检索结果-内蒙古大学图书馆

A survey of few shot learning based on intelligent perception

Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica 2020年 41卷

作者： Song, Chuang Zhao, Jiajia Wang, Kang Liang, Xinkai Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China School of Computer and Technique Fudan University Shanghai200433 China

Few-shot learning refers to using only a small amount of supervision information of the target class to train the machine learning model. Due to its practical values, recent advances in few-shot learning by academia and industry have made significant contributions. However, there were few reviews on this issue in China. This paper systematically summarizes and explores the few-shot learning algorithms and the object detection algorithms based on few-shot learning. Firstly, the problem definition of few-shot learning is given, and its connections with other classic machine learning problems are also enumerated. Meanwhile, the theoretical challenges of the problem of few-shot learning are explained. Then, we summarize the image classification based on few-shot learning, and analyze its representative works. Based on this, we focus on the problem of few-shot object detection, especially the problem of zero-shot object detection, and analyze the existing research works in detail. Finally, we look forward to the future development of few-shot learning in terms of problem setting, theoretical research, implementation technology, and application scenarios based on the advantages and disadvantages of the existing methods. It is expected to provide inspirations for the subsequent research works in this field. © 2020, Beihang University Aerospace Knowledge Press. All right reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Cross-cycle iterative unmanned aerial vehicle reentry guidance based on reinforcement learning

Cross-cycle iterative unmanned aerial vehicle reentry guidan...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Yang Cheng Zunshi Shui Cheng Xu Tianyu Feng Yiyang Jiang Beijing Aerospace Technology Research Institute Beijing China Science and technology on complex system control and intelligent agent cooperation laboratory Beijing China

The traditional predictive correction algorithm requires a large number of iterative calculations for the predicted trajectory, which greatly occupies a large amount of computing resources, so that the real-time solution of the guidance command can not be guaranteed, and the guidance accuracy will have a large impact. And the prediction correction guidance requires the algorithm to have the ability of selfadaptation and intelligent learning. Therefore, this paper proposes a cross-cycle iterative hypersonic UAV predictive correction guidance method based on reinforcement learning. The parametric control variable (CVP) method is used to construct the parametric model of the guidance command. The actor-critic-based reinforcement learning method is used to solve the guidance command in real time, and the guidance information is effectively transmitted in the adjacent guidance solution cycle. The guidance error converges to within the allowable accuracy range during the cross-cycle iteration. Monte Carlo simulation shows that the proposed method has good adaptability to initial conditions and flight parameter uncertainty, and can guarantee the real-time performance of the guidance command while achieving high-precision guidance.

关键词： Trajectory Aircraft Atmospheric modeling Earth Mathematical model Iterative algorithms Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

A Infrared Cloud Image Simulation Method for Cloud Segmentation Network Training

A Infrared Cloud Image Simulation Method for Cloud Segmentat...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Hang Qi Jianquan Yuan Lei Li Jun Ren Jie Liang Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Institute of Mechanical and Electrical Engineering Beijing China

ISBN: (数字)9780996007894

ISBN: (纸本)9781728146331

Due to the difficulty of acquiring real aerial infrared cloud images, we propose an efficient way to set up cloud simulation data set by particle system and texture synthesis, in order to alleviate the problem of data shortage. The deep network for cloud segmentation is trained on our simulation image data set, substantially decreasing the demand for real aerial cloud images. When testing on the real image data set, a satisfactory segmentation result with 79.64% has been reached which can meet the usage requirements. Our method can make the deep cloud segmentation network training feasible despite of the real image shortage, reducing the cost of data acquisition.

关键词： Clouds Image segmentation Data models Training Shape Image edge detection Force

来源：评论

学校读者我要写书评

暂无评论

Attitude control of hypersonic vehicle based on optimized ADRC 8

Attitude control of hypersonic vehicle based on optimized AD...

