检索结果-内蒙古大学图书馆

4th International Conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2021

作者： Li, Penghui Zhang, Lijun Qiao, Jinlong Wang, Xiangguo China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System Wuhan China

ISBN: (纸本)9781665415965

Semantic segmentation is the most important branch of image processing. Semantic segmentation based on deep learning occupies the mainstream method. CNN, FCN, U-NET and DEEPLAB series have achieved good results in the field of image semantic segmentation. The improvement methods of each network also emerge in an endless stream, but the emphasis of improving the network focuses on the feature transfer and feature fusion between network layers in each method. In this paper, based on u-net, we use deep convolution, residual autonomic force and dendrite network to improve the network model. Deep convolution can reduce the amount of calculation, deepen the depth of network, extract more abundant image information, and transmit information between network layers in a more refined way. Dendritic networks are different from ordinary neural networks. Ordinary neural networks process information as models of nerve cell bodies. The role of neural dendrites is also important in the process of information processing. Dendritic network is used as a model of neural dendrites to improve the ability of information processing. The improved network in this paper was tested on the VOC2012 dataset, and the experimental results showed that PA, mAP and IoU were 93.36%, 92.28% and 68.26% respectively. The experimental results showed that the improved network in this paper had improved in all indicators. © 2021 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Delay-Dependent H_∞ Robust Frequency control in Microgrids: Coordination of Secondary Frequency control and Virtual Inertia control

引用

IEEE Transactions on Industrial Informatics 2025年

作者： Wei, Chen-Guang Shangguan, Xing-Chen Yang, Yuan-Hang He, Yong Zhang, Chuan-Ke China University of Geosciences School of Automation Wuhan 430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan 430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan 430074 China

The time delay, disturbances, and parameters uncertainties brought by open communication networks and renewable energy source threaten the stable operation of the frequency control system (FCS) in microgrids (MGs). Plus, the low inertia of MGs exacerbates frequency fluctuations. In this article, the codesign of H_∞ robust controllers for secondary frequency control (SFC) and virtual inertia control (VIC) in the delay-dependent FCS of MG is presented. First, the FCS of MG considering the VIC under the influence of the time delay is established. Second, based on Lyapunov stability theory, an H_∞ performance analysis method is proposed for the FCS of MG with the time-varying delay. Then, with robust performance index as the design condition, the grey wolf optimizer is used to carry out the codesign of the SFC and VIC. Finally, the simulation test proves that the proposed control strategy can effectively codesign the SFC and VIC. The designed robust controllers can effectively deal with the problems of low inertia, time delay, disturbance, and parameters uncertainty in MG frequency control. © 2005-2012 IEEE.

关键词： Codesign of H∞ robust controllers frequency control microgrid (MG) virtual inertia control (VIC)

来源：评论

学校读者我要写书评

暂无评论

An Automatic Hand Rehabilitation Assessment System: Implementation and Experiments 12

An Automatic Hand Rehabilitation Assessment System: Implemen...

引用

12th International Conference on CYBER Technology in automation, control, and intelligent systems, CYBER 2022

作者： Wang, Yifan Cheng, Long Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

The lack of rehabilitation therapists and the increase of disabled individuals have reduced the opportunities for patients to receive well rehabilitation assessment. Towards solving this challenge, establishing a therapist-assistance assessment system to reduce the medical resource consumption is demanding. This paper proposes an automatic hand rehabilitation assessment system based on the Leap Motion vision sensor and a self-designed hand strength measurement device. The assessment algorithm requires the patients to complete every motion given in Fugl-Meyer assessment scale (FMA), and automatically scores the completion level of each motion via recognizing different hand gestures and hand grasping strength. As illustrated by the experiments on ten volunteers, the proposed assessment system can obtain the reliable scores which are consistent with the ones manually obtained via FMA. © 2022 IEEE.

关键词： Patient rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Multiple Non-cooperative Targets Encirclement by Relative Distance based Positioning and Neural Anti-Synchronization control

arXiv

引用

arXiv 2024年

作者： Liu, Fen Yuan, Shenghai Meng, Wei Su, Rong Xie, Lihua Guangdong Provincial Key Laboratory of Intelligent Decision and Cooperative Control School of Automation Guangdong University of Technology Guangzhou510006 China School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore

