检索结果-内蒙古大学图书馆

Few-shot object detection via class encoding and multi-target decoding

IET cyber-systems and Robotics 2023年第2期5卷 1-14页

作者： Xueqiang Guo Hanqing Yang Mohan Wei Xiaotong Ye Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhouChina Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province HangzhouChina

The task of few‐shot object detection is to classify and locate objects through a few annotated *** many studies have tried to solve this problem,the results are still not *** studies have found that the class margin significantly impacts the classification and representation of the targets to be *** methods use the loss function to balance the class margin,but the results show that the loss‐based methods only have a tiny improvement on the few‐shot object detection *** this study,the authors propose a class encoding method based on the transformer to balance the class margin,which can make the model pay more attention to the essential information of the features,thus increasing the recognition ability of the ***,the authors propose a multi‐target decoding method to aggregate RoI vectors generated from multi‐target images with multiple support vectors,which can significantly improve the detection ability of the detector for multi‐target *** on Pascal visual object classes(VOC)and Microsoft Common Objects in Context datasets show that our proposed Few‐Shot Object Detection via Class Encoding and Multi‐Target Decoding significantly improves upon baseline detectors(average accuracy improvement is up to 10.8%on VOC and 2.1%on COCO),achieving competitive *** general,we propose a new way to regulate the class margin between support set vectors and a way of feature aggregation for images containing multiple objects and achieve remarkable *** method is implemented on mmfewshot,and the code will be available later.

关键词： Class Margin Few-Shot Object Detection Multi-Target Transformer

来源：评论

学校读者我要写书评

暂无评论

Model predictive control with fractional-order delay compensation for fast sampling systems

引用

Science China(Information Sciences) 2021年第7期64卷 165-180页

作者： Ze ZHOU Zhitao LIU Hongye SU Liyan ZHANG State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang University School of Automation Wuhan University of Technology

Model predictive control(MPC) is widely used in fast sampling systems owing to its fast regulating ability. However, the sampling delay is a key issue and tends to be a fractional multiple of the sampling period. If the fractional-order delay is not accurately offset, the controller output will exhibit errors, thus resulting in oscillations in controlled system. Moreover, the MPC delay compensation algorithm is limited to the computation time. To address the problems of fractional delay and computational burden in fast sampling systems, we propose a new method to compensate for the fractional-order sampling ***, we use a finite-impulse-response fractional delay filter based on a Lagrange interpolation polynomial to approximate the fractional portion. Moreover, we prove that high accuracy and simplicity can be ensured when the polynomial order is one. Then, we estimate the current state variable using the delayed sampling signal and control signals of past moments. Further, we obtain the current control signal according to the estimated state variable. By considering the simultaneous existence of computational and sampling delays,a full compensation strategy is proposed. Computational simulation results validate the proposed MPC algorithm with fractional-order delay compensation and demonstrate its advantages.

关键词： model predictive control fast sampling systems sampling delay fractional-order Lagrange interpolation polynomial

来源：评论

学校读者我要写书评

暂无评论

Formal management-specifying approach for model-based safety assessment

引用

Journal of systems Engineering and Electronics 2023年第6期34卷 1589-1601页

作者： XU Changyi DUAN Yiman ZHANG Chao School of Control Science and Engineering Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of EducationDalian University of TechnologyDalian 116024China State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical EngineeringZhejiang UniversityHangzhou 310027China

In the field of model-based system assessment,mathematical models are used to interpret the system ***,the industrial systems in this intelligent era will be more *** management operations will be dynamically set,and the system will be no longer static as it is initially ***,the static model generated by the traditional model-based safety assessment(MBSA)approach cannot be used to accurately assess the *** mainly exists three ***:huge and complex behaviors make the modeling to be trivial manual;Dynamic:though there are thousands of states and transitions,the previous model must be resubmitted to assess whenever new management arrives;Unreusable:as for different systems,the model must be resubmitted by reconsidering both the management and the system itself at the same time though the management is the *** by solving the above problems,this research studies a formal management specifying approach with the advantages of agility modeling,dynamic modeling,and specification design that can be ***,three typical managements are specified in a series-parallel system as a demonstration to show the potential.

关键词： model-based safety assessment(MBSA) management availability reliability maintainability continuous time Markov chain.

