检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Weiqin Squillante, Mark S. Wu, Chai Wah Paternain, Santiago Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute United States Mathematical Sciences Department IBM Research

We devise a control-theoretic reinforcement learning approach to support direct learning of the optimal policy. We establish various theoretical properties of our approach, such as convergence and optimality of our analog of the Bellman operator and Q-learning, a new control-policy-variable gradient theorem, and a specific gradient ascent algorithm based on this theorem within the context of a specific control-theoretic framework. We empirically evaluate the performance of our control-theoretic approach on several classical reinforcement learning tasks, demonstrating significant improvements in solution quality, sample complexity, and running time of our approach over state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Semi-Autonomous Interaction Framework for Contact-Based Operations with Commercial UAVs IN GNSS-Denied Environments

Semi-Autonomous Interaction Framework for Contact-Based Oper...

引用

International Conference on Unmanned Aircraft systems (ICUAS)

作者： A. González-Morgado Q. Zhang G. Damigos E. Cuniato T. Hui E. Sahin G. Nikolakopoulos R. Siegwart M. Fumagalli A. Ollero G. Heredia GRVC Robotics Labs University of Seville Spain 3D Media Group Tampere University Finland Department of Computer Electrical and Space Ericsson Research and the Robotics and AI Group Autonomous Systems Lab (ASL) at ETH Zurich Switzerland Department of Electrical and Photonics Engineering Technical University of Denmark Denmark Department of Computer Electrical and Space Robotics and AI Group

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

Unmanned aerial vehicles (UAVs) are being increasingly established for autonomous contacted-based inspection of industrial assets, reducing the risk of errors by human operators. However, challenges remain in the navigation under unreliable Global Navigation Satellite System (GNSS) signals, or in the detection and interaction with the inspection surface, which limits the autonomy level of current UAV industrial technologies. This paper presents a semi-autonomous framework which combines automated target detection and interaction in GNSS-denied environments, with supervision commands by a human operator, to increase both safety and reliability. Our framework is composed of: (i) a camera-based onboard odometry solution for positioning the UAV in GNSSdenied conditions, (ii) a target-detection and filtering algorithm which estimates the orientation and position of the interaction target and (iii) a visual servoing strategy for approaching and contacting the target. The proposed framework is developed completely in ROS, and can be used with any commercial UAV. The framework is validated through outdoor flights, where a UAV detects and contacts a target on a vertical pipe.

关键词： Vibrations Global navigation satellite system Three-dimensional displays Switches Inspection Autonomous aerial vehicles Visual servoing Safety Odometry Reliability

来源：评论

学校读者我要写书评

暂无评论

Real-time behavior recognition of animal: an IoT-based system design using acceleration data

引用

Multimedia Tools and Applications 2024年 1-26页

作者： Tran, Duc-Nghia Manh, Do Viet Van Thanh, Pham Shankar, A. Achyut Joshi, Kireet Tran, Duc-Tan Institute of Information Technology Vietnam Academy of Science and Technology Hanoi Viet Nam University of Fire Prevention and Fighting Hanoi100000 Viet Nam Department of Cyber Systems Engineering WMG University of Warwick CoventryCV74AL United Kingdom Department of CSE University Centre for Research & ampDevelopment Chandigarh University Punjab Mohali140413 India School of Computer Science Engineering Lovely Professional University Punjab Phagwara144411 India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun248002 India Center of Research Impact and Outcome Chitkara University Punjab Chandigarh India Department of Computer Science & amp Engineering Graphic Era Deemed to be University Uttarakhand Dehradun248002 India Faculty of Electrical and Electronic Engineering Phenikaa University Hanoi12116 Viet Nam

By analyzing large amounts of animal behavior data, humans can assess cattle’s condition. It leads to research and development a field using accelerometers and machine learning algorithms to ‘study’ behavior from acceleration data. It is challenging to analyze animal behavior due to the activity complexity. For example, acceleration data of some cow behaviors (e.g., feeding and standing) are similar if these behaviors contain similar gestures. In practical, real-time applications even bring more challenging since it is necessary to minimize a data window for behavior consideration. Using short data window often reduces the performance of classification algorithms. This study proposes a new solution for the mentioned challenges by combining neck-mounted and leg-mounted accelerometers, then using the vector of the dynamic body acceleration (VeDBA) and Mean features of synchronized acceleration data for the Decision Tree algorithm. The proposed method is demonstrated that performs well (0.94 accuracy, 0.91 sensitivity, 0.90 positive predictive value) within a low computational complexity algorithm and short data window (3-second data window, at the rate of one sample per second). It is particularly suited for the case of a real-time IoT-based system. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Policy Gradients for Probabilistic Constrained Reinforcement Learning 57

Policy Gradients for Probabilistic Constrained Reinforcement...

