检索结果-内蒙古大学图书馆

第41届中国控制会议

作者： Rong Cheng Lizhen Li Haoyun Li Songsong Cheng Xiaohan Fang Yuan Fan Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and AutomationAnhui University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper presents a fault-tolerant control with fixed time convergence for a class of robot manipulators over uncertainties,external disturbances and actuator *** design a disturbance observer to estimate and reject the external ***,based on the disturbance observer,we propose a sliding mode control method for the considered the uncertain robot ***,we show a numerical example to illustrate the effectiveness of the proposed method.

关键词： Fault-tolerant nonsingular fixed time sliding mode control Lyapunov stability theory

来源：评论

学校读者我要写书评

暂无评论

Agent Maze Path Planning Based on Simulated Annealing Q-Learning Algorithm 41

Agent Maze Path Planning Based on Simulated Annealing Q-Lear...

引用

第41届中国控制会议

作者： Zhongtian Mao Zipeng Wu Xiaohan Fang Songsong Cheng Yuan Fan Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and AutomationAnhui University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

The problem of path exploration and planning of agents in unknown environments is a popular application problem in the field of reinforcement *** this paper,we propose an improved reinforcement learning algorithm called the QLearning algorithm for adaptive exploration based on simulated annealing(AE-SAQL).We apply the algorithm to the agent path planning problem,improve the setting of the reward function and add the feedback information of the *** simulating the Metropolis criterion in the annealing algorithm and adding an adaptive adjustment mechanism,the agent fully explores the environment and makes full use of the environmental information,solving the exploration-utilization dilemma during the algorithm and finally enabling the agent to reach the target location *** with the standard Q-Learning algorithm and SARSA algorithm,AE-SAQL achieves better.

关键词： Reinforcement learning Q-Learning Simulated annealing algorithm Maze path planning

来源：评论

学校读者我要写书评

暂无评论

Scene image recognition with knowledge transfer for drone navigation

引用

Journal of Systems Engineering and Electronics 2023年第5期34卷 1309-1318页

作者： DU Hao WANG Wei WANG Xuerao ZUO Jingqiu WANG Yuanda School of Automation Southeast UniversityNanjing 210096China Autonomous Control Robot Laboratory Jiangsu Zhongke Institute of Applied Research on Intelligent Science and TechnologyChangzhou 213164China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and TechnologyNanjing 210044China

In this paper,we study scene image recognition with knowledge transfer for drone *** divide navigation scenes into three macro-classes,namely outdoor special scenes(OSSs),the space from indoors to outdoors or from outdoors to indoors transitional scenes(TSs),and ***,there are difficulties in how to recognize the TSs,to this end,we employ deep convolutional neural network(CNN)based on knowledge transfer,techniques for image augmentation,and fine tuning to solve the ***,there is still a novelty detection prob-lem in the classifier,and we use global navigation satellite sys-tems(GNSS)to solve it in the prediction *** results show our method,with a pre-trained model and fine tun-ing,can achieve 91.3196%top-1 accuracy on Scenes21 dataset,paving the way for drones to learn to understand the scenes around them autonomously.

关键词： scene recognition convolutional neural network knowledge transfer global navigation satellite systems(GNSS)-aided

来源：评论

学校读者我要写书评

暂无评论

Autonomous landing scene recognition based on transfer learning for drones

引用

Journal of Systems Engineering and Electronics 2023年第1期34卷 28-35页

作者： DU Hao WANG Wei WANG Xuerao WANG Yuanda School of Automation Southeast UniversityNanjing 210096China Autonomous Control Robot Laboratory Jiangsu Zhongke Institute of Applied Research on Intelligent Science and TechnologyChangzhou 213164China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and TechnologyNanjing 210044China