来源：评论

学校读者我要写书评

暂无评论

Resilient observer-based event-triggered control for cyber-physical systems under asynchronous denial-of-service attacks

引用

Science China(Information Sciences) 2022年第4期65卷 182-196页

作者： Yifang ZHANG Zheng-Guang WU Zongze WU Deyuan MENG State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang University School of Automation Guangdong University of Technology Seventh Research Division Beihang University (BUAA) School of Automation Science and Electrical Engineering Beihang University (BUAA)

We develop the resilient observer-based event-triggered control update strategy in this *** is utilized to achieve the input-to-state stability（ISS） of cyber-physical systems（CPSs） when there is an asynchronous denial-of-service（DoS） attack, which is launched by malicious adversaries both on measurement channel and control channel in a random attack strategy. To estimate the unmeasurable states while saving the limited networked bandwidth, an H∞observer-based event-triggered control scheme is first designed to guarantee the ISS of CPSs with economic communication. Moreover, the occurrence of Zeno behavior can be eliminated by providing the existence of a lower positive bound of any two inter-event times. Then, a recursive model of asynchronous DoS attacks is introduced. A resilient control update strategy is proposed and further analyzed to derive the stability criterion of CPSs. At last, a numerical simulation example is given to demonstrate the effectiveness of the introduced control update policy.

关键词： cyber-physical systems input-to-state stability asynchronous DoS attacks $H_\infty~$ observer event-triggered control

来源：评论

学校读者我要写书评

暂无评论

An Improved A-Star Algorithm Based on Dynamic Congestion control 4

An Improved A-Star Algorithm Based on Dynamic Congestion Con...

引用

4th International Conference on Advances in Computer technology, Information Science and Communications, CTISC 2022

作者： Lin, Zeyu Feng, Ligen Chen, Xinyu Wu, Weimin Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Hangzhou China

ISBN: (数字)9781665458726

ISBN: (纸本)9781665458726

Automatic guided vehicles (AGV) are widely used in warehousing systems, flexible manufacturing systems and other fields. The path planning for AGV is often a huge challenge. And the path planning methods described in the existing literature are often not good at avoiding congestion. In this paper, we propose an improved A-star algorithm based on dynamic planning that senses the presence of congestion in the map and avoids congestion by increasing the congestion weights. Compared with existing methods, it is able to significantly improve efficiency. © 2022 IEEE.

关键词： Automatic guided vehicles

来源：评论

学校读者我要写书评

暂无评论

Optimal Velocity control of Spherical Robots Based on Offset-free Linear Model Predictive control

Optimal Velocity Control of Spherical Robots Based on Offset...

引用

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Hu, Tao Guan, Xiaoqing Lin, Boyu Wang, Yixu Liu, Yifan Wang, You Li, Guang Institute of Cyber Systems and Control State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

ISBN: (纸本)9781665481090

Since the sensors of spherical robots rotate with the longitudinal axis, an efficient velocity controller must also account for robot's attitude. Therefore, this paper proposed an optimal velocity controller for spherical robots based on the offset-free linear model predictive control (LMPC), which controls the velocity while considering robot's attitude, motor's current and other variables. The prediction model of LMPC was generated by linearizing and discretizing the dynamic model and introducing the disturbance model. Then the kalman filter (KF) was used to estimate the states and disturbance. After that, combined with LMPC, the offset-free tracking of different velocities under different terrains was achieved by fully considering velocity, attitude and current in the target function. Finally, a series of physical experiments show that the proposed controller ensures fast convergence, strong stability and no bias, while the velocity changes more smoothly, the attitude changes less and the current output is more stable. © 2022 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

MMH-FE:AMulti-Precision and Multi-Sourced Heterogeneous Privacy-Preserving Neural Network Training Based on Functional Encryption

引用

Computers, Materials & Continua 2025年第3期82卷 5387-5405页

作者： Hao Li Kuan Shao Xin Wang Mufeng Wang Zhenyong Zhang The State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science CenterQilu University of Technology(Shandong Academy of Sciences)Jinan250014China China Industrial Control Systems Cyber Emergency Response Team Beijing100040China

Due to the development of cloud computing and machine learning,users can upload their data to the cloud for machine learning model ***,dishonest clouds may infer user data,resulting in user data *** schemes have achieved secure outsourced computing,but they suffer from low computational accuracy,difficult-to-handle heterogeneous distribution of data from multiple sources,and high computational cost,which result in extremely poor user experience and expensive cloud computing *** address the above problems,we propose amulti-precision,multi-sourced,andmulti-key outsourcing neural network training ***,we design a multi-precision functional encryption computation based on Euclidean ***,we design the outsourcing model training algorithm based on a multi-precision functional encryption with multi-sourced ***,we conduct experiments on three *** results indicate that our framework achieves an accuracy improvement of 6%to 30%.Additionally,it offers a memory space optimization of 1.0×2^(24) times compared to the previous best approach.

