检索结果-内蒙古大学图书馆

Chinese automation Congress (CAC)

作者： Haozhe Zhang Liyan Ma Shihui Ying Institute of Artificial Intelligence Shanghai University Shanghai China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Computer Engineering and Science School of Mechatronic Engineering and Automation Shanghai University Shanghai China Department of Mathematics School of Science Shanghai University Shanghai China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Traditional fully annotated closed set 3D object detection methods improve model performance but are impractical in real-world settings due to the emergence of new categories and the complexity of 3D annotations. Open-World Object Detection (OWOD) addresses these issues but relies heavily on manual labeling, which is costly. This paper focuses on open world active learning and proposes an entropy-guided reinforced open world active 3D object detection (EROA). EROA regards active learning as a reinforcement learning problem tailored for open driving scenarios. We use entropy as a reward metric for efficient reinforcement learning. We also leverage knowledge from the 2D domain using object-level large-scale vision-language models to enhance sample selection. Extensive experiments evidence that the proposed EROA meets the dynamic and cost-sensitive requirements of autonomous driving, enabling real-time detection of both known and unknown objects.

关键词： Measurement Solid modeling Three-dimensional displays Active learning Object detection Reinforcement learning Entropy Real-time systems Labeling Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptive Object Detection Based on Frequency Domain Adjustment and Pixel-Level Feature Fusion 12

Unsupervised Domain Adaptive Object Detection Based on Frequ...

引用

12th International Conference on CYBER Technology in automation, Control, and Intelligent Systems, CYBER 2022

作者： Xu, Yanlong Fan, Huijie Pan, Hao Wu, Lianquan Tang, Yandong College of Information Engineering Shenyang University of Chemical Technology Shenyang110142 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China Department of Police Skills and Tactics Training Criminal Investigation Police University of China Shenyang110854 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

It is very risky to apply the knowledge learned by the model on the labeled dataset directly to a completely new dataset, especially the unlabeled data, as the gap between these two domains can lead to a severe drop in model performance, However, the difference in illumination, texture and background of the image is one of the difficult problems to solve. In this paper, We proposed a Frequency domain Adjustment module (FA) and Pixel-Level feature Fusion (PLF) block for unsupervised domain adaptation of different types of features. From a frequency domain perspective, we first transfer the style of unlabeled target domain data to labeled source domain data before training using a Fourier transform. The benefit of this strategy can narrow the illumination gap between the source domain and the target domain. Secondly, due to the lack of labels in the target domain data, the feature extraction effect is poor. We consider proposing an improved multi-scale feature fusion mechanism to integrate information. Our method is experimentally validated on multiple public adaptive public datasets, The experimental results show that this method can more accurately detect and recognize images in domain adaptive scenes, and it outperforms the mainstream methods of domain adaptive object detection. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Learning Goal-oriented Bimanual Dough Rolling Using Dynamic Heterogeneous Graph Based on Human Demonstration

arXiv

引用

arXiv 2024年

作者： Liu, Junjia Li, Chenzui Wang, Shixiong Dong, Zhipeng Calinon, Sylvain Li, Miao Chen, Fei The Department of Mechanical and Automation Engineering T-Stone Robotics Institute The Chinese University of Hong Kong Hong Kong The Idiap Research Institute Martigny Switzerland The School of Microelectronics The Institute of Technological Sciences Wuhan University Wuhan China