In this paper, we study autonomous landing scene recognition with knowledge transfer for drones. Considering the difficulties in aerial remote sensing, especially that some scenes are extremely similar, or the same scene has different representations in different altitudes, we employ a deep convolutional neural network(CNN) based on knowledge transfer and fine-tuning to solve the problem. Then, LandingScenes-7 dataset is established and divided into seven classes. Moreover, there is still a novelty detection problem in the classifier, and we address this by excluding other landing scenes using the approach of thresholding in the prediction stage. We employ the transfer learning method based on ResNeXt-50 backbone with the adaptive momentum(ADAM) optimization algorithm. We also compare ResNet-50 backbone and the momentum stochastic gradient descent(SGD) optimizer. Experiment results show that ResNeXt-50 based on the ADAM optimization algorithm has better performance. With a pre-trained model and fine-tuning, it can achieve 97.845 0% top-1 accuracy on the LandingScenes-7dataset, paving the way for drones to autonomously learn landing scenes.

关键词： landing scene recognition convolutional neural network(CNN) transfer learning remote sensing image

来源：评论

学校读者我要写书评

暂无评论

Deep Regression on Quaternion: A Forward Kinematics Neural Network for Study Six-DoF Pose

Deep Regression on Quaternion: A Forward Kinematics Neural N...

引用

2022 IEEE International Conference on Cyborg and Bionic Systems, CBS 2022

作者： Zhu, Huizhi Xu, Wenxia Wu, Jing Huang, Jian Li, Yanan Yu, Baocheng Li, Jiaxin Lv, Canjiong Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Hubei Wuhan430205 China Huazhong University of Science and Technology Jian Huang Is with School of Automation Hubei Wuhan430074 China

ISBN: (纸本)9781665490283

Solving the forward kinematics problem of robots with high degrees of freedom using neural networks is a really innovative field of study. However, conventional neural network has not been adequate to address this mission requirements of the robot under it's large-scale data with significant unpredictability and low coupling. Thus, we have analyzed and discussed this methodology, and have proposed three solutions, using empirical theory of visual tasks. The results of the experiments demonstrate that our proposed model was effective. © 2023 IEEE.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

A line segment detector based on subanchor point and line segment combination method 37

A line segment detector based on subanchor point and line se...

引用

37th Youth Academic Annual Conference of Chinese Association of automation, YAC 2022

作者： Fan, Fuyou Jiang, Yuanhui Han, Ke Li, Hong Fang, Xiaohan Fan, Yuan Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering Automation Anhui University Hefei230601 China

ISBN: (纸本)9781665465366

Linear segment features contains rich geometric information and it is crucial to perform accurate linear segment detection. We propose a temporal line segment detector based on subanchor point and line segment combination approach, which gives more accurate results without adjusting the parameters. The speed remains essentially the same as the fastest running line segment detectors (EDLines) existing and is 89' faster compared to the conventional LSD line extraction algorithm. The proposed algorithm introduces bilateral filtering and line segment combination methods based on EDLines. The bilateral filter is used after the image input to remove the noise and retain the edge information of the image well. The short line segments that exist homologous are combined to generate clearer long line segments, which overcomes the problem of broken lines in LSD algorithm and excessive filtering of short line segments in EDLines algorithm. We validate the effectiveness of the proposed algorithm in experiments of line feature extraction for multiple sets of images in different scenes. © 2022 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Periodic Sample Based Event-Triggered Control for Linear Systems with State Observer 2

Periodic Sample Based Event-Triggered Control for Linear Sys...

引用

2nd International Conference on Electrical Engineering and Control Science, IC2ECS 2022

作者： Wan, Shiwang School of Electrical Engineering and Automation Anhui University Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment Hefei Anhui China

ISBN: (纸本)9798350399165

To save communication traffic, this paper considers event-Triggered Control for linear systems with state observer and period sampling strategies, which are mostly periodically sampled in conventional control and waste communication resources when the load is too high. Designing a state observer to observe the system state and to implement full-state feedback control. Periodic sampling of the event-Triggered column effectively avoids Zeno's behavior and saves communication resources. Finally, through experiments that the modified algorithm can achieve the stability of the system. © 2022 IEEE.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Trajectory Tracking for Nonholonomic Mobile robot Using Dynamic Event Design 37

Event-Triggered Trajectory Tracking for Nonholonomic Mobile ...

