检索结果-内蒙古大学图书馆

2023 International Conference on Neuromorphic Computing, ICNC 2023

作者： Wang, Yonghuan Wang, Leimin Wu, Genping China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation Wuhan430074 China Wuhan Second Ship Design and Research Institute Wuhan430064 China

ISBN: (纸本)9798350316889

In this paper, by using the flux-controlled memristor model, the finite-time synchronization problem of delayed complex-valued memristive neural networks (MCNNs) is studied. Firstly, according to the proposed memristor model, we model the MCNNs as continuous systems on voltage-flux-time (wp, varpi, t) domain. Then, we design a class of approaches to realize state synchronization between the drive and response systems, and the corresponding synchronization conditions are achieved. Finally, the effectiveness of results is illustrated with the simulations. © 2023 IEEE.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Enhancing sensitivity of ultrasmall rotation velocity measurements with biased quantum weak measurement 41

Enhancing sensitivity of ultrasmall rotation velocity measur...

引用

第41届中国控制会议

作者： Guang-Jun Wang Xue-Ying Duan Jing-Hui Huang Xiang-Yun Hu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Institute of Geophysics and Geomatics China University of Geosciences Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Recently,biased quantum weak measurement has shown higher precision than both conventional measurement and standard quantum weak measurement in optical *** this work,a scheme of detecting the ultrasmall rotation velocity in Sagnac's interferometer with biased quantum weak measurement is *** biased quantum weak measurement,additional progress of pre-coupling is introduced in standard quantum weak measurement to enhance the sensitivity for the estimated parameter,and the cost of the reduction of photons in the post-selection by pre-coupling may not impact the measurement because eliminating the saturation effect of the detector *** addition,our numerical results show that the scheme with biased quantum weak measurement can obtain a higher sensitivity for rotation velocity measurement than the scheme with standard quantum weak measurement.

关键词： quantum measurement quantum weak measurement quantum optical rotation velocity sensitivity enhanced

来源：评论

学校读者我要写书评

暂无评论

Two-Stage OD Flow Prediction for Emergency in Urban Rail Transit

引用

IEEE Transactions on Intelligent Transportation systems 2024年第1期25卷 920-928页

作者： Zhu, Guangyu Ding, Jiacun Wei, Yun Yi, Yang Xu, Sendren Sheng-Dong Wu, Edmond Q. Beijing Jiaotong University Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport The Beijing Research Center of Urban Traffic Information Sensing and Service Technologies Beijing100044 China Beijing Mass Transit Railway Operation Corporation Ltd. Beijing100014 China Yangzhou University College of Information Engineering Yangzhou225127 China National Taiwan University of Science and Technology Automation and Control Center The Graduate Institute of Automation and Control Taipei106335 Taiwan Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China The Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai200240 China

Urban rail transit (URT) is vulnerable to natural disasters and social emergencies including fire, storm and epidemic (such as COVID-19), and real-time origin-destination (OD) flow prediction provides URT operators with important information to ensure the safety of URT system. However, hindered by the high dimensionality of OD flow and the lack of supportive information reflecting the real-time passenger flow changes, study in this area is at the beginning stage. A novel model consisting of two stages is proposed for OD flow prediction. The first stage predicts the inflows of all stations by Long Short-Term Memory (LSTM) in real time, where the dimension is reduced compared with predicting OD flows directly. In the second stage, the notion of separation rate, namely, the proportion of inbound passengers bounding for another station, is estimated. Finally, The OD flow is predicted by multiplying the inflow and separation rate. Experiments based on Hangzhou Metro dataset show the proposed model outperforms the contrast model in weighted mean average error (WMAE) and weighted mean square error (WMSE). Results also suggest that the proposed prediction model performs better on weekdays than on weekends, and with greater accuracy on larger OD flows. © 2000-2011 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Demonstration of the Dyna Reinforcement Learning Framework for Reactive Close Proximity Operations

Demonstration of the Dyna Reinforcement Learning Framework f...