引用

57th Annual Conference on Information Sciences and systems, CISS 2023

作者： Chen, Weiqin Subramanian, Dharmashankar Paternain, Santiago Rensselaer Polytechnic Institute Department of Electrical Computer and Systems Engineering TroyNY United States Ibm T. J. Watson Research Center Yorktown HeightsNY United States

ISBN: (纸本)9781665451819

This paper considers the problem of learning safe policies in the context of reinforcement learning (RL). In particular, we consider the notion of probabilistic safety. This is, we aim to design policies that maintain the state of the system in a safe set with high probability. This notion differs from cumulative constraints often considered in the literature. The challenge of working with probabilistic safety is the lack of expressions for their gradients. Indeed, policy optimization algorithms rely on gradients of the objective function and the constraints. To the best of our knowledge, this work is the first one providing such explicit gradient expressions for probabilistic constraints. It is worth noting that the gradient of this family of constraints can be applied to various policy-based algorithms. We demonstrate empirically that it is possible to handle probabilistic constraints in a continuous navigation problem. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Integrated Data-Driven and Model-Based Trade-off Analysis of Sensor Suite System for Autonomous Ground Vehicle Navigation

Integrated Data-Driven and Model-Based Trade-off Analysis of...

引用

IEEE International Symposium on systems engineering (ISSE)

作者： Sai Sandeep Damera Praveen Kumar M. S John S. Baras Department of Electrical and Computer Engineering Institute for Systems Research (ISR) at the University of Maryland College Park MD USA

ISBN: (数字)9798350353723

ISBN: (纸本)9798350353730

In recent years, the deployment of robots for commercial applications has surged, emphasizing the need to incorporate autonomy into these systems. The widespread adoption of autonomous robots across diverse fields thus necessitates a rigorous design framework. To address this, we recently proposed an Integrated Data-Driven and Model-Based systems engineering (IDDMBSE) framework—an extension of our traditional Model-Based systems engineering (MBSE). Our IDDMBSE framework aims to enable trusted autonomy in autonomous systems. In this work, we outline a methodology for trade-off analysis within the IDDMBSE framework, supporting the development of autonomous robots based on functional, performance, and programmatic requirements. The method comprises two key components: 1) Model-Based Optimization (MBO) - Leveraging domain-specific knowledge, MBO facilitates efficient simulation-based design, and 2) Data-Driven Evaluation (DDE) - Decoupling DDE from MBO allows effective exploration and statistical analysis of the design space. We demonstrate the utility of the proposed framework by using it to perform design space exploration and trade-off analysis for the design of the sensor suite of an autonomous ground robot. Our results show how a classical design problem that is often deemed intractable using model-based methods and unscalable using data-driven methods can benefit through the use of our hybrid framework.

关键词： Space vehicles Analytical models Statistical analysis Navigation Robot sensing systems Land vehicles Space exploration Optimization Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

Electric Vehicle Performance Enhancement Utilizing Hybrid Energy Storage systems

Electric Vehicle Performance Enhancement Utilizing Hybrid En...

引用

IEEE Conference on Vehicle Power and Propulsion (VPPC)

作者： Hossam M. Hussein SM Sajjad Hossain Rafin Mahmoud S. Abdelrahman Ibtissam Kharchouf Osama A. Mohammed Department of Electrical and Computer Engineering Energy Systems Research Laboratory Florida International University Miami Fl USA

ISBN: (数字)9798331541606

ISBN: (纸本)9798331541613

Energy storage systems (ESSs) are vital in various applications, including electric vehicles (EVs) and microgrids. In comparison, lithium-ion batteries (LIBs) are widely used in ESSs, and challenges such as power density, thermal management, and cell voltage balance prompt the exploration of alternative solutions. Integrating supercapacitors (SCs) alongside batteries in hybrid energy storage systems (HESS) presents a promising solution. SCs can provide high bursts of power, extending battery lifespan and improving efficiency, especially during high-demand scenarios like acceleration and braking. Optimizing energy management strategies (EMS) is crucial to minimize operational costs and ensure practical battery usage within HESS. Different driving cycles, such as the New European Driving Cycle (NEDC) and World Harmonized Light Vehicles Test Procedure (WLTP), provide insights into real-world driving conditions. HESS configurations and operational modes, including traction and regenerative braking, are essential for efficient EV operation. This study uses simulation models to investigate EVs' performance with HESS under various driving conditions, highlighting the system's stability and adaptability.

关键词： Lithium-ion batteries Power system measurements Supercapacitors Propulsion Power system stability Thermal management Stability analysis Energy management Thermal stability Strain

来源：评论

学校读者我要写书评

暂无评论

Container-based Platform for Edge-Computing in Energy System Applications

Container-based Platform for Edge-Computing in Energy System...

引用

IEEE General Meeting Power& Energy Society

作者： Mahmoud S. Abdelrahman Hossam Hussein Osama A. Mohammed Department of Electrical and Computer Engineering Energy Systems Research Laboratory Florida International University Miami Fl USA

ISBN: (数字)9798350381832

ISBN: (纸本)9798350381849

The design of power systems is growing more complex due to the large-scale building of microgrids and the ongoing advancement of renewable energy technologies. Several management approaches are applied to overcome these issues using cloud computing and the Internet of Things (IoT). However, the security and time delay for long-distance transferring to cloud communication are crucial concerns. Edge computing is a promising technology to address these challenges. Emerging smart energy systems are frequently deployed at the Edge of the power grid to meet the needs of smart grid users and achieve secure, efficient, and low-latency data processing. This paper proposes a container-based platform for Edge computing emulation based on a co-simulation model to implement, test, and validate Edge computing-based energy system applications. In addition, the feasibility of the proposed model is demonstrated by a case study of a consensus control technique based on an Edge computing framework for multi-microgrids.

