检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Shi, Hao Wang, Song Zhang, Jiaming Yin, Xiaoting Wang, Zhongdao Wang, Guangming Zhu, Jianke Yang, Kailun Wang, Kaiwei The State Key Laboratory of Extreme Photonics and Instrumentation The National Engineering Research Center of Optical Instrumentation Zhejiang University Hangzhou310027 China The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The College of Computer Science and Technology Zhejiang University Hangzhou310027 China The Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe76131 Germany Huawei Noah’s Ark Lab. Canada The Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom

Vision-based occupancy prediction, also known as 3D Semantic Scene Completion (SSC), presents a significant challenge in computer vision. Previous methods, confined to onboard processing, struggle with simultaneous geometric and semantic estimation, continuity across varying viewpoints, and single-view occlusion. Our paper introduces OccFiner, a novel offboard framework designed to enhance the accuracy of vision-based occupancy predictions. OccFiner operates in two hybrid phases: 1) a multi-to-multi local propagation network that implicitly aligns and processes multiple local frames for correcting onboard model errors and consistently enhancing occupancy accuracy across all distances. 2) the region-centric global propagation, focuses on refining labels using explicit multi-view geometry and integrating sensor bias, especially to increase the accuracy of distant occupied voxels. Extensive experiments demonstrate that OccFiner improves both geometric and semantic accuracy across various types of coarse occupancy, setting a new state-of-the-art performance on the SemanticKITTI dataset. Notably, OccFiner elevates vision-based SSC models to a level even surpassing that of LiDAR-based onboard SSC models. Furthermore, OccFiner is the first to achieve automatic annotation of SSC in a purely vision-based approach. Quantitative experiments prove that OccFiner successfully facilitates occupancy data loop-closure in autonomous driving. Additionally, we quantitatively and qualitatively validate the superiority of the offboard approach on city-level SSC static maps. The source code will be made publicly available at https://***/MasterHow/OccFiner. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Influence of the pyrolysis of benzotriazole passivator on the characteristics of dissolved gas in the insulating oil 7

Influence of the pyrolysis of benzotriazole passivator on th...

引用

7th IEEE International Conference on High Voltage Engineering and Application, ICHVE 2020

作者： Gao, Sihang Li, Jiajun Ke, Tingjing Liu, Yang Ding, Dong Key Laboratory of Industrial Internet of Things and Networked Control Ministry of Education Chongqing University of Posts and Telecommunications Chongqing China State Grid Chongqing Electric Power Company Chongqing Chongqing China Baoding Electric Power Corporation Baoding China

ISBN: (纸本)9781728155111

Insulation failures of oil-immersed power transformer induced by sulfur corrosion can be controlled by adding the metal passivator into insulating oil. However, it has been reported that the addition of benzotriazole and its derivative passivators into insulating oil would cause abnormal generation of dissolved gases in the oil during the operation of oil-immersed transformer. Therefore, this paper investigated on the effect of passivator on the characteristics of dissolved gas in the oil under the action of thermal field. Benzotriazole (BTA) that widely used in the oil-immersed transformer was selected as the research object, the thermogravimetric analysis of BTA was conducted, and a series of accelerate thermal ageing experiments of oil-paper insulation with and without BTA were also conducted, the composition and content of dissolved gases in oil were measured and analyzed. The results show that BTA was pyrolyzed continuously as the temperature increase. The addition of BTA in oil accelerated the contents of H2, CO and CO2 and decelerated the content of hydrocarbon gases, which lead to abnormal generation of dissolved gases in oil. All of these may interfere the operation condition evaluation of oil-immersed transformer based on DGA technology. © 2020 IEEE.

关键词： Thermogravimetric analysis

来源：评论

学校读者我要写书评

暂无评论

Development of micro-and nanorobotics: A review

引用

Science China(Technological Sciences) 2019年第1期62卷 1-20页

作者： YANG Jia ZHANG Chuang WANG XiaoDong WANG WenXue XI Ning LIU LianQing State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Emerging Technologies Institute Department of Industrial & Manufacturing Systems Engineering University of Hong Kong

Micro-and nanorobotic is an emerging field of research arising from the cross-fusion of micro/nano technology and robotics and has become an important part of robotics. Micro-and nanorobots have the advantages of small size, low weight, large thrust-toweight ratio, high flexibility, and high sensitivity. Due to the characteristics distinguishing from macroscopic robots, micro-and nanorobots have stimulated the research interest of the scientific community and opened up numerous application fields such as drug delivery and disease diagnosis. In the past 30 years, research on micro-and nanorobots has made considerable *** article provides a comprehensive overview of the development of these robots. First, the application of the robots is reviewed. Then, the key components of the robots are discussed separately, covering their actuation, design, fabrication and control. In addition, from the perspectives of intelligence and sensing, clinical applications, materials and performance, the challenges that may be encountered in the development of such robots in the future are discussed. Finally, the entire article is summarized, and concepts for future micro-and nanorobots are described.