引用

8th IEEE Data Driven control and Learning systems Conference, DDCLS 2019

作者： Piao, Minnan Sun, Mingwei Huang, Jian Wang, Zenghui Chen, Zengqiang Science and Technology on Complex System Control Intelligent Agent Cooperation Laboratory Beijing100074 China College of Artificial Intelligence Nankai University Tianjin300350 China Beijing Automatic Control and Equipment Institute Beijing100074 China University of South Africa Department of Electrical and Mining Engineering Florida1710 South Africa

ISBN: (纸本)9781728114545

In this paper, two types of practical angle of attack control schemes are proposed for hypersonic vehicle which is subject to large unmodeled, parametric uncertainties and external disturbances. In the first scheme, the pitch angle control method based on the second-order linear active disturbance rejection control is directly applied to the angle of attack control through simple command transformation. Inner-loop pitch angular rate feedback is performed first to enhance the damping in the second scheme, and then first-order linear active disturbance rejection control is designed for the overdamped plant. Both schemes provide simple and robust solutions to the angle of attack control. To achieve desired stability and performance robustness, non-smooth $H-{\infty}$ synthesis technique is utilized to optimize the controller within the designed flight envelope. Nonlinear simulations are performed to validate the advantages of the proposed methods. © 2019 IEEE.

关键词： Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

3-D Velocity Estimation for Moving Targets Based on InISAR with Orthogonal Baselines

3-D Velocity Estimation for Moving Targets Based on InISAR w...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Meng Ma Guangzhou Qu Youcheng Wang Hucheng Pei Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9780996007894

ISBN: (纸本)9781728146331

In this paper, we proposed a novel approach to estimate target 3-D velocity based on InISAR system with orthogonal baselines. For targets with slow maneuverability, the target movement can be approximated to uniform linear motion during a short coherent processing interval (CPI). By introducing SAR imaging method into ISAR and utilizing the projection relationship between target velocity and the orthogonal baselines, the proposed method can obtain target 3-D velocity without radar line of sight (LOS) information. Simulation analysis verified the effectiveness of the new approach.

关键词： Imaging Estimation Radar imaging Antennas Radar tracking Doppler effect

来源：评论

学校读者我要写书评

暂无评论

Finite Time Cooperative Guidance Law for Multiple UAVs with Intermittent Communication Topologies

Finite Time Cooperative Guidance Law for Multiple UAVs with ...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Teng LYU Cheng XU Hongchun LI Song HU Daochi ZHANG Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Beijing Electro-mechanical Engineering Institute Beijing China

ISBN: (纸本)9781728137933

To solve the problem of multiple Unmanned Aerial Vehicles (UAVs) with intermittent communication topologies simultaneously attack a stationary target, a time cooperative guidance law is studied in this paper. First, a novel time cooperative guidance model for multiple UAVs is constructed based on UAVs-target relative motion equations. Then, a cooperative guidance law is designed based on consensus theory, which can ensure multiple UAVs' impact times realize finite time consensus under intermittent topologies. After UAVs' impact times become to be the same, traditional PN guidance law is applied in all UAVs to guarantee that the UAVs can attack the target precisely without influencing the consensus of impact times. Finally, the validity of the proposed method is shown by numerical simulations.

关键词： Multiple UAVs Cooperative guidance Intermittent communication topologies Finite time consensus Unmanned Aerial Vehicle Guidance

来源：评论

学校读者我要写书评

暂无评论

Time consistency technique of multi-aircrafts simulation system for cooperative mission

Time consistency technique of multi-aircrafts simulation sys...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Jian Han Hang Shi JiaHui Tong Qing Zhang Jing Li Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

Aiming at the problem of time inconsistency problem exposed in multi-aircrafts simulation system during executing cooperative mission, a control solution of time consistency has been proposed to realize the unity of time information. On the basis of thoroughly analyzing the components and features of system, the factors that affect time synchronization are summarized and classified. After embedding a hardware of time synchronization system, a control solution is devised to maintain time consistency. Time synchronization and delay compensation are achieved from two aspects of hardware and software, which provides technical support for the following development and verification of cooperative control technology based on multiaircrafts simulation system.