引用

AIAA Science and technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Majumdar, Ritwik Albee, Keenan Sternberg, David C. Jia-Richards, Oliver Department of Aerospace Engineering University of Michigan Ann ArborMI United States Payload/Instrument Pointing Control Systems Engineering Group Jet Propulsion Laboratory California Institute of Technology PasadenaCA United States Maritime and Multi-Agent Autonomy Group Jet Propulsion Laboratory California Institute of Technology PasadenaCA United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

Lessons from the International Space Station (ISS) emphasize the necessity of exterior inspection for anomaly detection and maintenance, but current methods rely on costly and limited human extravehicular activities and robotic arms. Deployable free-flying small spacecraft offer a flexible, autonomous solution, capable of comprehensive exterior inspections without human involvement. However, the safety of these spacecraft during close proximity operations remains a concern, particularly given uncertain variability in thruster performance. This paper presents SmallSat Steward, a reactive and integrated architecture for online model learning and trajectory planning based on the Dyna reinforcement learning architecture. By combining model-based planning and direct reinforcement learning, Dyna offers a potentially flexible and computationally-efficient solution capable of adapting to changes in thruster performance and other system uncertainties. Preliminary results in both simulation and hardware environments demonstrate the potential of this architecture to successfully regulate position under single and double thruster failures. In simulation, the Dyna-based controller outperformed an PD-LQR controller in ∼70% of all cases. On hardware, Dyna was able to eliminate the steady state error caused by thruster failures. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Space stations

来源：评论

学校读者我要写书评

暂无评论

Synthesis of Diagnostic Observers for Linear systems Based on Optimal control Methods

Synthesis of Diagnostic Observers for Linear Systems Based o...

引用

2022 International Conference on control, automation and Diagnosis, ICCAD 2022

作者： Kabanov, Aleksey A. Zuev, Aleksandr V. Zhirabok, Aleksey N. Filaretov, Vladimir F. Department of Informatics and Control in Technical Systems Sevastopol State University Russia Laboratory of Intelligent Information Systems for Marine Robots Institute of Marine Technology Problems FEB RAS Russia Department of Automation and Robotics Far Eastern Federal University Russia Robotics Laboratory Institute of Automation and Control Processes FEB RAS Russia

ISBN: (数字)9781665497947

ISBN: (纸本)9781665497947

The paper considers the problem of fault identification in dynamic systems described by linear differential equations. To solve this problem, diagnostic observers constructed on the basis of optimal control methods are used. The proposed new method for the synthesis of such observers is based on the idea of introducing a new system with some auxiliary control which plays a role of an unknown vector function describing emerging faults. This control is proposed to be formed in such a way that it provides a minimum for the residual functional. Unlike popular approaches to solving the problem of fault identification based on observers operating in a sliding mode, the proposed method allows us to expand the class of systems for which the identification problem can be solved. It is known that the methods of sliding mode observers design impose certain restrictions on the systems under consideration. The suggested theory is illustrated by an example. The simulation results confirmed the operability of the diagnostic observers synthesized using the method proposed in the work. © 2022 IEEE.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

MAN: Mix-domain attentional single-stage object detection network with multiple attention mechanisms 20

MAN: Mix-domain attentional single-stage object detection ne...

引用

20th IEEE International Conference on Mechatronics and automation, ICMA 2023

作者： Sun, Lei Han, Yun Gong, Xinxiang Jin, Shuaiyu Tianjin University of Technology School of Electrical Engineering and Automation Binshui Xidao Extension 391 Tianjin300384 China Tianjin University of Technology Tianjin Key Laboratory for Control Theory and Complicated Industry Systems Binshui Xidao Extension 391 Tianjin300384 China

