检索结果-内蒙古大学图书馆

Dynamic Movement Primitives Based robot Skills Learning

Machine Intelligence Research 2023年第3期20卷 396-407页

作者： Ling-Huan Kong Wei He Wen-Shi Chen Hui Zhang Yao-Nan Wang School of Intelligence Science and Technology University of Science and Technology BeijingBeijing 100083China Institute of Artificial Intelligence University of Science and Technology BeijingBeijing 100083China School of Robotics and the National Engineering Laboratory of Robot Visual Perception and Control Technology Hunan UniversityChangsha 410082China

In this article,a robot skills learning framework is developed,which considers both motion modeling and *** order to enable the robot to learn skills from demonstrations,a learning method called dynamic movement primitives(DMPs)is introduced to model motion.A staged teaching strategy is integrated into DMPs frameworks to enhance the generality such that the complicated tasks can be also performed for multi-joint *** DMP connection method is used to make an accurate and smooth transition in position and velocity space to connect complex motion *** addition,motions are categorized into different goals and *** is worth mentioning that an adaptive neural networks(NNs)control method is proposed to achieve highly accurate trajectory tracking and to ensure the performance of action execution,which is beneficial to the improvement of reliability of the skills learning *** experiment test on the Baxter robot verifies the effectiveness of the proposed method.

关键词： Dynamic movement primitives(DMPs) trajectory tracking control robot learning from demonstrations neural networks(NNs) adaptive control

来源：评论

学校读者我要写书评

暂无评论

An insulator feature-enhanced segmentation method based on the residual-type attention mechanism 5

An insulator feature-enhanced segmentation method based on t...

引用

5th IEEE Advanced Information Management, Communicates, Electronic and Automation control Conference, IMCEC 2022

作者： Tang, Xin Mao, Jianxu Yi, Junfei Tao, Ziming He, Zhenyu College of Electrical and Information Engineering Hunan University Changsha China National Engineering Research Center for Robot Vision Perception and Control Technology Changsha China

ISBN: (纸本)9781665479677

As an crucial component of power line, the timely check for the state of insulator is necessary for the normal running of transmission lines. In view of debasement of insulator segmentation accuracy in current transmission line caused by complex background, low contrast, and the quality of images is not guaranteed, we improve U-Net by combining attention mechanism and residual connection. Residual connection is added to the encoder part to improve the extraction of low-level semantic information, and the attention mechanism is added to the decoder part for integrating high and low level features better and reduce the error between them. We confirm the effectiveness of the improved module through experiments, while the results showing that the improved U-Net model segmentation performance on insulator dataset is improved from 0.875 to 0.912. And our method also outperforms previous segmentation work on insulator dataset. © 2022 IEEE.

关键词： Electric lines

来源：评论

学校读者我要写书评

暂无评论

Power Grid Fastener Defect Detection Based on Dual Context Information Fusion 5

Power Grid Fastener Defect Detection Based on Dual Context I...

引用

5th IEEE Advanced Information Management, Communicates, Electronic and Automation control Conference, IMCEC 2022

作者： Qingxian, Liu Jianxu, Mao Junfei, Yi Ziming, Tao Junlong, Yu College of Electrical and Information Engineering Hunan University Changsha China National Engineering Research Center for Robot Vision Perception and Control Technology Changsha China

ISBN: (纸本)9781665479677

The working state of fasteners is closely related to the safe and stable operation of the power grid. However, the performance of the existing fastener defect detection models is not enough to meet the requirements, because the size of object is small, the environment is complex, the sample size is unbalanced and so on. Therefore, we design a simple but effective feature fusion method, called Double Context Information Enhancement Module. The model can fully learn the features of fasteners by expanding the receptive field of the feature map during the construction of the feature pyramid, and the feature expression ability of fasteners can be enhanced by learning the features of adjacent layers after the construction of the feature pyramid. Through experiments, we proved that DCEM can improve about 8.8AP compared with the original model, and at the same time, the effectiveness and advancement of DCEM are proved by comparing with SOTA. © 2022 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Admittance Based robot Force control Framework for Server Board Assembly 25

Admittance Based Robot Force Control Framework for Server Bo...

引用

25th IEEE International Conference on Industrial technology, ICIT 2024

作者： Ma, Yunlong Wang, Yaonan Jiang, Yiming Zhou, Xianen Zhu, Ge Zhu, Qing Institute of Artificial Intelligence University of Science and Technology Beijing Beijing China Xiangjiang Laboratory Hunan China College of Electrical and Information Engineering Hunan University Changsha China School of Robotics Hunan University Changsha China National Engineering Research Center for Robot Vision Perception and Control Technology Hunan University Changsha China ZTE Corporation Shenzhen China

In server board assembly tasks, the effect of vision-based robot assembly schemes is not ideal due to the small installation gap and the blocking of vision. Adding force sensors and force controllers can be a good solution to the above problems and increase the flexibility in the assembly process. In this paper, we propose a force control strategy applied to a server board assembly task. The method is divided into two main parts. In the first part, the zero offset of the force sensor and the load gravity are calibrated and compensated, so that the external force on the load is accurately obtained. In the second part, the admittance controller is designed to achieve compliant behavior between the robot and the environment. Finally, the experimental verification of the board insertion is carried out on the experimental platform. Experimental results verify the effectiveness and practicability of the proposed method. © 2024 IEEE.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Tackling Real-world Complexity: Hierarchical Modeling and Dynamic Prompting for Multimodal Long Document Classification