关键词： micro-and nanorobots magnetic actuation manipulation biohybrid robot

来源：评论

学校读者我要写书评

暂无评论

Information Modeling and Verification Method for Edge Computing of Power Internet of Things

Information Modeling and Verification Method for Edge Comput...

引用

IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC)

作者： Dawei Li Xiaolu Chen Chunhe Song Shimao Yu Start Grid Shanghai Information & Telecommunication Company Shanghai China 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 Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (数字)9781728152448

ISBN: (纸本)9781728152455

There are various types of power Internet of Things terminals, and a unified edge-side information fusion model is the basis of data unification. This article describes the unified modeling method of power Internet of Things terminal information, and describes the construction method of the Internet of Things terminal information model from three aspects: attribute, message and service. Combined with the characteristics of the electric power Internet of Things information model, a model verification method is given. Finally, through the terminal data on the edge side of the power Internet of Things, the feasibility and effectiveness of the model verification method are verified.

关键词： Analytical models Computational modeling Data models Power systems Internet of Things Information technology Edge computing

来源：评论

学校读者我要写书评

暂无评论

Distributed computing framework of intelligent sensor network for electric power internet of things

Distributed computing framework of intelligent sensor networ...

引用

IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC)

作者： Dawei Li Ruimo Yu Chunhe Song Shu Li Gengtao Jia Xiaoli Zhou Start Grid Shanghai Information & Telecommunication Company Shanghai China 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 Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China

ISBN: (数字)9781728152448

ISBN: (纸本)9781728152455

The power IoT terminal environment is complex, and current smart sensor sensors have problems such as poor networking capabilities and large processing delays, and few specific edge-side automatic networking capabilities. This paper analyzes and elaborates the distributed intelligent sensor computing framework from the perspective of edge intelligent networking, designs a computing model for intelligent sensors of power Internet of Things terminals, and gives the edge-based deployment of convolutional neural network architecture, data aggregation, model training, and intelligent reasoning. Finally, the validity of the proposed framework model is verified by public sample data.

关键词： Training Analytical models Computational modeling Data aggregation Data models Internet of Things Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

GenMapping: Unleashing the Potential of Inverse Perspective Mapping for Robust Online HD Map Construction

arXiv

引用

arXiv 2024年

作者： Li, Siyu Yang, Kailun Shi, Hao Wang, Song Yao, You Li, Zhiyong The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China The College of Computer Science Zhejiang University Hangzhou310027 China Shanghai Supremind Technology Company Ltd. Shanghai201210 China The USC Viterbi School of Engineering The University of Southern California Los AngelesCA90089 United States

Online High-Definition (HD) maps have emerged as the preferred option for autonomous driving, overshadowing the counterpart offline HD maps due to flexible update capability and lower maintenance costs. However, contemporary online HD map models embed parameters of visual sensors into training, resulting in a significant decrease in generalization performance when applied to visual sensors with different parameters. Inspired by the inherent potential of Inverse Perspective Mapping (IPM), where camera parameters are decoupled from the training process, we have designed a universal map generation framework, GenMapping. The framework is established with a triadic synergy architecture, including principal and dual auxiliary branches. When faced with a coarse road image with local distortion translated via IPM, the principal branch learns robust global features under the state space models. The two auxiliary branches are a dense perspective branch and a sparse prior branch. The former exploits the correlation information between static and moving objects, whereas the latter introduces the prior knowledge of OpenStreetMap (OSM). The triple-enhanced merging module is crafted to synergistically integrate the unique spatial features from all three branches. To further improve generalization capabilities, a Cross-View Map Learning (CVML) scheme is leveraged to realize joint learning within the common space. Additionally, a Bidirectional Data Augmentation (BiDA) module is introduced to mitigate reliance on datasets concurrently. A thorough array of experimental results shows that the proposed model surpasses current state-of-the-art methods in both semantic mapping and vectorized mapping, while also maintaining a rapid inference speed. Moreover, in cross-dataset experiments, the generalization of semantic mapping is improved by 17.3% in mIoU, while vectorized mapping is improved by 12.1% in mAP. The source code will be publicly available at https://***/lynn-yu/GenMappin

关键词： Photomapping

来源：评论

学校读者我要写书评

暂无评论

Advanced Robot Programming: a Review

引用

Current robotics Reports 2020年第4期1卷 251-258页

作者： Zhou, Zhongxiang Xiong, Rong Wang, Yue Zhang, Jiafan State Key Laboratory of Industrial Control Technology and Institute of Cyber-Systems and Control of Zhejiang Province Zhejiang University Hangzhou China Research Center China Robotics and Discrete Automation ABB Shanghai China