引用

37th Youth Academic Annual Conference of Chinese Association of automation, YAC 2022

作者： Gao, Zhiliang Wu, Zipeng Han, Ke Fang, Xisohan Fan, Yuan Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering Automation Anhui University Hefei230601 China

ISBN: (纸本)9781665465366

In this note, we investigate the trajectory tracing for nonholonomic mobile robot using the dynamic event-triggered control method. Firstly, we propose the system model and take the input control as an update to the nonholonomic mobile robot system. Then, we propose two kind of the trigger conditions and provide the corresponding. finally, the simulation clearly illustrates that the proposed dynamic event-triggered controller is able to reduce more communication burden compared to a classical event-triggered. © 2022 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Visual Realism Assessment for Face-Swap Videos 12th

Visual Realism Assessment for Face-Swap Videos

引用

12th International Conference on Image and Graphics, ICIG 2023

作者： Sun, Xianyun Dong, Beibei Wang, Caiyong Peng, Bo Dong, Jing Beijing Key Laboratory of Robot Bionics and Function Research Beijing University of Civil Engineering and Architecture Beijing China Center for Research on Intelligent Perception and Computing Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783031463044

Deep-learning-based face-swap videos, also known as deepfakes, are becoming more and more realistic and deceiving. The malicious usage of these face-swap videos has caused wide concerns. The research community has been focusing on the automatic detection of these fake videos, but the assessment of their visual realism, as perceived by human eyes, is still an unexplored dimension. Visual realism assessment, or VRA, is essential for assessing the potential impact that may be brought by a specific face-swap video, and it is also important as a quality assessment metric to compare different face-swap methods. In this paper, we make a small step towards this new VRA direction by building a benchmark for evaluating the effectiveness of different automatic VRA models, which range from using traditional handcrafted features to different kinds of deep-learning features. The evaluations are based on a recent competition dataset named DFGC-2022, which contains 1400 diverse face-swap videos that are annotated with Mean Opinion Scores (MOS) on visual realism. Comprehensive experiment results using 11 models and 3 protocols are shown and discussed. We demonstrate the feasibility of devising effective VRA models for assessing face-swap videos and methods. The particular usefulness of existing deepfake detection features for VRA is also noted. The code can be found at https://***/XianyunSun/***. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DGN-MEF: A DenseNet-Based Multi-Exposure Image Fusion Framework using Adaptive Gabor convolution 43

DGN-MEF: A DenseNet-Based Multi-Exposure Image Fusion Framew...

引用

43rd Chinese Control Conference, CCC 2024

作者： Zhang, Mei Jin, Ye Zhu, Jinhui South China University of Technology School of Automation Science and Engineering Guangzhou510641 China South China University of Technology School of Software Engineering Guangzhou510006 China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou510006 China

ISBN: (纸本)9789887581581

Multi-exposure image fusion is a cost-effective method to improve the dynamic range of images. For the problems of inadequate detail extraction in bright and dark areas and the over simplicity of existing fusion rules by current deep learning multi-exposure image fusion algorithms, we propose a DenseNet-based framework using adaptive Gabor convolution. Building on the Dense network architecture, we design an adaptive Gabor convolution module, which the parameters of the Gabor filter can be updated along with the network, enhancing the ability of Gabor to extract image features. Additionally, a cross-domain aggregation attention module is proposed, which effectively aggregates and enhances information. Comparing our method with seven advanced methods on the multi-exposure image fusion benchmark dataset, the subjective and objective evaluations outperform the other methods, proving the effectiveness and superiority of our method. The experiments of different exposure images fusion demonstrate the good generalization performance of our method. © 2024 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Convolution

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：