检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

403 篇 会议
121 篇 期刊文献
2 册 图书

馆藏范围

526 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

297 篇 工学
- 151 篇 计算机科学与技术...
- 131 篇 软件工程
- 125 篇 控制科学与工程
- 83 篇 机械工程
- 52 篇 信息与通信工程
- 46 篇 仪器科学与技术
- 32 篇 生物医学工程（可授...
- 31 篇 光学工程
- 29 篇 电气工程
- 26 篇 生物工程
- 19 篇 电子科学与技术（可...
- 14 篇 力学（可授工学、理...
- 12 篇 土木工程
- 10 篇 建筑学
- 10 篇 交通运输工程
- 8 篇 材料科学与工程（可...
- 8 篇 安全科学与工程
- 7 篇 动力工程及工程热...
122 篇 理学
- 59 篇 数学
- 51 篇 物理学
- 22 篇 生物学
- 21 篇 统计学（可授理学、...
- 11 篇 系统科学
67 篇 管理学
- 48 篇 管理科学与工程(可...
- 22 篇 图书情报与档案管...
- 12 篇 工商管理
30 篇 医学
- 23 篇 临床医学
- 15 篇 基础医学(可授医学...
- 11 篇 药学(可授医学、理...
7 篇 经济学
- 7 篇 应用经济学
4 篇 教育学
3 篇 法学
1 篇 农学
1 篇 艺术学

主题

32 篇 feature extracti...
26 篇 training
22 篇 accuracy
21 篇 robots
18 篇 semantics
17 篇 cameras
14 篇 real-time system...
12 篇 three-dimensiona...
12 篇 robustness
11 篇 force
11 篇 optimization
11 篇 computational mo...
11 篇 robot sensing sy...
11 篇 visualization
11 篇 trajectory
11 篇 sensors
10 篇 convolution
10 篇 mathematical mod...
9 篇 vehicle dynamics
9 篇 object detection

机构

279 篇 faculty of robot...
86 篇 college of infor...
59 篇 northeastern uni...
20 篇 multi-robot syst...
18 篇 graduate school ...
16 篇 state key labora...
14 篇 foshan graduate ...
13 篇 faculty of engin...
12 篇 the faculty of r...
12 篇 department of mo...
11 篇 siasun robot & a...
11 篇 school of creati...
10 篇 liaoning disable...
9 篇 faculty of engin...
8 篇 shenyang institu...
8 篇 key laboratory o...
7 篇 global robot aca...
7 篇 national frontie...
7 篇 faculty of scien...
6 篇 faculty of engin...

作者

60 篇 chengdong wu
38 篇 fei wang
27 篇 fang zheng
22 篇 xiaosheng yu
22 篇 wang fei
20 篇 omar m. shehata
17 篇 zheng fang
17 篇 zixi jia
15 篇 wu chengdong
15 篇 jianning chi
14 篇 cui yubo
14 篇 lijin fang
14 篇 yu xiaosheng
14 篇 elsayed i. morga...
12 篇 shiguang wen
12 篇 yang jiang
12 篇 chu hao
11 篇 li zhiheng
10 篇 junyi wang
10 篇 fang lijin

语言

504 篇 英文
19 篇 其他
3 篇 中文
1 篇 日文

检索条件"机构=Faculty of Robot Science and Engineering"

共 526 条记录，以下是21-30 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Human Target Detection and Tracking Algorithm Based on Improved YOLOv7 13

Human Target Detection and Tracking Algorithm Based on Impro...