Soft object manipulation poses significant challenges for robots, requiring effective techniques for state representation and manipulation policy learning. State representation involves capturing the dynamic changes in the environment, while manipulation policy learning focuses on establishing the relationship between robot actions and state transformations to achieve specific goals. To address these challenges, this research paper introduces a novel approach: a dynamic heterogeneous graph-based model for learning goal-oriented soft object manipulation policies. The proposed model utilizes graphs as a unified representation for both states and policy learning. By leveraging the dynamic graph, we can extract crucial information regarding object dynamics and manipulation policies. Furthermore, the model facilitates the integration of demonstrations, enabling guided policy learning. To evaluate the efficacy of our approach, we designed a dough rolling task and conducted experiments using both a differentiable simulator and a real-world humanoid robot. Additionally, several ablation studies were performed to analyze the effect of our method, demonstrating its superiority in achieving human-like behavior. Copyright © 2024, The Authors. All rights reserved.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Model-Free Large-Scale Cloth Spreading With Mobile Manipulation: Initial Feasibility Study

arXiv

引用

arXiv 2023年

作者： Chu, Xiangyu Wang, Shengzhi Feng, Minjian Zheng, Jiaxi Zhao, Yuxuan Huang, Jing Samuel Au, K.W. Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong Multi-Scale Medical Robotics Center Hong Kong School of Engineering Westlake University China Department of Mechanical and Aerospace Engineering The Hong Kong University of Science and Technology Hong Kong

Cloth manipulation is common in domestic and service tasks, and most studies use fixed-base manipulators to manipulate objects whose sizes are relatively small with respect to the manipulators' workspace, such as towels, shirts, and rags. In contrast, manipulation of large-scale cloth, such as bed making and tablecloth spreading, poses additional challenges of reachability and manipulation control. To address them, this paper presents a novel framework to spread large-scale cloth, with a single-arm mobile manipulator that can solve the reachability issue, for an initial feasibility study. On the manipulation control side, without modeling highly deformable cloth, a vision-based manipulation control scheme is applied and based on an online-update Jacobian matrix mapping from selected feature points to the end-effector motion. To coordinate the control of the manipulator and mobile platform, Behavior Trees (BTs) are used because of their modularity. Finally, experiments are conducted, including validation of the model-free manipulation control for cloth spreading in different conditions and the large-scale cloth spreading framework. The experimental results demonstrate the large-scale cloth spreading task feasibility with a single-arm mobile manipulator and the model-free deformation controller. Copyright © 2023, The Authors. All rights reserved.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Machine Vision Applications in robotics and automation

Machine Vision Applications in Robotics and Automation

引用

International Conference on Science Technology engineering and Management (ICONSTEM)

作者： Bharathi GP Kavitha P Laxman Baburao Abhang G. Rathinasabapathi Vipin Sharma T. Sathish Department of Computer and Communication Engineering Sri Sai Ram Institute of Technology Chennai Tamil Nadu India Department of Electrical and Electronics Engineering R.M.K Engineering College Kavaraipettai Tamil Nadu India Department of Automation and Robotics Pravara Rural Engineering College Loni Maharashtra India Department of Mechanical Engineering Panimalar Engineering College Chennai Tamil Nadu India Department of Mechanical Engineering Medi-Caps University Indore Madhya Pradesh Department of Mechanical Engineering Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

The extensive incorporation of machine vision into the fields of robotics and automation in a variety of different ways. The various uses of machine vision and the revolutionary impact it has on the capabilities of robotic systems. This investigation is fueled by improvements in imaging technology and artificial intelligence. In the abstract, major features such as object detection, navigation, and human-robot interaction are discussed in depth. The abstract also demonstrates how machine vision algorithms contribute to enhanced precision, efficiency, and adaptability in automation processes. The purpose of thisis to shed light on the role that machine vision plays in revolutionising industrial automation, collaborative robotics, and autonomous systems by conducting an examination of real-world implementations and case studies. This all-encompassing investigation not only highlights the current status of machine vision applications but also forecasts the future trajectory of this technology, thereby establishing it as a foundational component for the development of robotics and automation in a variety of fields.

