检索结果-内蒙古大学图书馆

International Black Sea Conference on Communications and Networking (BlackSeaCom)

作者： Paul Cotae Nii Emil Alexander Reindorf Myong Kang Alexander Velazquez Department of Electrical and Computer Engineering The University of the District of Columbia Washington DC USA U. S. Naval Research Laboratory Center for High Assurance Computer Systems Washington DC USA

We focus on a real-time multi agent decision-making algorithm that combines a centralized algorithm and a distributed algorithm. A network segmentation is unavoidable in a dynamic environment. In such cases, it is necessary for each agent to continually make the most urgent real-time decisions in both centralized and decentralized ways. In this paper, we present a Hybrid Factored-Value Max-Plus algorithm with cost which has online, anytime, and scalable properties despite network segmentation. We also study the performance of centralized and distributed algorithms to understand the performance characteristics of a hybrid algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Channel Dual Staging: Hierarchical and Portable Staging for GPU-Based In-Situ Workflow 31

Dual Channel Dual Staging: Hierarchical and Portable Staging...

引用

31st Annual IEEE International Conference on High Performance Computing, Data, and Analytics, HiPC 2024

作者： Zhang, Bo Davis, Philip E. Zhang, Zhao Teranishi, Keita Parashar, Manish Scientific Computing and Imaging Institute University of Utah Salt Lake CityUT84112 United States Department of Electrical and Computer Engineering Rutgers University PiscatawayNJ08854 United States Oak Ridge National Laboratory Oak RidgeTN37830 United States

ISBN: (纸本)9798331509095

In-situ workflows have emerged as an attractive approach for addressing data movement challenges at very large scales. Since GPU-based architectures dominate the HPC landscapes, porting these in-situ workflows, and, specifically, the inter-application data exchange, to GPU-based systems can be challenging. Technologies such as GPUDirect RDMA (GDR), which is typically used for I/O in GPU applications as an optimization that circumvents the CPU overhead, can be leveraged to support bulk data exchanges between GPU applications. However, current GDR design often lacks performance portability across HPC clusters built with different hardware configurations. Furthermore, the local CPU may also be effectively used as an auxiliary communication mechanism to offload data exchanges. In this paper, we present a dual channel dual staging approach for efficient, scalable, and performance-portable inter-application data exchange for in-situ workflows. This approach exploits the data access pattern within in-situ workflows along with the inherent execution asynchrony to accelerate data exchanges and, at the same time, improve performance portability. Specifically, the dual channel dual staging method leverages both the local CPU and the remote data staging server to build a hierarchical joint staging area and uses this staging area to transform blocking inter-application bulk data exchanges into best-effort local data movements between GPU and CPU. The dual channel dual staging is implemented as a portability extension of the Dataspaces-GPU staging framework. We present an experimental evaluation of its performance, portability, and scalability using this implementation on three leadership GPU clusters. The evaluation results demonstrate that the dual channel dual staging method saves up to 75% in data-exchange time compared to host-based, GDR, and alternate portable designs, while maintaining scalability (up to 512 GPUs) and performance portability across the three platforms. © 2

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimization of electric automated bus trajectories based on the ε-constraint method

Multi-objective optimization of electric automated bus traje...

引用

Mediterranean Conference on Control and Automation (MED)

作者： C. Pasquale S. Sacone S. Siri A. Ferrara Department of Informatics Bioengineering Robotics and Systems Engineering University of Genova Italy Department of Electrical Computer and Biomedical Engineering University of Pavia Italy

This paper deals with electric automated buses that have to follow a given route in inter-urban roads including stops, with a given timetable. Some stops are provided with a charging infrastructure allowing to charge the batteries while others are not. In order to control these buses, it is necessary to account for the traffic conditions along the road and to minimize two objectives, respectively related to the minimization of the deviations from the timetable and the minimization of the energy lack, at the end of the bus route, with respect to a desired final energy level. To address this problem and to investigate the conflicting nature of these objectives, two multi-objective methods based on the $\varepsilon$-constraint approach are applied in this paper, allowing to find different sets of efficient solutions for the problem. The results obtained in a real case study show that the two objective are in conflict, and compromise solutions can be found using the methods proposed in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accelerated Saddle Flow Dynamics for Bilinearly Coupled Minimax Problems

Accelerated Saddle Flow Dynamics for Bilinearly Coupled Mini...

引用

IEEE Conference on Decision and Control

作者： Yingzhu Liu Enrique Mallada Zhongkui Li Pengcheng You College of Engineering Peking University Beijing China State Key Laboratory for Turbulence and Complex Systems Peking University Beijing China Department of Electrical and Computer Engineering Johns Hopkins University Baltimore MD USA

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

Minimax problems have attracted much attention due to various applications in constrained optimization problems and zero-sum games. Identifying saddle points within these problems is crucial, and saddle flow dynamics offer a straightforward yet useful approach. This study focuses on a class of bilinearly coupled minimax problems with strongly convex-linear objective functions. We design an accelerated algorithm based on saddle flow dynamics, achieving a convergence rate beyond the stereotype limit (the strong convexity constant). The algorithm is derived from a sequential two-step transformation of a given objective function. First, a change of variables is applied to render the objective function better-conditioned, introducing strong concavity (from linearity) while preserving strong convexity. Second, proximal regularization, when staggered with the first step, further enhances the strong convexity of the objective function by shifting some of the obtained strong concavity. After these transformations, saddle flow dynamics based on the new objective function can be tuned for accelerated exponential convergence. Besides, such an approach can be extended to weakly convex-weakly concave functions and still guarantees exponential convergence to one stationary point. The theory is verified by a numerical test on an affine equality-constrained convex optimization problem.