关键词： Functional encryption multi-sourced heterogeneous data privacy preservation neural networks

来源：评论

学校读者我要写书评

暂无评论

Invariant EKF based state Estimator for Quadruped Robots 42

Invariant EKF based State Estimator for Quadruped Robots

引用

42nd Chinese control Conference, CCC 2023

作者： Zhang, Zhuqing Li, Zhang Chen, Yong Wang, Dongqi Yu, Jiyu Xiong, Rong Wang, Yue Zhejiang University State Key Laboratory of Industrial Control Technology and Institute of Cyber-Systems and Control Hangzhou310027 China Research Institute of Nuclear Power Operation Wuhan China

ISBN: (纸本)9789887581543

Quadruped robots have gained much attention in recent years due to their potential ability to handle various kinds of terrain. To control the quadruped robots to perform tasks, high frequency (up to 400Hz) state estimation is demanded. In this paper, we introduce an accurate and efficient state estimator by incorporating IMU measurements and quadruped robot joint encoder measurements. To be specific, we utilize the IMU measurements to propagate the state, while the joint encoder measurements are used to derive the foot position of the robot to update the state. The whole process is based on an invariant EKF, which is proved in this paper to be able to preserve the correct observability of the system. Moreover, based on the estimated state, the inclination of the terrain with respect to the horizontal plane can be calculated, which is useful for downstream control. Experiments are conducted to validate the effectiveness of our proposed state estimator. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： state estimation

来源：评论

学校读者我要写书评

暂无评论

Fast Adaptation Dynamics Model for Robot's Damage Recovery

Fast Adaptation Dynamics Model for Robot's Damage Recovery

引用

2022 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2022

作者： Chen, Ci Wang, Dongqi Yu, Jiyu Xiang, Pingyu Lu, Haojian Wang, Yue Xiong, Rong Institute of Cyber-Systems and Control Zhejiang University State Key Laboratory of Industrial Control and Technology Hangzhou310027 China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

In the process of operating, robots will inevitably encounter damage due to external or internal factors, such as motors blockage. For the legged robot, when the motors of joints are failing, if other motors still act according to the original instructions, it will cause the robot to deviate from the predetermined trajectory, which is unacceptable for legged robots. Inspired by the fact that the model trained by supervised learning on the training set can be generalized to the testing set, our goal is to obtain a dynamic model that can be generalized to all kinds of motor damage situations. It can predict what state will be reached in the next step when an action is applied in the current state. With this dynamics model, we use the Monte Carlo particles to optimize the feasible actions in a model predictive control (MPC) fashion and achieve the expected goal (such as making the robot walk in a straight line). The comparison experiment adopt two meta-learning model and vanilla dynamics model approaches, the results show that the proposed method is superior to the three baselines, which proves the effectiveness of the proposed method. © 2022 IEEE.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Research on real-time export container allocation considering loading efficiency 19

Research on real-time export container allocation considerin...

引用

19th IEEE International Conference on Networking, Sensing and control, ICNSC 2022

作者： Qian, Jianlin Wu, Weimin Zhu, Yangfei Institute of Cyber-Systems and Control Zhejiang University The State Key Laboratory of Industrial Control Technology Hangzhou310027 China

ISBN: (纸本)9781665472432

Determining where to stack the containers on the storage yard of a container terminal is an important problem, because it will make a great importance on the loading efficiency. In order to minimize the container relocation times and the average transportation distance of containers, we propose a penalty based strategy for real-time container allocation. When the sequence of containers arriving at the storage yard is uncertain, this strategy can allocate the location for a single container when it arrives, so as to minimize the container relocation times and transportation distance during shipment as a whole. Experiments show that this strategy can get a relatively good result. © 2022 IEEE.

关键词： Genetic algorithms

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：