关键词： automation Service robots Navigation Machine vision Imaging Human-robot interaction Object detection

来源：评论

学校读者我要写书评

暂无评论

Learning Stable Robotic Skills on Riemannian Manifolds

arXiv

引用

arXiv 2022年

作者： Saveriano, Matteo Abu-Dakka, Fares J. Kyrki, Ville Automatic Control Lab. Department of Industrial Engineering University of Trento Trento Italy Intelligent Robotics Group Department of Electrical Engineering and Automation Aalto University Finland

In this paper, we propose an approach to learn stable dynamical systems evolving on Riemannian manifolds. The approach leverages a data-efficient procedure to learn a diffeomorphic transformation that maps simple stable dynamical systems onto complex robotic skills. By exploiting mathematical tools from differential geometry, the method ensures that the learned skills fulfill the geometric constraints imposed by the underlying manifolds, such as unit quaternion (UQ) for orientation and symmetric positive definite (SPD) matrices for impedance, while preserving the convergence to a given target. The proposed approach is firstly tested in simulation on a public benchmark, obtained by projecting Cartesian data into UQ and SPD manifolds, and compared with existing approaches. Apart from evaluating the approach on a public benchmark, several experiments were performed on a real robot performing bottle stacking in different conditions and a drilling task in cooperation with a human operator. The evaluation shows promising results in terms of learning accuracy and task adaptation capabilities. Copyright © 2022, The Authors. All rights reserved.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

In-container Robot Palletizing with 3D vision-based Datum Point Positioning

In-container Robot Palletizing with 3D vision-based Datum Po...

引用

2021 China automation Congress, CAC 2021

作者： Li, Runze Fan, Siyuan Hou, Jinliang Hou, Qingwen Chen, Xianzhong School of Automation and Electrical Engineering Shunde Graduate School of University of Science and Technology Beijing Foshan China Vision Department Foshan Rossum Robotics Co. Ltd Foshan China School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China

ISBN: (纸本)9781665426473

Palletizing inside the container faces inefficiency of manual palletizing and positioning inprecision of robot. To solve these problems, it is necessary to consider two important procedures: robot palletizing scheme analysis and datum point positioning inside the container. A 3D vision-based positioning algorithm, which was combined with robot kinematics was proposed and then executed. A D-H table was built for robot RS050N to achieve the homogeneous transformation matrix;then, whole corner positioning algorithm based on 3D vision was designed, which included segmentation, down sampling, filter and an algorithm designed for boundary fitting in point cloud. It can reduce data volume, improve efficiency, and remove the point cloud which interferes positioning precision, such as stiffeners and bumps at corners. In the experiment, this algorithm can realize precise positioning for industrial robot palletizing in the container, meeting MAE of 1.715 mm and RMSE of 1.976 mm. © 2021 IEEE

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Automatic Facial Asymmetry Analysis for Elderly Stroke Detection by using Cosine Similarity 19

Automatic Facial Asymmetry Analysis for Elderly Stroke Detec...

引用

19th International Conference on Electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2022

作者： Kaewmahanin, Watchara Rassameecharoenchai, Teerameth Jutharee, Wisanu Tongskulroongruang, Thienrawit Wiphunawat, Paphatchaya Jennawasin, Tanagorn Kaewkamnerdpong, Boonserm Naresuan University Faculty of Allied Health Sciences Department of Cardiothoracic Technology Phitsanulok Thailand King Mongkut's University of Technology Thonburi Institute of Field Robotics and Automation Bangkok Thailand Mongkut's University of Technology Thonburi Department of Control Systems and Instrumentation Engineering Bangkok Thailand King Mongkut's University of Technology Thonburi Biological Engineering Program Faculty of Engineering Bangkok Thailand

ISBN: (纸本)9781665485845

For acute stroke patients, time to recognize the stroke symptom onset is crucial for the lifesaving treatment. The automatic detection of stroke signs has been increasingly developed for practical use. The better timely classification results could allow better detection of the symptoms and avoid morbidity and mortality. In this study, we proposed using cosine similarity between the left and right sides of the face as a part of features for classifying the stroke elderly patients from healthy elderly participants. We employed our method on images from the Toronto NeuroFace dataset. The results showed high classification accuracy (the average accuracy of 97.8998% from 6 classification methods). These results indicate that the cosine similarity features can be useful to detect facial asymmetry and pose very promising potential for elderly stroke detection. © 2022 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Permanent Magnet Shape Optimization Method for PMSM Air Gap Flux Density Harmonics Reduction