关键词： Couplings Heuristic algorithms Linearity Games Linear programming Convex functions Game theory Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Label-Free Molecular and Metabolic Virtual Histology with Multimodal Photoacoustic Remote Sensing Microscopy

Label-Free Molecular and Metabolic Virtual Histology with Mu...

引用

Optical Molecular Probes, Imaging and Drug Delivery, OMP 2023 - Part of Optica Biophotonics Congress: Optics in the Life Sciences 2023

作者： Zemp, Roger Haven, Nathaniel J.M. Martell, Matthew T. Cikaluk, Brendyn D. Restall, Brendon Deschenes, Jean Peiris, Lashan Giannakopoulos, Nadia Department of Electrical and Computer Engineering University of Alberta 116 Street & 85 Avenue EdmontonABT6G 2R3 Canada Department of Laboratory Medicine and Pathology University of Alberta Canada Department of Surgery University of Alberta Canada

A fundamentally new form of microscopy, photoacoustic remote sensing offers label-free optical absorption contrast in a reflection mode all-optical embodiment and is providing unprecedented opportunities for fast virt...

ISBN: (纸本)9781957171210

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Multi-Agent DRL Based Dynamic Cluster Reconfiguration for UAV Mobility Management

arXiv

引用

arXiv 2024年

作者： Meer, Irshad A. Besser, Karl-Ludwig Ozger, Mustafa Schupke, Dominic Poor, H. Vincent Cavdar, Cicek School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Electrical and Computer Engineering Princeton University United States Airbus Central Research and Technology Taufkirchen82024 Germany Department of Electronic Systems Aalborg University Copenhagen2450 Denmark

Multi-connectivity involves dynamic cluster formation among distributed access points (APs) and coordinated resource allocation from these APs, highlighting the need for efficient mobility management strategies for users with multi-connectivity. In this paper, we propose a novel mobility management scheme for unmanned aerial vehicles (UAVs) that uses dynamic cluster reconfiguration with energy-efficient power allocation in a wireless interference network. Our objective encompasses meeting stringent reliability demands, minimizing joint power consumption, and reducing the frequency of cluster reconfiguration. To achieve these objectives, we propose a hierarchical multi-agent deep reinforcement learning (H-MADRL) framework, specifically tailored for dynamic clustering and power allocation. The edge cloud connected with a set of APs through low latency optical back-haul links hosts the high-level agent responsible for the optimal clustering policy, while low-level agents reside in the APs and are responsible for the power allocation policy. To further improve the learning efficiency, we propose a novel action-observation transition-driven learning algorithm that allows the low-level agents to use the action space from the high-level agent as part of the local observation space. This allows the lower-level agents to share partial information about the clustering policy and allocate the power more efficiently. The simulation results demonstrate that our proposed distributed algorithm achieves comparable performance to the centralized algorithm. Additionally, it offers better scalability, as the decision time for clustering and power allocation increases by only 10% when doubling the number of APs, compared to a 90% increase observed with the centralized approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Design, Dynamic Modeling and Control of a 2-DOF Robotic Wrist Actuated by Twisted and Coiled Actuators

arXiv

引用

arXiv 2025年

作者： Zhang, Yunsong Zhou, Xinyu Zhang, Feitian Department of Advanced Manufacturing and Robotics College of Engineering State Key Laboratory of Turbulence and Complex Systems Peking University Beijing100871 China Department of Electrical and Computer Engineering Michigan State University East LansingMI48824 United States

Robotic wrists play a pivotal role in the functionality of industrial manipulators and humanoid robots, facilitating manipulation and grasping tasks. In recent years, there has been a growing interest in integrating artificial muscle-driven actuators for robotic wrists, driven by advancements in technology offering high energy density, lightweight construction, and compact designs. However, in the study of robotic wrists driven by artificial muscles, dynamic model-based controllers are often overlooked, despite their critical importance for motion analysis and dynamic control of robots. This paper presents a novel design of a two-degree-of-freedom (2-DOF) robotic wrist driven by twisted and coiled actuators (TCA) utilizing a parallel mechanism with a 3RRRR configuration. The proposed robotic wrist is expected to feature lightweight structures and superior motion performance while mitigating friction issues. The Lagrangian dynamic model of the wrist is established, along with a nonlinear model predictive controller (NMPC) designed for trajectory tracking tasks. A prototype of the robotic wrist is developed, and extensive experiments are conducted to validate its superior motion performance and the proposed dynamic model. Subsequently, extensive comparative experiments between NMPC and PID controller were conducted under various operating conditions. The experimental results demonstrate the effectiveness and robustness of the dynamic model-based controller in the motion control of TCA-driven robotic wrists. Copyright © 2025, The Authors. All rights reserved.