ISBN: (纸本)9798350320831

Deep convolutional neural networks (CNN) have achieved remarkable progress in the image processing field during the past decade. However, most existing CNN-based object detection algorithms mainly delve into network-deepening, overlooking the exploration of the inherent relationship amongst the features. To address this issue, an end-to-end Mix-domain Attention Network (MAN) is proposed. First, the backbone and head of MAN adopt the structure of YOLOv5 (YOLOv5 is a family of object detection architectures and models pre-trained on the COCO dataset by Ultralytics). Then, we embed two key modules in the backbone and head: non-local blocks and stereoscopic attention group (SAG). Non-local blocks are different from CNN's local operations in that they can capture long-distance spatial contextual information (Such as the pixel-to-pixel relationship in images, and the pixel-to-pixel relationship between different frames in video streams) and combined with the residual structure, this allows the feature dimensions of the input and output to be consistent. Subsequently, the features extracted from the non-local blocks will be further passed through a trainable stereoscopic attention group to calculate the correlation of channel-to-channel, pixel-to-pixel, and update the output features. The Non-local operation is the self-attention mechanism and the SAG operation is the channel and spatial attention mechanism. Our innovation is the combination of these two operations to form a Mix-domain attention mechanism. The Non-local increases the connection between the pixel points. The SAG allows the model to focus more on the places that need attention. The combination of these two modules enhances recognition accuracy. The experimental results demonstrate that the two versions of a Mixdomain Attention Network achieves the following results on Microsoft Common Objects in Context (MS-COCO) with an input size of 640∗640: AP(Average Precision)=38.2%, 44.4%,AP05 (IOU >0.5 Average Precisi

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Design and Modeling of a Spring-Based Continuum Manipulator for Minimally Invasive Surgery

Design and Modeling of a Spring-Based Continuum Manipulator ...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Zhang, Jianyong Li, Guotao Su, Tingting Liang, Xu Hou, Zeng-Guang North China Universily of Technology Department of Mechanical and Electrical Engineering Beijing100144 China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China School of Information Science and Technology Beijing University of Technology Beijing100190 China School of Automation and Intelligence Beijing Jiaotong University Beijing100190 China

ISBN: (纸本)9781665481090

Minimally invasive surgery (MIS) has gained significant attention from both patients and doctors for its less trauma, less pain, and faster recovery. Robot-assisted MIS has proven effective in reducing doctors' fatigue and improving surgical precision. MIS robots require more degrees of freedom of motion within limited dimensions to complete accurate, stable and safe surgery in a constrained working space. This paper proposes a spring-based continuum manipulator for MIS. The manipulator's length can be adjusted automatically. Its simple structure makes it easy to miniaturize. In addition, it includes a central channel for instrument replacement. The stiffness of the manipulator is analyzed, and a constant curvature kinematic model for the manipulator is developed. The effectiveness of the proposed constant curvature kinematics model was verified through experiments, and the motion performance experiments of the manipulator were conducted. © 2024 IEEE.

关键词： Robotic surgery

来源：评论

学校读者我要写书评

暂无评论

Dynamic Sensing Modeling of Dielectric Elastomer Sensors Based on GRU Neural Network 6

Dynamic Sensing Modeling of Dielectric Elastomer Sensors Bas...

引用

6th International Conference on Intelligent Robotics and control engineering, IRCE 2023

作者： Zhang, Mingyi Huang, Peng Wang, Yawu School of Automation China University of Geosciences Wuhan Hubei430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan Hubei430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan Hubei430074 China

ISBN: (纸本)9798350326338

Dielectric elastomer sensor (DES) is a flexible sensor that can perform free bending deformation, thus it has broad application prospects in the fields of medical electronics, wearable devices, soft robots, etc. Previous studies have mostly focused on exploring the static sensing characteristics of the DES. Considering that the DES may be used in dynamic conditions, it is very meaningful to study its dynamic sensing characteristics to broaden its application ranges. In this paper, a dynamic sensing model of the DES is established based on the gate recurrent unit (GRU) neural network. Firstly, the structure of the DES and the construction of the experimental system are introduced. In addition, the dynamic sensing characteristics of the DES are analyzed by conducting several sets of experiments, which shows that the DES has significant rate-dependent hysteresis nonlinearities, multivalued mapping and memory characteristics. After that, the dynamic sensing model of the DES is built based on the GRU neural network to describe the above dynamic sensing characteristics. Next, the dynamic displacement and force sensing models of the DES are trained according to the dynamic displacement-capacitance and dynamic force-capacitance experimental data, respectively. Finally, several experiments are performed to verify the effectiveness and generalization ability of the established dynamic sensing model. © 2023 IEEE.