引用

13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023

作者： Min, Yuyao Shui, Jiayi Liu, Shiyu Wang, Junyi Guo, Zexin Northeastern University Department of Faculty of Robot Science and Engineering Shenyang China

ISBN: (纸本)9798350315196

Recently, human-oriented target tracking has broad application prospects in various practical fields, such as medicine and security. YOLOv7 is a powerful detection algorithm in the current main-stream, and it still has room for development in terms of detection accuracy. To handle the issue of mobile robots struggling to maintain recognition precision and stability in complicated scenes, we propose an improved target detection network for YOLOv7. Firstly, based on YOLOv7-tiny network structure, the CBAM attention mechanism is introduced into the bottom of the backbone network, and the SPPCSP module is adopted to reduce the computation of the feature map, which could enhance the network's representational capability. Then, the KCF algorithm is incorporated into the model, which could track the human target after determining its position with respect to the robot with the RGB-D camera. In order to ensure the flexibility of the robot, the Jetson Nano is utilized as the processor. Finally, we conduct human target tracking experiments for the mobile robot in a realistic scenario. The experimental results show that the mAP reaches 91.17%, which is 1.88% higher than only using YOLOv7 after introducing the CBAM module. © 2023 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Dynamic 3D Path Planning for UAV Based on Enhanced Grey Wolf Optimization Algorithm 3rd

Dynamic 3D Path Planning for UAV Based on Enhanced Grey Wolf...

引用

3rd International Conference on Autonomous Unmanned Systems, ICAUS 2023

作者： Xu, Hongli Liu, Yubo Ru, Jingyu Faculty of Robot Science and Engineering Northeastern University Shenyang110169 China College of Information Science and Engineering Northeastern University Shenyang110819 China

ISBN: (纸本)9789819710904

The enhanced grey wolf optimization algorithm is proposed for the path planning problem of UAV in a multi-obstacle and dynamic obstacle environment. Firstly, the population is initialized by combining Tent chaos mapping, secondly, a differential evolution strategy is adopted for the leader grey wolf individuals, and finally, the enhanced grey wolf optimization algorithm and the artificial potential field method are fused to achieve the goal of avoiding dynamic obstacles. The results are tested under the dynamic obstacle model, and it is proved that the enhanced grey wolf optimization algorithm has excellent global search capability and better robustness under the complex environment. The method introduces innovative ideas to the domain of dynamic obstacle avoidance in path planning. © Beijing HIWING Scientific and Technological Information Institute 2024.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

A Face Super-Resolution Reconstruction Algorithm Based on Residual Estimation 14

A Face Super-Resolution Reconstruction Algorithm Based on Re...

引用

14th IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems, CYBER 2024

作者： Yu, Xiaosheng Liu, Guanglai Teng, Zi Li, Xiaoqiang Chen, Jubo Northeastern University Faculty of Robot Science and Engineering Liaoning Shenyang China College of Information Science and Engineering Northeastern University Liaoning Shenyang China

ISBN: (纸本)9798331506056

Face super resolution can greatly improve the performance of various facial analysis applications, such as face recognition and facial expression analysis. This paper introduces a facial super-resolution network model that utilizes residual estimation for enhancing image quality. The model engages a two-stage reconstruction process to generate super resolution face images, which effectively simplifies the learning complexities of the network. Moreover, the model incorporates prior facial information into the loss function to mitigate the influence of the background on the facial region within the image. This incorporation facilitates a more accurate reconstruction of super resolution facial images. The robustness and effectiveness of this facial super-resolution network based on residual estimation are evaluated through both quantitative and qualitative assessments, employing some classical facial image datasets. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge-guided nonlinear dynamic convolution network for lightweight semantic segmentation 2

Edge-guided nonlinear dynamic convolution network for lightw...

引用

2nd International Conference on Physics, Photonics, and Optical engineering, ICPPOE 2023

作者： Zhang, Chunyu Xu, Fang Wu, Chengdong Zhang, Chenghao Faculty of Robot Science and Engineering Northeastern University Shenyang China Shenyang Siasun Robot and Automation Company Ltd. Shenyang110168 China College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin China

