检索结果-内蒙古大学图书馆

A Multi-Model Fusion Approach for Transformer Fault Detection

A Multi-Model Fusion Approach for Transformer Fault Detectio...

Information Technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Ke Zhou Wei Zhang Ligang Li Shaoming Pan Chengwei Huang Guangxi Power Grid Equipment Monitoring and Diagnosis Technology Innovation Center Guangxi Key Laboratory of Intelligent Control and Maintenance of Power Equipment Electric Power Research Institute of Guangxi Power Grid CO. LTD. Nanning State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences China Power Supply Bureau of Guangxi Hezhou Power Grid Co. Ltd.

ISBN: (数字)9798350363609

ISBN: (纸本)9798350363616

Addressing the weak generalization capability and suboptimal prediction performance of single mechanistic and data-driven models, this paper proposes a transformer fault detection method based on the fusion of mechanism and data models. Firstly, vibration and current data are collected on-site to train the SVM vibration model and the Adaboost current model. Secondly, current simulation data is obtained using laboratory simulation software. This simulation data, combined with the current data collected under the same conditions on-site, is used as input to train the GBDT error compensation model. Finally, these three models are used as inputs to the GRNN, completing the overall model design. This fusion of mechanistic and data-driven models not only addresses the parameter mismatch issue of the mechanistic model under complex working conditions but also deeply mines time-series data. Experimental results show that The mean squared error of the fusion model is 0.002 lower than that of the data model, and the coefficient of determination is improved by 5.07% compared to the mechanistic model, enhancing the overall predictive accuracy of the model.

关键词： Vibrations Support vector machines Training Accuracy Biological system modeling Fault detection Predictive models Transformers Prediction algorithms Data models

来源：评论

学校读者我要写书评

暂无评论

DynaInsRemover: A Real-time Dynamic Instance-Aware Static 3D LiDAR Mapping Framework for Dynamic Environment

DynaInsRemover: A Real-time Dynamic Instance-Aware Static 3D...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Huanfeng Zhao Meibao Yao Xueming Xiao Bo Zheng Intelligent Robotics Lab (IRL) School of Artificial Intelligence Jilin University Changchun China Engineering Research Center of Knowledge-Driven Human-Machine Intelligence Ministry of Education China CVIR Lab Changchun University of Science and Technology Changchun China Key Lab of Opto-Electronic Measurement and Optical Information Transmission Technology Shanghai Aerospace Control Technology Institute Shanghai China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Dynamic objects diversify the distribution of point cloud in the map, degrading the performance of the robotic downstream tasks. To address this problem, we present a novel real-time dynamic instance-aware static mapping framework called DynaInsRemover, which exploits the geometric discrepancies between instances to efficiently remove dynamic objects and preserve more details of static map. It contains the Instance Occupancy Check module for initial dynamic instance proposal and the Instance Belief Update module for reverting false positives. We quantitatively evaluate our approach performance on the SemanticKITTI dataset and validate it in a real-world environment. Experimental evaluations show that our method achieves very promising results in dynamic environments. The implementation of our method is available as open source at: https://***/Zhaohuanfeng/***.

关键词： Point cloud compression Three-dimensional displays Laser radar Real-time systems Windows Proposals Object recognition

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Simulation by Learning from Online Human Demonstration with VR Headset

Pedestrian Simulation by Learning from Online Human Demonstr...

引用

International Conference on Intelligent Transportation

作者： Feiyang Yu Tingting Long Zhichao Cui Linhai Xu Li Li Chi Zhang National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an Shaanxi China Department of Automation BNRist Tsinghua University Beijing China School of Electronics and Control Engineering Chang'an University.

Pedestrian simulation is essential for verifying the safety of autonomous vehicles in simulators. The goal of pedes-trian simulation is to create realistic virtual representations of the pedestrian. However, current simulations lack empirical knowledge about real pedestrian behavior. In this paper, we propose a virtual reality (VR)-based method that enables real-time interaction between an individual and a simulated traffic environment. Our human-in-the-loop approach incorporates the empirical knowledge of a VR user into the simulator. The user can view the traffic simulation by wearing a VR device, which includes a head-mounted display and two controllers and provides sparse sensor data about their position and rotation. We combine representation learning techniques to develop a full-body motion-tracking agent that takes in sparse signals from the VR device and simulates full-body motions. This agent can estimate the full-body pose and visualize a pedestrian avatar in a traffic simulation scene. To validate our method, we constructed a VR traffic simulation environment and demonstrated that our approach can produce a pedestrian avatar whose behavior closely resembles that of the real VR user.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Regularization Approach to Analyze the Time-Optimal Motion of a Mobile Robot under State Constraints using Pontryagin’s Maximum Principle

引用

Procedia Computer Science 2021年 186卷 11-20页

作者： Fernando Lobo Pereira Roman Chertovskih Anna Daryina Askhat Diveev Dmitry Karamzin Elena Sofronova SYSTEC Faculty of Electrical Engineering Porto University and the Institute for Systems and Robotics 4200-465 Porto Portugal Federal Research Center “Computer Science and Control” of the Russian Academy of Science Moscow Russia

This work concerns the investigation of time-optimal control problem for a simplified mobile robot model subject to state constraints. In this type of problems, which involve the so-called unicycle dynamics, the well-established regularity conditions with respect to the state constraints are not fulfilled. This fact greatly complicates the analysis of the control problem bearing in mind the use of the maximum principle. Moreover, the difficulty is also due to the presence of a singular control mode with respect to the angular velocity. Herein, a regularization approach is proposed in order to overcome these obstacles. A certain tool for the numerical implementation is developed. The numerical analysis is provided for a sample problem.