关键词： Capacitance

来源：评论

学校读者我要写书评

暂无评论

Real-Time Implementation of MEKF using VDPL Localization Algorithm by Utilizing MATLAB & ROS Communication

Real-Time Implementation of MEKF using VDPL Localization Alg...

引用

Innovations in Intelligent systems and Applications Conference

作者： Ozan Vahit Altinpinar Emre Can Contarlı Volkan Sezer Department of Mechatronics Engineering Smart and Autonomous Systems Laboratory Istanbul Technical University Istanbul TURKEY Department of Control and Automation Engineering Smart and Autonomous Systems Laboratory Istanbul Technical University Istanbul TURKEY

ISBN: (数字)9798350379433

ISBN: (纸本)9798350379440

Mobile robots, which are produced to fulfill certain tasks to make our lives easier, are becoming more and more common in our environment day by day. In the long run, these robots can be more cost-effective, faster, and more efficient than humans in accomplishing tasks. In order for mobile robots to fulfill the tasks, they need to be able to safely navigate to specific destinations without hitting obstacles. Safely reaching a given goal most accurately and shortly is the problem of autonomy. This autonomy problem is divided into sub-problems and algorithms are needed to solve each sub-problem. The main sub-problems in the field of autonomy are localization, mapping, local planning, and global planning. The main purpose of this paper is to describe how the position information computed by a MEKF (Modified Extended Kalman Filter) localization algorithm using the VDPL (Virtual Dynamic Point Landmark) algorithm, which was previously designed in MATLAB, is published to the ROS environment via a topic. This position information can be used together with the local and global planning algorithms in the navigation stack to realize fully autonomous driving capability in a real-time environment. Using these algorithms, full-autonomous driving tests were conducted on the Turtlebot3 mobile robot in a real-time environment according to a predefined scenario. The performance results of both simulation and real-world tests show that the MEKF using the VDPL algorithm outperforms the AMCL algorithm in the navigation stack in both cases.

关键词： Location awareness Technological innovation Navigation Heuristic algorithms Real-time systems Planning Mobile robots Kalman filters MATLAB Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Mining Better Samples and Semantic Consistency for Contrast Learning in Forest Semantic Segmentation 41

Mining Better Samples and Semantic Consistency for Contrast ...

引用

第41届中国控制会议

作者： Chongjin Chen Yichao Cao Qingfei Tang Xiaobo Lu School of Software Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing Enbo Technology Co. Ltd.

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Image segmentation has impressive progress in the past several *** good segmentation usually follows pixelwise well-annotated labels which is ***,the robustness would not be guaranteed due to lack-ofdiversity *** work usually focuses on pixels individually and pay less attention to the neighbor *** local context would be scarce and the global context is not utilized following these *** proposal a method,named Forest Semantic Segmentation Network(FSSNet) to address these *** organizes original version and augmented version of images,as two inputs into student branch and teacher branch,and force the two outputs being consistent to strengthen the robustness of our ***,we not only consider pixel itself and also the neighbor pixels because the context of neighbor pixels helps understanding the *** utilizes contrastive loss with memory bank to involve global context in training which will make pixels closer to others in same category and far away from pixels of different categories.A bank filter is suggested to improve the quality of features in the memory *** also proposal a new sample strategy to improve the effect of contrastive loss and reduce the *** method can improve accuracy and strengthen the robustness with affordable extra computation during training process,and no additional computation during inference toward *** to benchmark,the proposed approach can improve the mIoU by 3.1% on our challenging dataset.

关键词： Semantic segmentation Contrastive learning Deep learning

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：