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5776-5790页

作者： Liu, Tengfei Hu, Yongli Li, Mingjie Yi, Junfei Chang, Xiaojun Gao, Junbin Yin, Baocai Beijing University of Technology Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence School of Information Science and Technology Beijing100124 China Stanford University Department of Radiation Oncology StanfordCA94305 United States Hunan University National Engineering Laboratory of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha410082 China University of Technology Sydney ReLER Laboratory Australian Artificial Intelligence Institute Faculty of Engineering and Information Technology UltimoNSW2007 Australia The University of Sydney Business School The University of Sydney Discipline of Business Analytics CamperdownNSW2006 Australia

With the rapid growth of internet content, multimodal long document data has become increasingly prominent, drawing significant attention from researchers. However, most existing methods primarily focus on scenarios where all modalities are present, often overlooking more challenging and realistic cases involving missing image modality. To address this limitation, we propose a robust multimodal long document classification (MLDC) framework that integrates hierarchical modeling and dynamic prompting to handle complex multimodal long document data. Our approach begins by leveraging hierarchical modeling combined with an Adaptive Correlation Multimodal Transformer (ACMT) to effectively capture relationships between text and images at both section and sentence levels. We also introduce a Dynamic Prompt Generation (DPG) module at both levels to enhance the model's robustness in handling missing image data. By evaluating sample uncertainty, the DPG module dynamically adjusts both the number of prompts and the prompts themselves, allowing the model to better adapt to the varying needs of different samples. Finally, a Hierarchical Heterogeneous Graph (HHG) is introduced to enhance feature interactions across levels, further improving the coherence and accuracy of the model. Extensive experiments on four multi-modal long document datasets demonstrate that our model shows superior performance compared to existing state-of-the-art MLDC classification methods in various conditions. © 1991-2012 IEEE.

关键词： Adaptation models Transformers Data models Correlation Circuits and systems Electronic mail Robustness Uncertainty Training Complexity theory

来源：评论

学校读者我要写书评

暂无评论

An Efficient Generative Intelligent Multiobjective Grasping Model for Kitchen Waste Sorting

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Deng, Songyun Pei, Ruiyuan Zhou, Li Qin, Hai Sun, Wei Liang, Qiaokang Hunan University College of Electrical and Information Engineering Changsha410082 China Hunan University National Engineering Laboratory for Robot Vision Perception and Control College of Electrical and Information Engineering Changsha410082 China

The key challenge in automated kitchen waste sorting on conveyor belts is how robots execute grasping tasks. Current methods, dependent on object detection, struggle to adopt generative architectures due to data scarcity and algorithmic inefficiency. To solve these issues, this article proposes solutions in three aspects: dataset construction, annotation data processing, and generative model lightweighting. First, we built the KWG2024 dataset, which includes 3116 RGB-D images, 18231 standard annotations, and three new evaluation metrics. Second, we proposed two novel annotation processing methods to address the issue of excessive and incorrect grasps generated by generative networks in single-attempt grasp planning of multiobjects. Third, we constructed an efficient network with classification capabilities, AMI-LiteNet, by integrating the advantages of PP-LiteSeg and AMI-NanoNet. On the public Cornell dataset, AMI-LiteNet achieved a grasping accuracy of 98.3% and an efficiency of 118 frames per second (FPS). In extensive comparative experiments on KWG2024, our model reached a leading computational efficiency compared with recent state-of-the-art methods. It acquired a grasp planning generation accuracy of 87.96% while only requiring a computational effort of 2.79 GFLOPs. Finally, our model was deployed on an edge computing device and achieved a maximum grasping accuracy of 90.91% and a classification accuracy (CA) of 97.48% in our actual robotic system. To our knowledge, this is the first time that a generative grasp method has been applied independently to kitchen waste sorting tasks on a conveyor belt. © 1963-2012 IEEE.

关键词： Belt conveyors

来源：评论

学校读者我要写书评

暂无评论

High Dynamic Range 3d Measurement with Adaptive Projection Pattern Generated from Saturated Image

SSRN

引用

SSRN 2024年

作者： Yu, Hongshan Liang, Xianqiang Yu, Ruiming Xu, Haiqiang Sun, Wei National Engineering Laboratory for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan University Changsha China

Fringe projection profilometry (FPP) shows the advantages of high efficiency and high accuracy in distance sensing. However, it is prone to measurement errors due to fringe saturation in high dynamic range (HDR) scenes. Popular adjust projection intensity (API) based FPP methods have been proposed to reduce the influence of reflectivity variance. Because existing API based FPP method depend on unsaturated images to generate adaptive projection patterns, its measurement time is increased. In this paper, we propose a high dynamic range 3D measurement method with adaptive projection pattern generated from saturated image. Firstly, we establish the reflectance relationship between unsaturated region and saturated region to compute adaptive projection intensity, which removes the dependence of unsaturated images. Secondly, we improve measurement efficiency in computation process by recycling the captured images. In addition, we propose a capture intensity correction method to remove the effect of light propagation distance. Experiments prove that the proposed method has significant advantages in a variety of HDR scenes. Compared with linear-API method, proposed method improves the measurement accuracy by 15.59%. Meanwhile, the number of projection patterns is reduced by 40% compared to the method which based on multiple exposure fusion image (MEFI). © 2024, The Authors. All rights reserved.

