检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zeng, Runhao Zhou, Dingjie Liang, Qiwei Liu, Junlin Li, Hui Huang, Changxin Li, Jianqiang Hu, Xiping Sun, Fuchun Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science and Technology Tsinghua University China

Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running. Copyright © 2024, The Authors. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Linear Taper Slot Antenna for Multiband Applications 3

Design and Implementation of Linear Taper Slot Antenna for M...

引用

3rd International Conference on Power, Energy, control and Transmission Systems, ICPECTS 2022

作者： Revathi, M. Ruban Thomas, D. Mohamed Abbas, A. Mohanraj, K. Tharani Chitra, U. Balaji, N. Dr. Sakunthala Engineering College Vel Tech Multi Tech Dr. Rangarajan Department of ECE Chennai India Dr. Sakunthala Engineering College Vel Tech Multi Tech Dr. Rangarajan Department of ECE India Sri Sairam Engineering College Instrumentation and Control Engineering Chennai India Sri Sairam Engineering College Computer Science Engineering Chennai India

ISBN: (纸本)9781665462754

Small, high-gain antennas have been in demand due to the proliferation of wireless technology over the past decade. For some uses, a high gain is preferable, while for others, a high return loss is required. Using multiband frequencies, a single Microstrip patch antenna can support all of these uses. For optimal performance and low return loss, a Linear Tapered Slot Antenna constructed from FR4 and fed by coaxial cable is required for this endeavor. At MmW frequencies, increasing channel capacity and decreasing inter-user interference calls for a directional antenna with a high gain. The proposed antenna is 38mm ∗ 50mm in size and has a return loss of -16.03dB at 8.77GHz, 10.86dB at 9.55GHz, 7.68dB at 11.3GHz, -24.93dB at 14.32GHz, and -20.98dB at 16.13GHz. The proposed antenna was developed and tested with HFSS software, and it operates effectively in the C-band, X-band, and Ku-band for wireless communication. The outcome demonstrates the high degree of concordance between simulation and measurement. © 2022 IEEE.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

Software-defined event-based camera and vision algorithms for digitizing highly dynamic manufacturing tasks

Software-defined event-based camera and vision algorithms fo...

引用

2024 Low-Cost Digital Solutions for Industrial Automation, LoDiSA 2024

作者： Walker, Emily Turner, Christopher J. Oyekan, John Department of Automatic Control & Systems Engineering The University of Sheffield SheffieldS1 3JD United Kingdom Surrey Business School The University of Surrey Surrey GuildfordGU2 7XH United Kingdom Real Time & Distributed Systems Group Department of Computer Science University of York Heslington YorkYO10 5GH United Kingdom

ISBN: (纸本)9781837242672

Event-based cameras are inspired by the way the retina in the eye process information. Rather than capturing image frames at a constant rate, event cameras generate data asynchronously, based on changes in pixel value between frames. As a result, these cameras have a high spatiotemporal accuracy, low power constraints and reduced artefacts from motion blur. Hence, they represent favourable properties for digitizing highly dynamic manufacturing tasks such as machine vibrations and rapid human assembly actions. However, the costs of event-based cameras are prohibitively high for small to medium sized enterprises (SMEs). In this research, we present the development of a rig that combines low-cost visual sensors with low-cost algorithms to perform action recognition for highly dynamic manual manufacturing tasks. We applied our algorithms to achieve an action classification system via a novel threshold-based approach and in parallel use a neural network to perform classification of objects in the video feed. The results achieved demonstrated that our approach was able to successfully identify various rapid manual tasks being performed on identified objects. In addition to SMEs, our approach would be suited for providing low-cost digitization on legacy machines. © This is an open access article published by the IET under the Creative Commons Attribution License (http://***/licenses/by/3.0/).

关键词： Machine vibrations

来源：评论

学校读者我要写书评

暂无评论

A Non-Iterative LMI-Based Design of Static Output Feedback control with $\mathcal{L}_{2}$ Gain Performance for Linear Systems

A Non-Iterative LMI-Based Design of Static Output Feedback C...

引用

International Conference on Electrical, control and Instrumentation engineering (ICECIE)

作者： Hidetoshi Oya Daiki Asada Shunya Nagai Kazushi Nakano Department of Computer Science Tokyo City University Tokyo Japan Graduate School of Integrative Science and Engineering Tokyo City University Tokyo Japan Department of Electronics and Control Engineering National Institute of Technology (KOSEN) Niihama College Ehime Japan Graduate School of Informatics and Engineering The University of Electro-Communications Tokyo Japan

ISBN: (数字)9798350380040

ISBN: (纸本)9798350380057

In this paper, we present a new LMI-based non-iterative design strategy for static output feedback controllers with $\mathcal{L}_{2}$ Gain Performance for linear systems. In our approach, on the basis of the well-known necessary and sufficient condition for the existence of the static output feedback control for linear systems, the non-iterative LMI-based design procedure for the proposed static output feedback controller is derived. In this paper, we show the LMI-based non-iterative design procedure for static output feedback controllers with $\mathcal{L}_{2}$ Gain Performance and the effectiveness of the proposed static output feedback control is presented through a simple illustrative example.