ISBN: (纸本)9781510674684

As the demand for autonomous driving and robot vision arises, semantic segmentation has developed rapidly. Semantic segmentation provides the means for machines to understand the environment. However, current methods face a balance issue between segmentation quality and computational resources. Our proposed edge-guided non-linear dynamic convolutional network (ENNet) achieves real-time and accurate semantic segmentation. The core of our network is a novel non-linear, dynamic combination (Nd-conv) that allows for a non-linear, dynamic combination (Nd-conv) of multiple convolution weights, improving the convolution's encoding ability while maintaining a low computational burden. The Non-linear Dynamic Convolutional Modules (NDCM) is introduced to enhance the segmentation accuracy of the network while maintaining efficiency. The Multi-stage Feature Fusion Module (MFFM) is also introduced to fuse low-level details and high-level semantic information to improve the segmentation accuracy of the network. Experiments conducted on a 1080Ti GPU show that our model achieves 74.6 mIOU on the Cityscapes dataset while being able to perform inference at 202 FPS. Our network design has achieved an optimal balance between speed and accuracy. © COPYRIGHT 2024 SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Improving Teleoperation of High Degree-of-Freedom robots with a Dual-Mode System and Variable Admittance Controller Using IMU-Based Tracking 13

Improving Teleoperation of High Degree-of-Freedom Robots wit...

引用

13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023

作者： Lian, Siyi Wen, Shiguang Liu, Jing Wu, Qi Han, Lu Wang, Fei Northeastern University Faculty of Robot Science and Engineering Shenyang110169 China Northeastern University Faculty of Robot Science and Engineering Shenyang110819 China LiaoNing Disabled Persons' Service Center China

ISBN: (纸本)9798350315196

Admittance control allows for teleoperation with compliant performance by using external force signals driven by the operator. However, low-cost teleoperation solutions for high degree-of-freedom (DoF) robots using constant admittance controllers are mainly affected by the accuracy of sensors and jitter from operators, which can be avoided with cost-prohibitive solutions. We firstly propose a dual-mode teleoperation system with variable admittance controller and analysis the stability. To accurately track the operator's intention, an open-loop IMU-based method is designed. Our low-cost system enables operators to effectively perform complex tasks in the workspace by smoothly switching between two modes: an operating workspace to ensure teleoperation accuracy, and a moving workspace to improve efficiency of movement. We validate the proposed system through experiments using the UR5 robot in a controlled environment. Results show that our approach outperforms the constant admittance controller in terms of accuracy and efficiency. © 2023 IEEE.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Dynamic Event-triggered H∞ Sliding Mode Control for Multi-agent Systems Using a Dual Hidden Markov Model

Dynamic Event-triggered H∞ Sliding Mode Control for Multi-a...

引用

2024 China Automation Congress, CAC 2024

作者： Zheng, Ying Cui, Huixia Wang, Junyi College of Information Science and Engineering Northeastern University Shenyang China Faculty of Robot Science and Engineering Foshan Graduate School of Innovation Northeastern University Shenyang China

ISBN: (纸本)9798350368604

This paper investigates the dynamic event-triggered H∞ sliding mode control (SMC) issue for a class of linear multi-agent systems (MASs) with Markov jump parameters and Markov switching topologies. A mapping technique for continuous-time Markov chains is employed to address the challenge of MASs with dual Markov jumping process. Based on the hidden Markov model detector, the distributed event-triggered sliding mode controllers are constructed, and the dynamic event-triggering scheme (DETS) is introduced to reduce bandwidth pressure. By constructing mode-dependent Lyapunov-Krasovskii functionals (LKFs), the stochastic consensus conditions of MASs with prescribed performance index are formulated by linear matrix inequalities (LMIs). Finally, a numerical simulation is conducted to validate the effectiveness of the proposed method. © 2024 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Monocular Dynamic Object Detection with multi-modal fusion

Monocular Dynamic Object Detection with multi-modal fusion

引用

2024 lEEE International Conference on Advanced Information, Mechanical engineering, robotics and Automation, AIMERA 2024

作者： Li, Li Wan, Yingcai Peng, JiShen Liaoning Technical University Faculty of Electrical and Control Hu Ludao China Northeastern University Faculty of Robot Science and Engineering Shen Yang China

ISBN: (纸本)9798350343335

In the field of 3D scene understanding, object motion estimation holds great significance in handling dynamic scenes. To address this, This paper presents a novel method for rigid object motion segmentation from video, integrating multiple data modalities including imagery, optical flow, depth, scene flow, and camera ego-motion. Utilizing a motion filtering module, effectively removes background motion due to camera dynamics, while a motion extraction module accurately segments moving objects. The approach computes the objects' motion characteristics such as speed, direction, and position using a sophisticated fusion of 3D motion data. Validated on the KITTI dataset, our method demonstrates superior accuracy and robustness in dynamic environments. © 2024 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

robotic Grasp Detection Based on the Improved Light-weight ShuffleNet Model

Robotic Grasp Detection Based on the Improved Light-weight S...

