检索结果-内蒙古大学图书馆

Contrastive Augmented Graph2Graph Memory Interaction for Few Shot Continual Learning

IEEE Transactions on Circuits and systems for Video Technology 2025年第6期35卷 5805-5820页

作者： Qi, Biqing Gao, Junqi Chen, Xinquan Li, Dong Liu, Jianxing Wu, Ligang Zhou, Bowen Tsinghua University Department of Electronic Engineering Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China Harbin Institute of Technology Department of Control Science and Engineering Harbin China Harbin Institute of Technology School of Mathematics Harbin China

Few-Shot Class-Incremental Learning (FSCIL) has gained considerable attention in recent years for its pivotal role in addressing continuously arriving classes. However, it encounters additional challenges. The scarcity of samples in new sessions intensifies overfitting, causing incompatibility between the output features of new and old classes, thereby escalating catastrophic forgetting. A prevalent strategy involves mitigating catastrophic forgetting through the Explicit Memory (EM), which comprise of class prototypes. However, current EM-based methods retrieves memory globally by performing Vector-to-Vector (V2V) interaction between features corresponding to the input and prototypes stored in EM, neglecting the geometric structure of local features. This hinders the accurate modeling of their positional relationships. To incorporate information of local geometric structure, we extend the V2V interaction to Graph-to-Graph (G2G) interaction. For enhancing local structures for better G2G alignment and the prevention of local feature collapse, we propose the Local Graph Preservation (LGP) mechanism. Additionally, to address sample scarcity in classes from new sessions, the Contrast-Augmented G2G (CAG2G) is introduced to promote the aggregation of same class features thus helps few-shot learning. Extensive comparisons on CIFAR100, CUB200, and the challenging ImageNet-R dataset demonstrate the superiority of our method over existing methods. © 1991-2012 IEEE.

关键词： Prototypes Adaptation models Power capacitors Feature extraction Data models Accuracy Vectors Training Incremental learning Overfitting

来源：评论

学校读者我要写书评

暂无评论

General Kinetostatic Modeling and Deformation Analysis of a Two-Module Rod-Driven Continuum Robot with Friction Considered

引用

Chinese Journal of Mechanical engineering 2023年第3期36卷 110-122页

作者： Peiyi Wang Xinhua Yang Xiangyang Wang Sheng Guo School of Mechanical Electronic and Control EngineeringBeijing Jiaotong UniversityBeijing 100044China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518005China

Continuum robots actuated by flexible rods have large potential applications,such as detection and operation tasks in confined environments,since the push and pull actuation of flexible rods withstand tension and compressive force,and increase the structure's *** this paper,a generalized kinetostatics model for multi-module and multi-segment continuum robots considering the effect of friction based on the Cosserat rod theory is ***,the model is applied to a two-module rod-driven continuum robot with winding ropes to analyze its deformation and load *** different in-plane configurations under the external load term as S1,S2,C1,and C2 are *** a bending plane as an example,the tip deformation along thex-axis of these shapes is simulated and compared,which shows that the load capacity of C1 and C2 is generally larger than that of S1 and ***,the deformation experiments and simulations show that the maximum error ratio without external loads relative to the total length is no more than 3%,and it is no more than 4.7%under the external *** established kinetostatics model is proven sufficient to accurately analyze the rod-driven continuum robot with the consideration of internal friction.

关键词： Rod-driven continuum robot Kinetostatic model Cosserat rod theory Deformation and stiffness analysis

来源：评论

学校读者我要写书评

暂无评论

Time-Varying Formation Tracking control of Heterogeneous Multi-Agent systems With Intermittent Communications and Directed Switching Networks

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 294-296页

作者： Yuhan Wang Zhuping Wang Hao Zhang Huaicheng Yan the Shanghai Research Institute for Intelligent Autonomous Systems Tongji University the National Key Laboratory of Autonomous Intelligent Unmanned Systems the Frontiers Science Center for Intelligent Autonomous System of Ministry of Education the College of Electronic and Information Engineering the Department of Control Science and Engineering Tongji University the Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education the School of Information Science and Engineering East China University of Science and Technology

Dear Editor,This letter is concerned with the problem of time-varying formation tracking for heterogeneous multi-agent systems(MASs) under directed switching networks. For this purpose, our first step is to present so... 详细信息

关键词： Switches Topology Observers Formation control Event detection Switched systems Multi-agent systems control theory Autonomous systems Stability

来源：评论

学校读者我要写书评

暂无评论

Perturbation Event Oriented Dynamic Task Scheduling Algorithm for Parallel Testing of control systems

Perturbation Event Oriented Dynamic Task Scheduling Algorith...