关键词： Linear systems Sufficient conditions Instruments Interconnected systems control systems Output feedback Gain

来源：评论

学校读者我要写书评

暂无评论

Translating Assembly Accuracy Requirements to Cut-Off Frequencies for Component Mode Synthesis

arXiv

引用

arXiv 2023年

作者： Janssen, Lars A.L. Besselink, Bart Fey, Rob H.B. van de Wouw, Nathan Dynamics & Control Department of Mechanical Engineering Eindhoven University of Technology Netherlands Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Netherlands

One of the most popular methods for reducing the complexity of assemblies of finite element models in the field of structural dynamics is component mode synthesis. A main challenge of component mode synthesis is balancing model complexity and model accuracy, because it is difficult to predict how component reduction influences assembly model accuracy. This work introduces an approach that allows for the translation of assembly model accuracy requirements in the frequency domain to the automatic selection of the cut-off frequencies for the model-order reduction (MOR) of components. The approach is based on a mathematical approach for MOR for coupled linear systems in the field of systems and control. We show how this approach is also applicable to structural dynamics models. We demonstrate the use of this approach in the scope of component mode synthesis (CMS) methods with the aim to reduce the complexity of component models while guaranteeing accuracy requirements of the assembly model. The proposed approach is illustrated on a mechanical, three-component structural dynamics system for which reduced-order models are computed that are reduced further compared to reduction using standard methods. This results in lower simulation cost, while maintaining the required accuracy. © 2023, CC BY-NC-ND.

关键词： Structural dynamics

来源：评论

学校读者我要写书评

暂无评论

Dual-Active-Bridge Converter with Triple Phase Shift control for a Wide Operating Voltage Range

Dual-Active-Bridge Converter with Triple Phase Shift Control...

引用

International Conference on Power Electronics (ICPE)

作者： Yi-Hsuan Chen Ta-Wei Huang Shih-Hao Kuo Yu-Chen Chang Huang-Jen Chiu Serafin Bachman Marek Jasiński Department of Electronics and Computer Engineering National Taiwan University of Science and Technology Taiwan Institute of Control and Industrial Electronics Warsaw University of Technology Warszawa Poland

An optimal modulation scheme with Triple-Phase-Shift (TPS) control that increase efficiency in the whole load range is presented for a Dual Active Bridge (DAB) converter under wide output voltage range conditions. This paper provides a comprehensive analysis of the DAB with TPS modulation, identifying all the switching modes to operate the DAB where expressions for the transfer functions, the peak inductor current and RMS inductor current are provided. An analysis of minimum Peak Current and minimum RMS Current control also are investigated. On this basic all-ZVS modulation scheme is originally proposed to improve light-load efficiency and to reduce the switching losses. A 15 kW prototype circuit is applied, and experimental results are presented to validate that the modulation and efficiency improvement are realized by applying the optimized modulation scheme. The experimental results also verify the effectiveness of the closed-loop control strategy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Invisible Servoing: a Visual Servoing Approach with Return-Conditioned Latent Diffusion

arXiv

引用

arXiv 2024年

作者： Gerges, Bishoy Bazzana, Barbara Botteghi, Nicolò Aboudorra, Youssef Franchi, Antonio Robotics and Mechatronics Group Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede7500AE Netherlands Department of Applied Mathematics University of Twente Enschede7500AE Netherlands Department of Computer Control and Management Engineering Sapienza University of Rome Rome00185 Italy

In this paper, we present a novel visual servoing (VS) approach based on latent Denoising Diffusion Probabilistic Models (DDPMs). Opposite to classical VS methods, the proposed approach allows reaching the desired target view, even when the target is initially not visible. This is possible thanks to the learning of a latent representation that the DDPM uses for planning and a dataset of trajectories encompassing target-invisible initial views. The latent representation is learned using a Cross-Modal Variational Autoencoder, and used to estimate the return for conditioning the trajectory generation of the DDPM. Given the current image, the DDPM generates trajectories in the latent space driving the robotic platform to the desired visual target. The approach is applicable to any velocity-based controlled platform. We test our method with simulated and real-world experiments using generic multi-rotor Uncrewed Aerial Vehicles (UAVs). A video of our experiments can be found at https://***/yu-aTxqceOA. Copyright © 2024, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Real-Time Inertia Estimation and Validation Using PMU Data and the Swing Equation in Power Systems

Real-Time Inertia Estimation and Validation Using PMU Data a...