关键词： Unicycle model state constraints regularization maximum principle

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Hypergraph Neural Network based on Attention Mechanism for Multi-view Data Action Recognition

Spatial-Temporal Hypergraph Neural Network based on Attentio...

引用

International Conference on Dependable Systems and Their Applications (DSA)

作者： Zhixuan Wu Nan Ma Tao Zhi Genbao Xu Beijing Key Laboratory of Information Service Engineering College of Robotics Beijing Union University Beijing China Faculty of Information Technology Beijing University of Technology Beijing China Engineering Research Center of Intelligence Perception and Autonomous Control Ministry of Education Beijing University of Technology Beijing China Yunji Technology Beijing China

To address the issue of large network computing parameters for spatial-temporal features of actions in multi-view video sequences, this paper proposes a Spatial-Temporal Hypergraph Neural Network based on Attention Mechanism (STHGNN-AM). This method consists of a Temporal Attention Mechanism based on Trainable Threshold (TAM-TT) and a Multi-scale Spatial-Temporal Residual Module (MS-STRM), achieving multi-view data action recognition. Specifically, TAM-TT is constructed by using a learnable threshold to extract key frames of actions from different view video frames input to the module. MS-STRM is employed to further improve the model performance, and high-order semantic features of actions are learned in a hypergraph neural network. The MS-STRM extracts features using a multi-scale approach, modeling long-term and short-term semantic information to capture the temporal information changes between different frames. Comparative experiments on the NTU RGB+D and imitating traffic police gestures datasets evince the superior performance and heightened recognition accuracy exhibited by the proposed methodology, effectively enhancing the cognitive ability of machine-human body language interaction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ODYSSEE: Oyster Detection Yielded by Sensor Systems on Edge Electronics

arXiv

引用

arXiv 2024年

作者： Lin, Xiaomin Mange, Vivek Suresh, Arjun Neuberger, Bernhard Palnitkar, Aadi Campbell, Brendan Williams, Alan Baxevani, Kleio Mallette, Jeremy Vera, Alhim Vincze, Markus Rekleitis, Ioannis Tanner, Herbert G. Aloimonos, Yiannis Maryland Robotics Center University of Maryland College ParkMD20742 United States Center for Autonomous and Robotic Systems University of Delaware NewarkDE19711 United States Automation and Control Institute TU Wien Vienna1040 Austria School of Marine Science and Policy University of Delaware LewesDE19958 United States University of Maryland Center for Environmental Science Horn Point Laboratory CambridgeMD21613 United States College of Engineering and Applied Science University of Cincinnati OH45221 United States Montreal QC Canada

Oysters are a vital keystone species in coastal ecosystems, providing significant economic, environmental, and cultural benefits. As the importance of oysters grows, so does the relevance of autonomous systems for their detection and monitoring. However, current monitoring strategies often rely on destructive methods. While manual identification of oysters from video footage is non-destructive, it is time-consuming, requires expert input, and is further complicated by the challenges of the underwater environment. To address these challenges, we propose a novel pipeline using stable diffusion to augment a collected real dataset with photorealistic synthetic data. This method enhances the dataset used to train a YOLOv10-based vision model. The model is then deployed and tested on an edge platform;Aqua2, an Autonomous Underwater Vehicle (AUV), achieving a state-of-the-art 0.657 mAP@50 for oyster detection. Copyright © 2024, The Authors. All rights reserved.

关键词： Shellfish

来源：评论

学校读者我要写书评

暂无评论

Inclined Quadrotor Landing using Deep Reinforcement Learning

arXiv

引用

arXiv 2021年

作者： Kooi, Jacob Eeuwe Babuška, Robert Department of Cognitive Robotics Delft Center for Systems and Control Delft University of Technology Delft2628 CD Netherlands Department of Cognitive Robotics Delft University of Technology Delft2628 CD Netherlands Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague Czech Republic

Landing a quadrotor on an inclined surface is a challenging maneuver. The final state of any inclined landing trajectory is not an equilibrium, which precludes the use of most conventional control methods. We propose a deep reinforcement learning approach to design an autonomous landing controller for inclined surfaces. Using the proximal policy optimization (PPO) algorithm with sparse rewards and a tailored curriculum learning approach, an inclined landing policy can be trained in simulation in less than 90 minutes on a standard laptop. The policy then directly runs on a real Crazyflie 2.1 quadrotor and successfully performs real inclined landings in a flying arena. A single policy evaluation takes approximately 2.5 ms, which makes it suitable for a future embedded implementation on the quadrotor. © 2021, CC BY.