引用

2024 IEEE International Conference on Sensing, Diagnostics, Prognostics, and control, SDPC 2024

作者： Chen, Jingyi Wang, Shenhang Tong, Xiaoxuan Xiang, Gang Yu, Yang Zhan, Ziyuan School of Electronic and Information Engineeer Harbin Institute of Technology Harbin China Beijing Aerospace Automatic Control Institute System Design Department Beijing China Beijing Aerospace Automatic Control Institute Beijing China Beijing Aerospace Automatic Control Institute Department of System Engineering Beijing China

ISBN: (纸本)9798350388855

Task scheduling algorithms are key to research and practice in parallel testing techniques, especially in control system applications. The complexity of control system testing requires higher scheduling efficiency. However, perturbation events caused by test equipment problems, data transmission obstacles, or task changes are almost unavoidable and may reduce the scheduling effectiveness or even lead to system crashes. Therefore, in this paper, based on the analysis of the dynamic test scheduling model, a disturbance factor is designed to judge the urgency of disturbance events for evaluating the dynamic scheduling cycle. On this basis, based on the comprehensive rescheduling index, a suitable adjustment strategy is selected to formulate the dynamic test scheduling scheme. The experimental results show that the algorithm proposed in this paper can achieve fast response capability for different disturbance events and exhibit good adaptivity. © 2024 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning guidance with impact time control

引用

Journal of systems engineering and electronics 2024年第6期35卷 1594-1603页

作者： LI Guofei LI Shituo LI Bohao WU Yunjie School of Astronautics Northwestern Polytechnical UniversityXi’an 710072China Beijing Institute of Control and Electronic Technology Beijing 100038China School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China

In consideration of the field-of-view(FOV)angle con-straint,this study focuses on the guidance problem with impact time control.A deep reinforcement learning guidance method is given for the missile to obtain the desired impact time and meet the demand of FOV angle *** basis of the framework of the proportional navigation guidance,an auxiliary control term is supplemented by the distributed deep deterministic policy gradient algorithm,in which the reward functions are developed to decrease the time-to-go error and improve the terminal guid-ance *** numerical simulation demonstrates that the missile governed by the presented deep reinforcement learning guidance law can hit the target successfully at appointed arrival time.

关键词： impact time deep reinforcement learning guidance law field-of-view(FOV)angle deep deterministic policy gradient

来源：评论

学校读者我要写书评

暂无评论

Design and simulation of a two-stage linear inverted pendulum control system based on fuzzy LQR control 7

Design and simulation of a two-stage linear inverted pendulu...

引用

7th International Symposium on Autonomous systems, ISAS 2024

作者： Peng, Siting Ren, Jun Li, Lei Ma, Yichao Song, Zhichao The Beijing Electro-Mechanical Engineering Institute Science and Technology On Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9798350363173

This paper introduces in detail the origin of the development of automatic control methods, applications and current research hotspots. It also introduces some control methods commonly used in industrial and agricultural production, and expounds the current application hotspots and new advanced control methods that are developing rapidly. The background, current situation and classification of the inverted pendulum platform are introduced in detail. In the first chapter, the LQR method in modern control theory is introduced in detail. The influence of parameters is analyzed through simulink space modeling and simulation control experiment. At the same time, the real-time experiment is also done in combination with the hardware platform. In the second chapter, the fuzzy control theory in intelligent control is introduced in detail. By combining fuzzy control with LQR method, suitable LQR parameters are calculated by pole assignment. After proper adjustment, reasonable fuzzy rules are adopted and adaptive fuzzy control principle is applied to adjust the control situation in real time. Using simulink space modeling, a good simulation control effect is obtained. Finally, the summary is made. © 2024 IEEE.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Study on photoelectric anti-interference technology of Optical Detecting system used in Surface-to-air Missiles 6

Study on photoelectric anti-interference technology of Optic...

引用

6th Conference on Frontiers in Optical Imaging and Technology: Imaging Detection and Target Recognition

作者： Li-Qin, Zhang Lei, Chen Wei, Shen Jin-Dong, Fei Beijing Institute of Electronic System Engineering Peking100854 China Science and Technology on Special System Simulation Laboratory Peking100854 China

ISBN: (数字)9781510679733

ISBN: (纸本)9781510679726

As the battlefield environment becomes more complex, optical guided weapons will face increasingly complex photoelectric interference environment. This paper analyzes the photoelectric interference and interference mode faced by the optical detection system used in surface-to-air missiles, also gives anti-interference methods and simulation results, aiming at providing reference for anti-interference design of surface-to-air missiles. © 2024 SPIE. All rights reserved.