引用

IEEE Green Technologies Conference (IEEE-Green)

作者： Mustafa A. Mhawesh Muthanna Al-Sarray Roy McCann Department of Electrical Engineering and Computer Science University of Arkansas Fayetteville AR USA Al-Furat Al-Awsat Technical University Kufa Iraq Operation and Control Office Ministry of Electricity Baghdad Iraq

ISBN: (数字)9798331520182

ISBN: (纸本)9798331520199

This paper presents a method to estimate power system inertia in real-time using Phasor Measurement Unit (PMU) data and the swing equation. Inertia is essential for maintaining power system stability during disturbances. The method calculates both electrical and mechanical power from PMU data and uses this information to estimate inertia by using Matlab. Then it validates the results by comparing calculated values with real measurements of the rate of change of frequency (ROCOF). Further validation is performed using data from a real-world generation trip event. The outcomes show that the proposed method is accurate, with minimal error, making it suitable for real-time applications.

关键词： Accuracy Estimation Power system stability Phasor measurement units Real-time systems Mathematical models Power grids Frequency measurement MATLAB

来源：评论

学校读者我要写书评

暂无评论

A Multi-Player Potential Game Approach for Sensor Network Localization with Noisy Measurements

A Multi-Player Potential Game Approach for Sensor Network Lo...

引用

IEEE Conference on Decision and control

作者： Gehui Xu Guanpu Chen Baris Fidan Yiguang Hong Hongsheng Qi Thomas Parisini Karl H. Johansson Department of Electrical and Electronic Engineering Imperial College London London UK Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Mechanical and Mechatronics Engineering University of Waterloo Waterloo ON Canada Department of Control Science and Engineering Tongji University shanghai China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai China Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing China Department of Electronic Systems Aalborg University Denmark Department of Engineering and Architecture University of Trieste Italy

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

Sensor network localization (SNL) is a challenging problem due to its inherent non-convexity and the effects of noise in inter-node ranging measurements and anchor node position. We formulate a non-convex SNL problem as a multiplayer non-convex potential game and investigate the existence and uniqueness of a Nash equilibrium (NE) in both the ideal setting without measurement noise and the practical setting with measurement noise. We first show that the NE exists and is unique in the noiseless case, and corresponds to the precise network localization. Then, we study the SNL for the case with errors affecting the anchor node position and the inter-node distance measurements. Specifically, we establish that in case these errors are sufficiently small, the NE exists and is unique. It is shown that the NE is an approximate solution to the SNL problem, and that the position errors can be quantified accordingly. Based on these findings, we apply the results to case studies involving only inter-node distance measurement errors and only anchor position information inaccuracies.

关键词： Location awareness Noise Games Position measurement Nash equilibrium Distance measurement Noise measurement

来源：评论

学校读者我要写书评

暂无评论

CLASS-SPECIFIC DISTRIBUTION ALIGNMENT FOR SEMI-SUPERVISED MEDICAL IMAGE CLASSIFICATION

arXiv

引用

arXiv 2023年

作者： Huang, Zhongzheng Wu, Jiawei Wang, Tao Li, Zuoyong Ioannou, Anastasia College of Computer and Control Engineering Minjiang University China College of Computer and Data Science Fuzhou University China College of Electrical and Mechanical Engineering Fujian Agriculture and Forestry University China International Digital Economy College Minjiang University China Department of Computer Science and Engineering European University Cyprus Cyprus Cyprus

Despite the success of deep neural networks in medical image classification, the problem remains challenging as data annotation is time-consuming, and the class distribution is imbalanced due to the relative scarcity of diseases. To address this problem, we propose Class-Specific Distribution Alignment (CSDA), a semi-supervised learning framework based on self-training that is suitable to learn from highly imbalanced datasets. Specifically, we first provide a new perspective to distribution alignment by considering the process as a change of basis in the vector space spanned by marginal predictions, and then derive CSDA to capture class-dependent marginal predictions on both labeled and unlabeled data, in order to avoid the bias towards majority classes. Furthermore, we propose a Variable Condition Queue (VCQ) module to maintain a proportionately balanced number of unlabeled samples for each class. Experiments on three public datasets HAM10000, CheXpert and Kvasir show that our method provides competitive performance on semi-supervised skin disease, thoracic disease, and endoscopic image classification tasks. Copyright © 2023, The Authors. All rights reserved.

关键词： Alignment

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：