From prehistoric encirclement for hunting to GPS orbiting the earth for positioning, target encirclement has numerous real world applications. However, encircling multiple non-cooperative targets in GPS-denied environments remains challenging. In this work, multiple targets encirclement by using a minimum of two tasking agents, is considered where the relative distance measurements between the agents and the targets can be obtained by using onboard sensors. Based on the measurements, the center of all the targets is estimated directly by a fuzzy wavelet neural network (FWNN) and the least squares fit method. Then, a new distributed anti-synchronization controller (DASC) is designed so that the two tasking agents are able to encircle all targets while staying opposite to each other. In particular, the radius of the desired encirclement trajectory can be dynamically determined to avoid potential collisions between the two agents and all targets. Based on the Lyapunov stability analysis method, the convergence proofs of the neural network prediction error, the target-center position estimation error, and the controller error are addressed respectively. Finally, both numerical simulations and UAV flight experiments are conducted to demonstrate the validity of the encirclement algorithms. The flight tests recorded video and other simulation results can be found in https://***/B8uTorBNrl4. © 2024, CC BY.

关键词： Orbits

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Silicon Optical Phased Array with Nonuniform Antenna

Performance Analysis of Silicon Optical Phased Array with No...

引用

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Yang Chen Mengyuan Ye Duowei Zeng School of Automation China University of Geosciences Wuhan China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

Optical phased array (OPA) on silicon platform is developed as a hot topic in the past decade. In order to achieve both large field of view (FOV) and high side mode suppression ratio (SMSR), large-scale antenna with spacing of half wavelength is usually required, resulting in large footprint and complex scanning design. Recently, OPAs with nonuniform antenna are proposed as efficient solutions to achieve large FOV with simplified layout. Here, we analyze the performance of various OPAs with different nonuniform antenna designs. In addition, a genetic algorithm optimization method is further proposed for nonuniform antenna design. OPA with the proposed nonuniform antenna is simulated with a steering range of ±50° and SMSR of 11.3dB.

关键词： Phased arrays Layout Asia Optimization methods Silicon Performance analysis Optical arrays

来源：评论

学校读者我要写书评

暂无评论

Task Sequence Planning Algorithm for Cooperative Assembly of Dual-arm Robot

Task Sequence Planning Algorithm for Cooperative Assembly of...

引用

2021 China automation Congress, CAC 2021

作者： Zhang, Jin Gan, Yahui Wang, Zhengwei Dai, Xianzhong School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (纸本)9781665426473

Dual-arm collaborative robots have gradually become a research hotspot in the field of robotics due to their unique collaboration and flexibility, and they have a wide range of application prospects especially in the assembly manufacturing industry. However, the existing dual-arm robot lacks autonomy in assembly operations, especially when faced with a large number of randomly placed assembly parts, how to make the robot have independent assembly task decision-making ability is a challenge. In response to this problem, this paper proposes a new dual-arm robot collaborative assembly task sequence planning algorithm, which fully considers the constraints of the dual-arm robot's mechanical structure, kinematics, characteristics of objects to be assembled, interference between objects, etc.. Firstly, The algorithm uses the Monte Carlo method to analyze the working space of the left and right arms of the dual-arm robot, while taking into account the structural constraints of the robot. Then, according to the characteristics of the object to be assembled, the idea of interference sphere is proposed to analyze the interference between objects in the assembly task. The influence of the operation, and finally combined with the movement cost of the dual-arm assembly, the assembly task sequence is effectively planned. The algorithm was verified by simulation using the ABB YuMi dual-arm collaborative robot, and the experimental results proved the feasibility and effectiveness of the algorithm. © 2021 IEEE

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

TASF: Terrestrial-Aerial Synergistic Framework for a New Generation of intelligent Transportation 27

TASF: Terrestrial-Aerial Synergistic Framework for a New Gen...

引用

27th IEEE International Conference on intelligent Transportation systems, ITSC 2024

作者： Wang, Cong Nie, Dujun Zhang, Ruijun Teng, Siyu Chen, Long Institute of Automation Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Hong Kong Baptist University Kowloon Hong Kong Waytous Inc. Beijing China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems The State Key Laboratory of Management and Control for Complex Systems Beijing100190 China Shenzhen518107 China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an710049 China

ISBN: (纸本)9798331505929

Terrestrial-Aerial Synergistic Framework (TASF) represents a novel approach to intelligent transportation, integrating terrestrial and aerial vehicles to enhance urban transportation efficiency and capacity. In this paper, we offer an in-depth analysis of TASF, emphasizing its innovative applications in urban transportation, parcel delivery, and emergency response services. TASF incorporates a five-layer architecture comprising perception, communication, planning, control, and interaction. With the five-layer architecture, TASF can achieve effective collaboration among terrestrial and aerial vehicles, encompassing two principal features: terrestrial-aerial synergistic parallel perception and multi-agent parallel management. Parallel perception results from fusing Bird's Eye View (BEV) representations from Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs), whereas decentralized multi-agent management employs foundational models to enhance decision-making capabilities. Additionally, we consider challenges and potential solutions related to TASF, including safety, reliability, energy efficiency, management and integration. TASF marks a paradigm-shifting leap in the realm of intelligent transportation systems, providing a scalable and efficacious solution tailored to the dynamic requirements of urban mobility and emergency services. © 2024 IEEE.