引用

2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023

作者： Jiang, Yang Zhang, Xuejiao Zhao, Bin Northeastern University Faculty of Robot Science and Engineering Shenyang China Northeastern University College of Information Science and Engineering Shenyang China

ISBN: (纸本)9798350331790

To predict grasping configurations from RGB and aligned grasping object depth pictures, we propose improved ShuffleNet, an convolutional neural network that is accurate, real-time, and light-weight in this research. The new network adds attention mechanisms to the ShuffleNet. In the paper, it references Adan as the optimization function when training the network. Furthermore, after training and testing our network, it only has a 4% loss in picture identification in the five-parameter Cornell Grasping Dataset and the Jacquard Grasping Dataset, and the GPU inference speed is 7.1 frames per second (fps), which can match the demands of real-time performance. Additionally, after tweaking a few parameters, our model is significantly smaller than the original ShuffleNet (465.92MB), allowing for memory adaption to constrained situations. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Collision Detection of Collaborative robot using improved Momentum-based Observer

Research on Collision Detection of Collaborative Robot using...

引用

2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023

作者： Jiang, Yang Wu, Yao Wu, Xingmao Zhao, Bin Northeastern University Faculty of Robot Science and Engineering Shenyang China Northeastern University College of Information Science and Engineering Shenyang China

ISBN: (纸本)9798350331790

With the increasing application of collaborative robots, it is essential to ensure staff safety during human-machine collaboration, so the robot collision detection problem must be addressed. Traditional collision detection requires external sensors, which increases the cost and the structure's complexity. This paper constructed a generalized momentum-based observer to detect external collisions and introduced a compensation link and variable damping design to improve collision detection speed and accuracy. At the same time, after witnessing an external collision, a collision response strategy based on time-scaling was adopted to protect staff safety. Through algorithm simulation, it was verified that the improved momentum-based observer had significantly improved the real-time performance and detection accuracy. At last, the proposed collision detection algorithm was carried out on a collaborative robot with 6 degrees of freedom. The results show that the proposed collision detection algorithm can accurately detect external collisions without external sensors and effectively protect staff safety. © 2023 IEEE.

关键词： Momentum

来源：评论

学校读者我要写书评

暂无评论

Research on deep reinforcement learning-based complex crowd navigation algorithm using risk perception and path selection 7

Research on deep reinforcement learning-based complex crowd ...

引用

7th International Conference on Mechanical, Electric, and Industrial engineering, MEIE 2024

作者： Zhao, Tianxiang Jiang, Yang Chang, Jiajun Zhao, Bin Faculty of Robot Science and Engineering Northeastern University Shenyang110819 China College of Information Science and Engineering Northeastern University Liaoning 110819 China SIASUN Robot & Automation CO. Liaoning 110618 China College of Information Science and Engineering Shenyang University of Technology Liaoning 110870 China

Aiming at the Frozen robot Problem and the poor effect of dynamic obstacle avoidance in traditional navigation methods when encountering dynamic obstacles, a deep reinforcement learning navigation method based on risk perception and path selection is proposed. The core of this method lies in CP (Collision Probability) module and IOU (Intersection over Union) module. The CP module calculates the CP between the robot and the nearby dynamic obstacles in real time, so that the robot can avoid the dangerous obstacles first. At the same time, the intersection-merging ratio module calculates the "pass ability"of the area near the robot in real time, and guides the robot to choose a safer area to pass through. Compared with the DRL method without these two modules, the proposed method achieves the highest navigation success rate in all simulation test environments, and the maximum improvement rate is 11%. At the same time, it still has advantages in navigation time and other indicators. © Published under licence by IOP Publishing Ltd.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共53页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：