The review presents an overview of advanced robot programming approaches which aims to ease robot programming and speed up the deployment of industrial robots, and then some considerations are shared with respect to requirements in new trends of manufacturing. The new trend of customization along with Industry 4.0 is appearing which is a challenge for robotized systems. The bottleneck is mainly the efficiency of deployment of industrial robots because traditional programming methods are not intuitive and always time-consuming. Advanced robot programming techniques are expected to ease robot programming and make it accessible for non-experts. A review on advanced robot programming is here presented, firstly introducing the background of this research, followed by reviewing literatures in four categories: programming by demonstration for low-level motion, programming by demonstration for high-level task, speech recognition-based and augmented reality-based programming approaches, and finishing on discussing future works.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel IMU-Based 6-DOF Pose Tracking Method for Parallel-Mechanism-Based Ultrasound Robot

A Novel IMU-Based 6-DOF Pose Tracking Method for Parallel-Me...

引用

IEEE International Conference on Mechatronics and Automation

作者： Zhaokun Deng Xilong Hou Pengcheng Zhang Mingrui Hao Chen Chen Shuangyi Wang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences 95 Zhongguancun East Road Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences 19 Yuquan Road Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong Science Park Hong Kong China

Parallel-mechanism-based ultrasound robots bring the benefits of convenient robot-assisted remote ultrasound or automated scanning. During the use of this type of robot, accurate tracking and feedback of 6-DOF posture are critical for potential intelligent control and real-time navigation. However, this presents significant challenges due to the complex forward kinematics and environmental changes, making it difficult to apply in practical settings. To address this issue, we propose a novel 6-DOF pose tracking method based on an inertial measurement unit. This method directly senses the orientation and calculates the position using the intrinsic structural and kinematic characteristics of the parallel mechanisms. Therefore, it is possible to solve all posture information by only partial posture information. We conducted both simulation and physical experiments to evaluate effectiveness and robustness of the proposed method. The maximal tracking errors for the physical experiments are within the 2 mm and 0.6.°. The experimental results show promising performance, demonstrating the method’s potential for practical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Quality Evaluation of Academic Papers in Carbon Capture, Utilization, and Storage

The Quality Evaluation of Academic Papers in Carbon Capture,...

引用

Machine Learning, control, and robotics (MLCR), International Conference on

作者： Hangyue Zhang Jie Bai School of Computer Science and Technology Sun Yat-sen University Guangzhou P. R. China City State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing P. R. China

ISBN: (纸本)9781665454605

Carbon capture, utilization, and storage (CCUS) technology is a research hotspot worldwide owing to global climate change and warm gas control. CCUS papers from the last twenty years, derived from the Web of Science database, were analyzed to investigate the impact and citation of academic papers using machine learning methods. Firstly, nine author characteristics, keywords, and three other categories were extracted from the literature. Then, the natural logarithm distribution of the annual average number of citations was obtained, and five evaluation grades were decided based on the citations. Next, the keyword evolution of papers in the CCUS field is analyzed, and a model on the keyword evolution trend index is proposed. Data integration and imbalance processing were conducted after random sampling. A citation prediction model was proposed to evaluate the quality of CCUS academic papers and was verified on the recent five years' CCUS papers by comparing it with nine other mainstream machine learning models. The results indicate that the random forest model exhibits the best performance, with an accuracy rate reaching 88.7%; an ablation experiment was also conducted using the same algorithm. The results prove the effectiveness of our proposed method, shedding light on the quality of academic papers and technology development in CCUS.

关键词： Machine learning Climate change Random forests Modeling Energy storage

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Differential Kinematics and Machine Learning Approaches in Motion Planning for Intra-operative Cardiac Ultrasound Robots

A Comparison of Differential Kinematics and Machine Learning...

引用

IEEE International Conference on Mechatronics and Automation

作者： Haichuan Lin Yiping Xie Xilong Hou Chen Chen Shuangyi Wang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences 95 Zhongguancun East Road Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences 19 Yuquan Road Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong Science Park Hong Kong China

Intra-operative cardiac ultrasound robots are emerging as a new tool to assist in cardiac interventional procedures to improve the efficiency of the procedure and reduce the operator’s experience. These robots are often based on a continuum mechanism to achieve end position changes. The central issue for the control of these robots is motion planning. With its flexibility, machine learning-based approaches may provide new ideas for this type of problem compared to traditional differential kinematics, although related research is limited. In this paper, we present specific approaches to achieve the corresponding tasks by differential kinematics, supervised learning and reinforcement learning for specific motion planning problems, and thus analyze the feasibility of different approaches and compare their performance. The results show that differential kinematics is able to perform the best considering all tasks, while both supervised learning and reinforcement learning methods can also accomplish the intended task within a certain error range and with different characteristics. To conclude, the work lays the foundation for further flexibility in solving more complex tasks in motion planning using the combination of conventional kinematics and machine learning-based methods.

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：