of Technology Hubei Key Laboratory for High-Efficiency Utilization of Solar Energy and Operation Control of Energy Storage System Wuhan430068 China Hubei University of Technology School of Electrical and Electronic Engineering Wuhan430068 China University of Macau State Key Laboratory of Internet of Things for Smart City Macao999078 China China University of Geosciences School of Automation Wuhan430074 China Hunan University College of Electrical and Information Engineering Changsha410082 China Hefei University of Technology State Key Laboratory of High Efficiency and High Quality Electric Energy Conversion Hefei230009 China Nanjing Tech University College of Electrical Engineering and Control Science Nanjing211816 China SGCC Jingmen Power Supply Company Jingmen448000 China

Mobile battery energy storage systems (MBESs), also called power-to-mobility, have been field-validated as backup generation resources. However, the role of multi-energy coordination towards resilient distribution systems (DSs) against large area disasters is still not yet involved. To cope with such challenges, this paper proposes a computing optimal resilient operation model for post-disaster microgrid-penetrated DS recovery based on the energy-to-mobility approach. In this model, mobile multi-energy storages (MMESs) are invested and routed based on their different transportation mobility, while DS with consumer-side biogas-solar-wind multi-energy microgrids are topologized by network reconfiguration. The coordinated resilient operation of different recovery actions of DS, MMESs, and consumer-side microgrids is a difficult optimization problem as results of its inherent nonconvexities, temporal-spatial mobility and strong multi-energy couplings. The original mixed-integer non-linear programming (MINLP) problem is thus equivalently linearized and reformulated into a mixed-integer linear programming (MILP) for computation performance improvement. The proposed methodology is benchmarked and performed on a modified radial DS with three consumer-side microgrids. Numerical studies demonstrate the effectiveness and superiority of the energy-to-mobility scheme over MBESs on system resilient level and economy. © 1975-2011 IEEE.

关键词： Mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Construction of Minecraft Virtual Reality Scene Based on Voxel Point Cloud 8th

Construction of Minecraft Virtual Reality Scene Based on Vox...

引用

8th International Conference on Cognitive systems and Information Processing, ICCSIP 2023

作者： Ji, Nuocheng Zhuang, Hanyang Yang, Ming The University of Michigan – Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai200240 China Global Institute of Future Technology Shanghai Jiao Tong University Shanghai200240 China Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

ISBN: (纸本)9789819980208

Virtual Reality is an important development direction in recent years. Minecraft, a popular sandbox game, has a great potential to become a virtual reality platform for building immersive environments. Traditional methods of building virtual reality scenes rely heavily on massive human labors and require high levels of proficiency. To address these limitations, we propose an automatic, voxelated 3D modeling method with foreground and background environment segmented that can reduce modeling costs and achieve effective application in Minecraft virtual reality scenes such as virtual campuses. The proposed method leverages the use of point cloud reconstruction using a voxelization approach. A pipeline of converting point cloud to Minecraft scene is developed. Through preprocessing, segmenting, coloring, and exporting, a Minecraft virtual reality scene can be automatically generated based on voxel point cloud. Due to the noise in point cloud may cause defect during voxelization, a denoising and smoothing method using slice scanning and voxel connectivity segmentation has been implemented. It can generate building structures with clear outlines and uniform colors. And the entire process requires low computational complexity and achieves fast generation. We conducted experiments based on this method in indoor scenes, outdoor building landmarks, and complex underground scenes, and obtained results with clear structures and smooth surfaces, saving a lot of time for subsequent detailed modeling. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Multi-level Coordinated Energy Management for Energy Hub in Hybrid Markets with Distributionally Robust Scheduling

arXiv

引用

arXiv 2022年

作者： Cao, Jiaxin Yang, Bo Zhu, Shanying Chung, Chi Yung Guan, Xinping Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education China Shanghai Engineering Research Center of Industrial Intelligent Control and Management Shanghai200240 China Department of Electrical and Computer Engineering University of Saskatchewan SaskatoonSKS7N 5A9 Canada

Maintaining energy balance and economical operation is significant for multi-energy systems such as the energy hub (EH). However, it is usually challenged by the frequently changing and unpredictable uncertain parameters at different timescales. Under this scope, this paper investigates the coordinated energy management problem for day-ahead and intra-day conditions considering uncertainties of source-load and market prices concurrently. Note that the precise knowledge of distributions about uncertainties may be unaccessible before the decision-making in day-ahead phase. A two-stage chance-constrained model based on distributionally robust approach with ambiguous moment information is proposed to immunize scheduling strategies against the worst-case probability distributions. The first stage is dedicated to obtaining more energy arbitrage and operation flexibility by optimizing bidding strategies in day-ahead power, natural gas and carbon trading markets. The second stage focuses on the optimization of the worst-case expected operation cost. It provides a robust energy equipment and load scheduling strategy for the reference of subsequent intra-day arrangements. With respect to different variations of electrical and thermal components, an intra-day two-timescale coordination is implemented step by step. The energy scheduling is re-dispatched circularly to minimize the operation and penalty costs. The possible energy imbalance is also compensated by this way. As the energy management program is nonlinear, chance-constrained and multi-stage, some linearization and dual transformation techniques are designed to enhance tractability of the program. Experimental results show that the developed multi-level framework results in a carbon emission decrease of 37%, and reduces energy cost averagely 3% compared with corresponding contrasting cases. The obtained strategy validates a good tradeoff between robustness and optimality. Copyright © 2022, The Authors. All rights reser

关键词： Power markets

来源：评论

学校读者我要写书评

暂无评论

Procedure Recognition by Knowledge-Driven Segmentation in Robotic-Assisted Vitreoretinal Surgery

Procedure Recognition by Knowledge-Driven Segmentation in Ro...

引用

IEEE International Conference on Robotics and automation (ICRA)

作者： Zhen Li Yawen Deng Qiang Ye Weihong Yu Haoxiang Qi Yaliang Liu Zhangguo Yu Gui-Bin Bian School of Electronic and Information Engineering Tongji University Shanghai China Institute of Automation Chinese Academy of Sciences Beijing China School of Mechatronic Engineering Beijing Institute of Technology Beijing China Department of Ophthalmology Peking Union Medical College Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing China Key Laboratory of Biomimetic Robots and Systems Ministry of Education Beijing China International Joint Research Laboratory of Biomimetic Robots and Systems Ministry of Education Beijing China State Key Laboratory of Intelligent Control and Decision of Complex System Beijing China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Internal limiting membrane (ILM) peeling is a vital vitreoretinal surgery procedure. However, due to the thickness of just 1-2 micrometers and the intricacies associated with its varying density and adhesion, the difficulty of manipulation exceeds the physiological limits of human perception and operation. Surgical robot is characterized by high precision and stability. However, navigating intricate intraocular environments and handling minuscule high-precision areas remain enormous challenges. These include issues of uneven lighting, field-of-view loss, and motion blur. This paper proposed a perception method named ‘Multimodal Surgical Process Recognition based on Domain Knowledge and Segmentation (MSPR-DKS),’ designed to address these challenges and provide input for the precise control of robots. Moreover, a comprehensive dataset focused on ILM peeling during macular hole surgeries was established. Experimental results underscore the efficacy of this approach, with segmentation accuracies exceeding 99.27% for instruments and macular holes and an average accuracy of 98.97% in recognizing surgical processes. This study paves the way for leveraging domain knowledge and image segmentation to improve robot-assisted manipulation of soft tissues in ophthalmology.

关键词： Image segmentation Visualization Accuracy Medical robotics Motion segmentation Surgery Lighting

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：