关键词： decision making

来源：评论

学校读者我要写书评

暂无评论

Smooth quadrotor trajectory generation for tracking a moving target in cluttered environments

引用

Science China(Information Sciences) 2021年第7期64卷 132-147页

作者： Lele XI Zhihong PENG Lei JIAO Ben M.CHEN School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex System Peng Cheng Laboratory Department of Mechanical and Automation Engineering The Chinese University of Hong Kong

In this paper, we present a trajectory generation method of a quadrotor, based on the optimal smoothing B-spline, for tracking a moving target with consideration of relative tracking pattern or limited field of view of the onboard sensor in cluttered environments. Compared to existing methods, safe flying zone,vehicle physical limits, and smoothness are fully considered to guarantee flight safety, kinodynamic feasibility, and tracking performance. To tackle the cluttered environments, a parallel particle swarm optimization algorithm is applied to find the feasible waypoints that the generated trajectory should be as close to as possible, with consideration of the target's future state as well as obstacles to trade off the tracking performance and flight safety. Then, a sequential motion planning method, considering the above constraints, is applied and embedded into a cost function for solving the problem of robust tracking trajectory generation for the quadrotor via a convex optimization approach. The feasibility and effectiveness of the proposed method are verified by numerical simulations.

关键词： quadrotor target tracking trajectory generation B-spline convex optimization

来源：评论

学校读者我要写书评

暂无评论

Distributed State and Fault Fusion Filtering for Nonlinear systems Subject to Quantization Effects 8

Distributed State and Fault Fusion Filtering for Nonlinear S...

引用

8th International Conference on control Science and systems Engineering, ICCSSE 2022

作者： Hu, Zhibin Hu, Jun Du, Junhua Zhao, Yuna Harbin University of Science and Technology Department of Mathematics Heilongjiang Prov. Key Lab. of Optimization Control and Intelligent Analysis for Complex Systems Harbin China School of Automation Harbin University of Science and Technology Harbin China

ISBN: (纸本)9781665484138

In this paper, the distributed state and fault fusion filtering problem is discussed for a class of multi-sensor networked systems (MSNSs) with randomly occurring quantized measurements (ROQMs). A series of random variables obeying the Bernoulli distribution are adopted to depict the phenomenon of the ROQMs and the fault signal is assumed to appear with an unknown constant type. The aim of this paper is to provide the state and fault fusion filtering algorithm by using the inverse covariance intersection fusion method. Moreover, a proper filter gain is designed by minimizing the local upper bound of filtering error covariance. Finally, the effectiveness of the presented fusion method is verified by using an illustrative example. © 2022 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Based Fixed-time Formation Tracking control for MASs with External Disturbance and Region Constraints

Adaptive Based Fixed-time Formation Tracking Control for MAS...

引用

Chinese control and decision Conference, CCDC

作者： Fenglan Sun Zhonghua Xu Xuemei Yu Key Lab of Intelligent Analysis and Decision on Complex Systems School of Science Chongqing University of Posts and Telecommunications Chongqing P. R. China Key Lab of Intelligent Air-Ground Cooperative Control for Universities in Chongqing College of Automation Chongqing University of Posts and Telecommunications Chongqing P. R. China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

In this paper, a fixed-time time-varying formation tracking controller is proposed for second-order multi-agent systems (MASs) with region constraints based on adaptive observation. A practical finite-time disturbance observer (DO) with an adaptive update law is proposed to eliminate the negative effects of disturbance. Using the sliding mode control technique, a novel fixed-time time-varying region constraints formation tracking controller is designed and the upper bound of convergence time is given. The simulation results show that the disturbance is estimated accurately and quickly by the designed DO, the desired time-varying regular hexagonal formation is realized within the upper bound of convergence time, and all agents remain within the constraint region, which verifies the effectiveness and feasibility of the theoretical results.

关键词： Upper bound Simulation Numerical simulation Disturbance observers Safety Time-varying systems Sliding mode control

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：