关键词： Cloud computing Computational modeling Emulation Microgrids Containers Consensus control Smart grids Internet of Things Security Edge computing

来源：评论

学校读者我要写书评

暂无评论

Towards a Compact Monolithic Integrated Laser Platform on SiN: Deep-groove-assisted Bends

Towards a Compact Monolithic Integrated Laser Platform on Si...

引用

2024 IEEE Photonics Conference, IPC 2024

作者： Zhang, Ziyao Skandalos, Ilias Ma, Rui Chen, Minjia Zhong, Chuan Gardes, Frederic Cheng, Qixiang Penty, Richard University of Cambridge Centre for Photonic Systems Electrical Engineering Division Department of Engineering CambridgeCB3 0FA United Kingdom University of Southampton Optoelectronics Research Centre SouthamptonSO17 1BJ United Kingdom Princeton University Electrical and Computer Engineering PrincetonNJ08544 United States

We demonstrate a novel bending structure on silicon nitride towards a monolithically integrated laser platform. This bending structure has a deep etched groove along the outer side, and can greatly reduce the footprin... 详细信息

ISBN: (纸本)9798350361957

关键词： Silicon nitride

来源：评论

学校读者我要写书评

暂无评论

Coordinated EMS for Stability Enhancement of NMGs During Disturbance and Fault Conditions

Coordinated EMS for Stability Enhancement of NMGs During Dis...

引用

Annual Conference of Industrial Electronics Society

作者： Hossam M. Hussein Mahmoud S. Abdelrahman Ibtissam Kharchouf S M Sajjad Hossain Rafin Osama A. Mohammed Department of Electrical and Computer Engineering Energy Systems Research Laboratory Florida International University Miami Fl USA

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

Power systems are evolving from centralized power grid structures to networks of intelligent microgrids (MGs) that can share power more independently. The interconnection between these MGs, forming the networked MGs (NMGs), will increase the power system’s stability and expand its capabilities. However, a critical concern that necessitates sophisticated management strategies for voltage stabilization across the microgrids is the optimal and effective power sharing between renewable resources and energy storage devices. Effective power sharing between AC and DC sides is critical, necessitating robust control mechanisms for interlink converters (ILC). This paper presents a coordinated energy management strategy for hybrid networked MGs (NMGs) to enhance stability during contingencies and fault instances. The proposed Energy Management System (EMS) operates in two distinct modes: grid-connected and islanded. The system takes specific actions to maintain stability depending on the current mode. In grid-connected mode, the grid supplies the load demand while one of the microgrids (MGs) serves as a backup to ensure system stability. Several scenarios were created using MATLAB/Simulink to test and validate the EMS. These scenarios included varying load demands, pulsed power loads, uncertainties in photovoltaic (PV) system generation, disconnection from the AC side, and fault conditions. The proposed EMS has proven its efficiency while maintaining the system stability within the standard limits and fulfilling the load demands.

关键词： Robust control Renewable energy sources Contingency management Microgrids Power system stability Stability analysis MATLAB Energy management systems Thermal stability Energy storage

来源：评论

学校读者我要写书评

暂无评论

Cyber-HIL Autonomous Inverter-Based Microgrid Framework: Control System Performance and Communication Network Quality of Service

Cyber-HIL Autonomous Inverter-Based Microgrid Framework: Con...

引用

IEEE Industry Applications Society Annual Meeting (IAS)

作者： Ola Ali Osama A. Mohammed Department of Electrical and Computer Engineering Energy Systems Research Laboratory Florida International University Miami FL USA

ISBN: (数字)9798350372717

ISBN: (纸本)9798350372724

The integration of communication networks within modern power systems enhances the control of modern power systems; however, it increases the system's complexity. This interdependence raises the need to analyze power systems as cyber-physical systems (CPS). Microgrids (MGs) play a vital role in modern power systems, facilitating sustainable operation while decreasing the reliance on the main grid. Different distributed energy resources can be integrated by utilizing power electronics inverters working under grid-forming mode; this configuration forms the inverter-based autonomous AC microgrids. Droop control as a primary control layer is a wellknown technique that enables power-sharing among the various resources within the inverter-based MG. However, it has a limitation in keeping the system voltage and frequency constant. Thus, a secondary control layer is introduced to compensate for the droop limitations. This paper presents an innovative study that considers the communication network performance while studying the control of MGs through a cyber hardware-in-theloop (Cyber-HIL) autonomous inverter-based MG framework that integrates Opal-rt, network simulator ns-3, and docker containers. The effectiveness of the designed MG system equipped with its primary and the developed centralized secondary control system, in addition to the quality of service (QoS) of the designed communication network emulation, are presented in the experimental results.

关键词： Emulation Microgrids Quality of service Containers Control systems Power systems Communication networks Voltage control Frequency control Load modeling

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：