关键词： Reflection

来源：评论

学校读者我要写书评

暂无评论

Boundary Gap Based Reactive Navigation in Unknown Environments

引用

IEEE/CAA Journal of Automatica Sinica 2021年第2期8卷 468-477页

作者： Zhao Gao Jiahu Qin Shuai Wang Yaonan Wang the Department of Automation University of Science and Technology of ChinaHefei 230027China the College of Electrical and Information Engineering Hunan UniversityChangsha 410082 the National Engineering Laboratory for Robot Visual Perception and Control Technology Changsha 410082China

Due to the requirements for mobile robots to search or rescue in unknown environments,reactive navigation which plays an essential role in these applications has attracted increasing ***,most existing reactive methods are vulnerable to local minima in the absence of prior knowledge about the *** paper aims to address the local minimum problem by employing the proposed boundary gap(BG)based reactive navigation ***,the narrowest gap extraction algorithm(NGEA)is proposed to eliminate the improper ***,we present a new concept called boundary gap which enables the robot to follow the obstacle boundary and then get rid of local ***,in order to enhance the smoothness of generated trajectories,we take the robot dynamics into consideration by using the modified dynamic window approach(DWA).Simulation and experimental results show the superiority of our method in avoiding local minima and improving the smoothness.

关键词： Boundary gap local minima reactive navigation unknown environments

来源：评论

学校读者我要写书评

暂无评论

NCV-PWM Method for the Phase Current Reconstruction With DC Link Single Sensor

NCV-PWM Method for the Phase Current Reconstruction With DC ...

引用

作者： Shen, Yongpeng Wu, Kexuan Yuan, Xiaofang Wu, Chengzhong Liang, Weihua Chen, Zhiwei The College of Electric and Information Engineering Zhengzhou University of Light Industry Zhengzhou450002 China The Department of Electric and Information Engineering Hunan University Changsha410082 China The National Engineering Laboratory for Robot Visual Perception and Control Technology Hunan University Changsha410082 China

The DC link current sampling with a single sensor is a promising solution in the electric drive field due to its low cost and small volume. However, limited by the minimum sampling time, the current reconstruction unobservable area is the most intractable challenge in the traditional single sensor reconstruction method, especially in sector boundary areas, where the phase current cannot be reconstructed completely. In this article, a new non-zero compensation vector pulse width modulation (NCV-PWM) method is proposed to eliminate the current unobservable area. Firstly, by introducing the definition of minimum sampling time, the voltage space vector plane is accurately divided into different modulation areas. Then, by applying non-zero compensation vector in the sector boundary, the current sampling window is extended, and the sampling time requirement for the DC link current is satisfied. Finally, the practicability and accuracy of the NCV-PWM method are verified by experiments, and results show that the current reconstruction error is less than 2.86%, which provides accurate current feedback for high-performance motor control. © 2023 IEEE.

关键词： Electric drives

来源：评论

学校读者我要写书评

暂无评论

Binocular vision System for Measuring the Height of control Rod Drive Rod in Nuclear Reactor 42

Binocular Vision System for Measuring the Height of Control ...

引用

42nd Chinese control Conference, CCC 2023

作者： Zhou, Xianen Wen, Yingjian Zhu, Qing Wang, Yaonan Sun, Feixiang Chen, Shaonan Hunan University National Engineering Research Center for Robot Vision Perception and Control Technology China Jiangxi Communication Terminal Industry Technology Research Institute Co. Ltd. China University of Electronic Science and Technology of China China China Nuclear Power Technology Research Institute Co. Ltd. China

ISBN: (纸本)9789887581543

Nuclear energy is widely recognized as an important source to meet the increasing energy demand in the future. However, since the occurrence of the Fukushima accident, its potential safety hazards have been strongly concerned by the public, and has become one of the most significant problems to be solved at this stage. In this paper, a vision inspection system with support detection scheme based on RGB-D fusion is proposed to achieve accurate detection of the control rod position for the potential danger in the decoupling process of the control rod drive mechanism. In order to separate the depth region containing the relevant information of the driving rod head, the ellipse region of the top ring of the driving rod is detected from the color image by the method based on line segment extraction and region of interest detection. Due to the smoothness and reflection of the surface of the control rod, part of the depth of the head of the control rod is lost. In order to predict the reference distance between the top value of the control rod and the camera, a center point filling method based on multi-direction linear regression in gradient stage is designed. In order to evaluate the effectiveness of the proposed method, a series of experiments are carried out on the head location and depth calculation of the drive rod. The results show that the vision inspection system in this paper can achieve high-precision positioning of the control rod. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Template matching

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：