关键词： Landing

来源：评论

学校读者我要写书评

暂无评论

control system for a robotic system for rehabilitation of lower limbs with feedback on the patient's effort 2022

Control system for a robotic system for rehabilitation of lo...

引用

2nd International Conference on robotics and control Engineering, RobCE 2022

作者： Rybak, Larisa Khalapyan, Sergey Rashoyan, Gagik Mohan, Santhakumar Nozdracheva, Anna Research Institute Robotics and Control Systems Bstu Named after V. G. Shukhov Belgorod Russia Stary Oskol Technological Institute N. A. A. A. Ugarov Nust MISiS Stary Oskol Belgorod Russia Mechanical Engineering Research Institute of the Russian Academy of Sciences Moscow Russia Indian Institute of Technology Palakkad Palakkad India Gamaleya National Research Center for Epidemiology and Microbiology Moscow Russia

ISBN: (纸本)9781450395854

The paper presents structural diagrams of the control system of a robotic system with feedback on the patient's effort and without it, illustrates the conditions for using each of them;a method is prepared to increase the reliability of data on the applied efforts, associated with the use of strain gauges in the absence of actions of the patient's motor organs;an example of the patient's motivation to perform "correct"movements, "helping"the mechanism, consisting in changing the speed of movement to form the patient's feeling that the mechanism moves due to his efforts;a mathematical model of the robotic system was obtained, graphs were constructed demonstrating the accuracy of working out a given trajectory due to the anthropometric parameters of the patient. © 2022 ACM.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detection

arXiv

引用

arXiv 2023年

作者： He, Xuan Yang, Fan Yang, Kailun Lin, Jiacheng Fu, Haolong Wang, Meng Yuan, Jin Li, Zhiyong The College of Computer Science and Electronic Engineering Hunan University Changsha410082 China The School of Robotics Hunan University China410012 China The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The School of Computer Science Hefei University of Technology Hefei230009 China

Transformer-based methods have demonstrated superior performance for monocular 3D object detection recently, which aims at predicting 3D attributes from a single 2D image. Most existing transformer-based methods leverage both visual and depth representations to explore valuable query points on objects, and the quality of the learned query points has a great impact on detection accuracy. Unfortunately, existing unsupervised attention mechanisms in transformers are prone to generate low-quality query features due to inaccurate receptive fields, especially on hard objects. To tackle this problem, this paper proposes a novel "Supervised Scale-aware Deformable Attention" (SSDA) for monocular 3D object detection. Specifically, SSDA presets several masks with different scales and utilizes depth and visual features to adaptively learn a scale-aware filter for object query augmentation. Imposing the scale awareness, SSDA could well predict the accurate receptive field of an object query to support robust query feature generation. Aside from this, SSDA is assigned with a Weighted Scale Matching (WSM) loss to supervise scale prediction, which presents more confident results as compared to the unsupervised attention mechanisms. Extensive experiments on the KITTI and Waymo Open datasets demonstrate that SSDA significantly improves the detection accuracy, especially on moderate and hard objects, yielding state-of-the-art performance as compared to the existing approaches. Our code will be made publicly available at https://***/mikasa3lili/SSD-MonoDETR. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Hardware-in-the-Loop Simulation of Vehicle-Manipulator Systems for Physical Interaction Tasks

Hardware-in-the-Loop Simulation of Vehicle-Manipulator Syste...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Hemjyoti Das Bjørn Kåre Sæbø Kristin Y. Pettersen Christian Ott Faculty of Electrical Engineering and Information Technology Automation and Control Institute (ACIN) Technical University of Vienna TU Wien Vienna Austria Department of Engineering Cybernetics Centre for Autonomous Marine Operations and Systems (NTNU AMOS) NTNU Norwegian University of Science and Technology Trondheim Norway German Aerospace Center Institute of Robotics and Mechatronics Wessling Germany

Hardware-in-the-loop simulation (HILS) allows a more realistic evaluation of control approaches than what is possible with pure software simulations, but without the actual complexity of the complete system. This is important for some complex systems such as orbital robots, where testing of the system is typically not possible after its launch, and an on-ground replica is used to validate the performance of such a system. In this article, an impedance-matching approach is presented to match the end-effector dynamics of a fixed-base robot manipulator with that of a target vehicle-manipulator system (VMS), while taking into account the redundant nullspace dynamics in a connected real-time simulation framework. This approach ensures that the forces and torques exerted by the system on the environment matches with that of the simulated system. The contact wrenches used in our approach are not obtained from numerical simulations, but rather from real physical interaction, which is one of the main advantages of our approach. The effectiveness of our method is validated by demonstrating various physical interaction tasks with the environment, using a suspended aerial manipulator as the target system.

关键词：

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：