关键词： Surface to air missiles

来源：评论

学校读者我要写书评

暂无评论

A novel adaptive lateral reentry guidance algorithm with complex distributed no-fly zones constraints

引用

Chinese Journal of Aeronautics 2022年第7期35卷 128-143页

作者： Yudong HU Changsheng GAO Junlong LI Wuxing JING Wenxue CHEN School of Astronautics Harbin Institute of TechnologyHarbin 150001China Beijing Institute of Electronic System Engineering China Aerospace Science and Industry CorporationBeijing 100854China

Aimed at complex distributed no-fly zones avoidance problems,a novel adaptive lateral reentry guidance algorithm is ***,by introducing the improved attractive and repulsive potential fields,an improved artificial potential field method is *** with the proposed judgment criterion for whether a no-fly zone has been avoided,the proposed improved artificial potential field method effectively solves the reference heading angle determination problem under the constraints of complex distributed no-fly ***,based on the proposed no-fly zone’s threat quantitative evaluation method and the reference heading angle determined by the proposed improved artificial potential field method,the heading corridor is improved to increase its sensitivity to the threat changes of the no-fly ***,for satisfying the requirements of complex distributed no-fly zones avoidance,a novel guidance logic via improved heading corridor is proposed to update the reference heading corridor adaptively in real time according to the threat and constraint changes of the no-fly zones,and the bank reversal logic is employed to control the lateral *** simulation results for nominal and dispersed cases indicate that the proposed guidance algorithm has high robustness,stability,and applicability,and is feasible and effective to deal with the complex distributed no-fly zones avoidance problems.

关键词： Guidance strategy Heading corridor Hypersonic vehicles Improved artificial potential field Lateral reentry guidance Threat quantitative evaluation

来源：评论

学校读者我要写书评

暂无评论

A Review:From Aquatic Lives Locomotion to Bio-inspired Robot Mechanical Designations

引用

Journal of Bionic engineering 2023年第6期20卷 2487-2511页

作者： Pengxiao Bao Liwei Shi Lijie Duan Shuxiang Guo Zhengyu Li School of Medical Technology Beijing Institute of TechnologyBeijing100081China School of Life Science Beijing Institute of TechnologyBeijing100081China The Key Laboratory of Convergence Medical Engineering System and Healthcare Technology The Ministry of Industry and Information TechnologyBeijing Institute of TechnologyNo.5ZhongguancunSouth StreetBeijing100081China The Department of Electronic and Electrical Engineering Southern University of Science and TechnologyShenzhen518055GuangdongChina

With the development of camera technology,high-speed cameras have greatly contributed to capturing the movement and posture of animals,which has dramatically promoted experimental biology *** the same time,with the concept of bionics gradually gaining popularity among researchers,the design of robots is absorbing more and more biological features,where the interest in the bio-inspired robot is hewed *** with the traditional robot,the bio-inspired robot imitates the motion pattern to achieve similar propulsion features,which may be more effective and *** this paper,the motion patterns of aquatic animals are divided into four categories according to their propulsion mechanisms:drag-based,lift-based,jet-based,and *** bio-inspired robots imitating aquatic prototypes are introduced and ***,the prospect of aquatic bio-inspired robots is discussed.

关键词： Bionic Bio-inspired robot Aquatic animal Propelling mechanism Structure design

来源：评论

学校读者我要写书评

暂无评论

A Shakedown Strength Based Parametric Optimization Technique and Its Application on an Airtight Module

引用

Chinese Journal of Mechanical engineering 2022年第4期35卷 139-151页

作者： Songhua Huang Yugong Xu Lele Zhang Geng Chen Feng Liu School of Mechanical Electronic and Control EngineeringBeijing Jiaotong UniversityBeijing 100044China National International Science and Technology Cooperation Base on Railway Vehicle Operation Beijing Jiaotong UniversityBeijing 100044China Beijing Institute of Spacecraft System Engineering Academy of Space TechnologyBeijing 100094China

In aerospace engineering,design and optimization of mechanical structures are usually performed with respect to elastic *** causing insufcient use of the material,such design concept fails to meet the ever growing needs of the light weight *** remedy this problem,in the present study,a shakedown theory based numerical approach for performing parametric optimization is *** this approach,strength of the structure is measured by its shakedown limit calculated from the direct *** numerical method developed for the structural optimization consists of nested loops:the inner loop adopts the interior point method to solve shakedown problems pertained to fxed design parameters,while the outer loop employs the genetic algorithm to fnd optimal design parameters leading to the greatest shakedown *** method established is frst verifed by the classic plate-with-a-circular-hole example,and after that it is applied to an airtight module for determining few key design *** carefully analyzing results generated during the optimization process,it is convinced that the approach can become a viable means for designing similar aerospace structures.

关键词： Parametric optimal design Shakedown analysis Direct method(DM) Genetic algorithm

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：