关键词： Cascading style sheets Synchronization Delays Clocks Benchmark testing Delay effects

来源：评论

学校读者我要写书评

暂无评论

Optimal linear-quadratic guidance law considering autopilot first-order lag with terminal acceleration constraint

Optimal linear-quadratic guidance law considering autopilot ...

引用

Asia-Pacific International Symposium on Aerospace technology, APISAT 2018

作者： Zheng, Duo Xu, Xinghua Yan, Ruyi Lin, Defu Beijing Electro-Mechanical Engineering Institute Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China Beijing Institute of Automatic Control Equipment Beijing100074 China Unit 95806 PLA Air Force Beijing100070 China School of Aerospace Engineering Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9789811333040

In this paper, a new optimal linear-quadratic guidance law with terminal acceleration constraints is proposed for intercepting maneuvering target. Because the angle of attack is approximately proportional to the normal acceleration for aerodynamic control missile, not only miss distance, but also terminal acceleration is required to converge to zero for increasing effectiveness of the warhead for destroying armored target in the proposed guidance law. The gain characteristic of proposed guidance law is studied by comparing with traditional optimal guidance law with considering autopilot dynamics lags. Numerical simulations are performed to examine performance of the proposed optimal guidance law, and its robustness with respect to the time constant of autopilot dynamic lags is also studied by considering time constant typical errors. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Angle of attack

来源：评论

学校读者我要写书评

暂无评论

Zero-attracted Lorentzian Algorithm for system Identification

Zero-attracted Lorentzian Algorithm for System Identificatio...

引用

Progress in Electromagnetics Research Symposium - Fall (PIERS - FALL)

作者： Yanyan Wang Qingxi Chi Xin Wang Yunong Bu Xujun Guan Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Beijing Electro-Mechanical Engineering Institute Beijing China

ISBN: (数字)9781728153049

ISBN: (纸本)9781728153056

In this paper, a zero attracted Lorentzian (ZAL) algorithm is created for system identification applications. The proposed ZAL algorithm is realized by using l 1 -norm penalty on the Lorentzian-based cost function to exploit the sparseness of the existing nature signals. Moreover, a reweighting method is adopt to enhance the ability of the proposed ZAL algorithm, and the new algorithm is called as reweighting zero attracted Lorentzian (RZAL) algorithm. The proposed algorithms are presented briefly and investigated via computer simulations. The gotten results from the simulation demonstrate that the proposed algorithms are superior to the popular adaptive filtering algorithms under alpha-stable noise interference.

关键词： Signal processing algorithms Cost function Adaptive systems Mathematical model Photonics Electromagnetics Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Cooperative collision avoidance method for multi-UAV based on kalman filter and model predictive control

Cooperative collision avoidance method for multi-UAV based o...

引用

2019 IEEE International Conference on Unmanned systems and Artificial Intelligence, ICUSAI 2019

作者： Huang, Hanqiao Zhou, Huan Zheng, Meiyun Xu, Cheng Zhang, Xiaofeng Xiong, Wei Unmanned System Research Institute Northwest Polytechnical University Xi'an China Aeronautical Engineering College Air Force Engineering University Xi'an China School of Marine Science and Technology Northwest Polytechnical University Xi'an China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China UAV Researc Center Army Aviation Institute Beijing China

ISBN: (纸本)9781728158594

Collision avoidance is the primary problem to be solved in formation flight of multiple Unmanned aerial vehicles(UAVs). Firstly, a cooperative collision avoidance architecture of multiple UAVs is designed according to the requirement of autonomous collision avoidance of single UAV. Then a new cooperative collision avoidance method of multiple UAVs based on Kalman filter and model predictive control(MPC) is proposed. In this method, extended Kalman filter(EKF) is used to estimate the state of obstacles and target points in uncertain environment space, and to predict the trajectory of obstacles and target points. At the same time, relevant performance index functions and constraints are set up. On the basis of sharing environmental information, model predictive control strategy is used to guide and make cooperative collision avoidance decisions for multiple UAVs. The simulation results show that the proposed method is effective in uncertain environment perception and UAV collision avoidance, and the cooperative mechanism has obvious advantages. © 2019 IEEE.

关键词： Model predictive 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：