关键词： Industrial manipulators

来源：评论

学校读者我要写书评

暂无评论

Late-Fusion Multimodal Human Detection Based on RGB and Thermal Images for Robotic Perception

Late-Fusion Multimodal Human Detection Based on RGB and Ther...

引用

European Conference on Mobile Robots (ECMR)

作者： Elísio Sousa Kennedy O. S. Mota Iago P. Gomes Luís Garrote Denis F. Wolf Cristiano Premebida Department of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Portugal Institute of Mathematics and Computer Science University of São Paulo Brazil

This paper addresses the problem of detecting humans in RGB and Thermal (long-wave IR) images taken by cameras mounted onboard a mobile robot. Human/Pedestrian detection is currently one of the most pertinent object detection problems, mainly due to safety concerns in autonomous vehicles. The majority of approaches apply deep-learning techniques based solely on RGB images. However, they have a few shortcomings, namely that during foggy weather, nighttime, and low-light scenarios, these images may not contain sufficient information. To address these issues, this work studies the use of thermal cameras as a complementary source of information for human detection in indoor and outdoor environments. The proposed approach uses YOLOv5 to detect pedestrians in both thermal and RGB images. Moreover, the different modalities are combined using early and late fusion techniques. Evaluation of the proposed approach is carried out in the FLIR Aligned dataset and in a new in-house dataset. Results indicate that the use of fusion techniques highlights a promising way to improve the overall performance in this application domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NEARLY MINIMAX OPTIMAL OFFLINE REINFORCEMENT LEARNING WITH LINEAR FUNCTION APPROXIMATION: SINGLE-AGENT MDP AND MARKOV GAME 11

NEARLY MINIMAX OPTIMAL OFFLINE REINFORCEMENT LEARNING WITH L...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Xiong, Wei Zhong, Han Shi, Chengshuai Shen, Cong Wang, Liwei Zhang, Tong Department of Mathematics The Hong Kong University of Science and Technology Hong Kong Center for Data Science Peking University China Department of Electrical and Computer Engineering University of Virginia United States National Key Laboratory of General Artificial Intelligence Peking University China School of Intelligence Science and Technology Peking University China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Offline reinforcement learning (RL) aims at learning an optimal strategy using a pre-collected dataset without further interactions with the environment. While various algorithms have been proposed for offline RL in the previous literature, the minimax optimality has only been (nearly) established for tabular Markov decision processes (MDPs). In this paper, we focus on offline RL with linear function approximation and propose a new pessimism-based algorithm for offline linear MDP. At the core of our algorithm is the uncertainty decomposition via a reference function, which is new in the literature of offline RL under linear function approximation. Theoretical analysis demonstrates that our algorithm can match the performance lower bound up to logarithmic factors. We also extend our techniques to the two-player zero-sum Markov games (MGs), and establish a new performance lower bound for MGs, which tightens the existing result, and verifies the nearly minimax optimality of the proposed algorithm. To the best of our knowledge, these are the first computationally efficient and nearly minimax optimal algorithms for offline single-agent MDPs and MGs with linear function approximation. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Manufacturing Process Selection Using Graph Neural Networks: A Novel Approach to CAD Model Semantic Segmentation 4

Manufacturing Process Selection Using Graph Neural Networks:...

引用

4th International Symposium on Artificial Intelligence and Intelligent Manufacturing, AIIM 2024

作者： Niu, Shuai Cai, Yishu Li, Feng Li, Yibo Tong, Xiaomeng School of Automation Science and Electrical Engineering Beijing China University of Liverpool Department of Computer Science Liverpool United Kingdom AVIC Shenyang Aircraft Corporation Shenyang China Central South University State Key Laboratory of Precision Manufacturing for Extreme Service Performance Changsha China

ISBN: (纸本)9798331541729

Manufacturing process selection, as a core element in the manufacturing workflow, plays a crucial role in improving processing efficiency and manufacturing quality. However, due to the fragmented, experience-based, and often outdated nature of processing knowledge, current process selection methods heavily rely on human intervention. To address these challenges, this study proposes an innovative approach that reframes manufacturing process selection as a graph-based semantic segmentation task. Building on this concept, we introduce a graph neural network-based method for manufacturing process selection, capable of effectively identifying processing methods in CAD models. This method discretely samples the topological faces and edges of CAD models, storing them as node and edge attributes in an attributed adjacency graph. Finally, we design experiments to validate the effectiveness and accuracy of this method in identifying manufacturing processes. Experimental results demonstrate that representing 3D CAD models with attributed adjacency graphs effectively captures the geometric and topological relationships between different faces of the model. This method can accurately identify corresponding manufacturing processes at the topological face level of CAD models, offering a novel approach to automated process selection. © 2024 IEEE.

关键词： Semantic Segmentation

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：