引用

CES Transactions on Electrical Machines and Systems 2021年第4期5卷 284-290页

作者： Chengsi Liu Yongxiang Xu Jibin Zou Guodong Yu Liang Zhuo School of Electrical Engineering and Automation of HIT Department of Electrical Engineering Harbin Institute of Technology the State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin Institute of Technology and National Engineering Research Center for Small and Special Precision Motors Guizhou Aerospace Linquan Motor Co.Ltd

This paper proposed a permanent magnet optimization method to suppress the air gap flux density harmonic of permanent magnet synchronous motor(PMSM).The method corrected the effective air gap length of the motor,calculated the magnetization length of the permanent in the case of parallel magnetization,and took the influence of the permanent magnet relative permeability into *** on these works,for a given sinusoidal air gap flux density waveform,the corresponding structural parameters can be calculated,so as to achieve the optimization of the permanent *** using this method to optimize the shape of the magnet,the fundamental wave of the air gap flux density can be retained to the greatest extent,so as to eliminate harmonics and maintain the output capacity at the same *** feasibility and accuracy of the method have been verified by finite element analysis(FEA)and prototype machine *** method is simple and time-saving,and has a satisfactory accuracy,which provides a reference method for permanent magnet optimization of PMSM.

关键词： Permanent magnet synchronous motor(PMSM) analytical method finite element analysis(FEA) magnet shape optimization.

来源：评论

学校读者我要写书评

暂无评论

Implementing Machine Learning Approaches to Identify Fabricated Profiles

Implementing Machine Learning Approaches to Identify Fabrica...

引用

Science, Technology, engineering and Management (ICSTEM), International Conference on

作者： George Princess T Kothai G Heartlin Maria H Kayalvizhi Rajadurai Ajai MR Department of ADS St. Joseph's Institute of Technology Chennai India Department of CSE (Artificial Intelligence and Machine Learning) KPR Institute of Engineering and Technology Coimbatore Department of ECE Rajalakshmi Engineering College Chennai India Dept.of Robotics and Automation Easwari Engineering College Chennai India Department of IT St. Joseph's Institute of Technology Chennai India

ISBN: (数字)9798350376913

ISBN: (纸本)9798350388473

The increase of fake news is a serious challenge in today's digital world. During the period of COVID-19 there is a lot of fake news about the COVID-19 virus has been spreading around the world, and it has also been believed among a lot of people, so a lot of conspiracy theories about the virus-like has been intentionally spread by the laboratory and some news is about supporting the zoonotic origin of the virus, likely originating from bats. Some of the news is about False Cures and Treatments, There were various claims about supposed cures for COVID-19, such as drinking bleach, consuming certain herbs, or taking specific vitamins. Health experts and authorities consistently warned against such unproven remedies. Thus it is really necessary to differentiate the fake profile from the genuine profile. This fake news is mostly spread through fake profiles. So it is necessary to differentiate fake profiles from genuine users. This paper introduces a method for the detection of fake profiles using machine learning techniques. The proposed system uses a diversity of features, to distinguish genuine profiles from fake. A dataset is employed to train and evaluate the machine learning algorithm. This dataset includes labeled examples of both pseudo (fake) and real profiles. This paper aims to increase the efficiency in the detection of genuine news from fake. This proposed system mainly focuses on stopping the spread of malicious activities through out the internet, since these activities is mostly spread through the fake account on the social media platforms..

关键词： COVID-19 Machine learning algorithms Social networking (online) Supervised learning Focusing Machine learning Forestry

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：