检索结果-南通市图书馆

Classification of Fog Situations Based on Gaussian Mixture Model 36

在线全文

学校读者我要写书评

暂无评论

Classification of Fog Situations Based on Gaussian Mixture M...

Reinforcement Learning Based Data Fusion Method for Multi-Sensors

第36届中国控制会议

作者： Jinjin Wan Zhenan Qiu Haifeng Gao Feiran Jie Qunnie Peng Science and Technology on electro-optical Control Laboratory luoyang institute of electro-optical equipment AVIC

ISBN: (纸本)9781538629185

In this paper,a learning approach is proposed to classify the fog situations into no fog,fog and dense fog three *** vectors designed according to the contrast and details of foggy images are extracted to form the training *** using the Gaussian Mixture Model to model the probability density of three situations and learning the parameters of the model with the expectation maximization algorithm,the cluster center as well as the model parameters can be well *** results show that the proposed approach performs well in all situations and is feasible and effective in fog situations recognition.

关键词： fog image non fog image unsupervised learning feature extraction

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2020年第6期7卷 1489-1497页

作者： Tongle Zhou Mou Chen Jie Zou College of Automation Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China IEEE Science and Technology on electron-Optic Control Laboratory Luoyang Institute of Electro-Optical Equipment of AvicLuoyang 471023China

In order to improve detection system robustness and reliability, multi-sensors fusion is used in modern air combat. In this paper, a data fusion method based on reinforcement learning is developed for multi-sensors. Initially, the cubic B-spline interpolation is used to solve time alignment problems of multisource data. Then, the reinforcement learning based data fusion(RLBDF) method is proposed to obtain the fusion results. With the case that the priori knowledge of target is obtained, the fusion accuracy reinforcement is realized by the error between fused value and actual value. Furthermore, the Fisher information is instead used as the reward if the priori knowledge is unable to be obtained. Simulations results verify that the developed method is feasible and effective for the multi-sensors data fusion in air combat.

关键词： Air combat cubic B-spline interpolation data fusion reinforcement learning

Barium Gallogermanate Glass Ceramics for Infrared Applications

在线全文

学校读者我要写书评

暂无评论

Journal of Materials Science & Technology 2010年第6期26卷 558-563页

作者： Bin Tang Yi Wang Youyu Fan Long Zhang Shanghai institute of Optics and Fine Mechanics Chinese Academy of Sciences Shanghai 201800 China Graduate School of Chinese Academy of Sciences Beijing 100029 China luoyang institute of electro-optical equipment of avic Luoyang 471009 China

The germanate glass ceramics is a potential candidate material for infrared （IR） dome and window applications. The crystallization mechanism of 20BaO-10Ga2O3-70GeO2 glass was investigated by differential thermal analysis （DTA）, scanning electron microscopy （SEM） and X-ray diffraction （XRD）. Two different types of phase evolution were found in the early stage of crystallization：（1） the further growth of the microcrystal formed during the slow cooling of glass melt and （2） the glass-in-glass phase separation. The controlled crystatlization was obtained by two-step heat treatment. obtained, with expected thermal and mechanical The middle infrared （MIR）-transparent glass ceramics were improvements.

关键词： Germanate glass Crystallization Infrared Window and dome

Autonomous air combat decision-making of UAV based on parallel self-play reinforcement learning

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2023年第1期8卷 64-81页

作者： Bo Li Jingyi Huang Shuangxia Bai Zhigang Gan Shiyang Liang Neretin Evgeny Shouwen Yao School of electronics Information Northwestern Polytechnical UniversityXi'anChina avic luoyang electro-optical equipment Research institute LuoyangChina Moscow Aviation institute 4 Volokolamskoe HighwayMoscowRussia School of Mechanical Engineering Beijing Institute of TechnologyBeijingChina

Aiming at addressing the problem of manoeuvring decision-making in UAV air combat,this study establishes a one-to-one air combat model,defines missile attack areas,and uses the non-deterministic policy Soft-Actor-Critic(SAC)algorithm in deep reinforcement learning to construct a decision model to realize the manoeuvring *** the same time,the complexity of the proposed algorithm is calculated,and the stability of the closed-loop system of air combat decision-making controlled by neural network is analysed by the Lyapunov *** study defines the UAV air combat process as a gaming process and proposes a Parallel Self-Play training SAC algorithm(PSP-SAC)to improve the generalisation performance of UAV control *** results have shown that the proposed algorithm can realize sample sharing and policy sharing in multiple combat environments and can significantly improve the generalisation ability of the model compared to independent training.

关键词： air combat decision deep reinforcement learning parallel self-play SAC algorithm UAV

Causal reasoning in typical computer vision tasks

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2024年第1期67卷 105-120页

作者： ZHANG KeXuan SUN QiYu ZHAO ChaoQiang TANG Yang Key Laboratory of Advanced Control and Optimization for Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237China National Key Laboratory of Air based Information Perception and Fusion Luoyang 471000China luoyang institute of electro optical equipment of avic Luoyang 471000China

Deep learning has revolutionized the field of artificial *** on the statistical correlations uncovered by deep learning-based methods,computer vision tasks,such as autonomous driving and robotics,are growing *** being the basis of deep learning,such correlation strongly depends on the distribution of the original data and is susceptible to uncontrolled *** the guidance of prior knowledge,statistical correlations alone cannot correctly reflect the essential causal relations and may even introduce spurious *** a result,researchers are now trying to enhance deep learningbased methods with causal *** theory can model the intrinsic causal structure unaffected by data bias and effectively avoids spurious *** paper aims to comprehensively review the existing causal methods in typical vision and visionlanguage tasks such as semantic segmentation,object detection,and image *** advantages of causality and the approaches for building causal paradigms will be *** roadmaps are also proposed,including facilitating the development of causal theory and its application in other complex scenarios and systems.

关键词： causal reasoning computer vision tasks vision-language tasks semantic segmentation object detection

同方期刊数据库

Experimental demonstration of suppressing residual geometric dephasing

在线全文

学校读者我要写书评

暂无评论

Science Bulletin 2019年第23期64卷 1757-1763页

作者： Jin-Ming Cui Ming-Zhong Ai Ran He Zhong-Hua Qian Xiao-Ke Qin Yun-Feng Huang Zheng-Wei Zhou Chuan-Feng Li Tao Tu Guang-Can Guo CAS Key Laboratory of Quantum Information University of Science and Technology of ChinaHefei 230026China CAS Center For Excellence in Quantum Information and Quantum Physics University of Science and Technology of ChinaHefei 230026China luoyang institute of electro-optical equipment AVICLuoyang 471000China

The geometric phase is regarded as a promising strategy in fault tolerance quantum information processing(QIP) domain due to its phase only depending on the geometry of the path executed. However, decoherence caused by environmental noise will destroy the geometric phase. Traditional dynamic decoupling sequences can eliminate dynamic dephasing but can not reduce residual geometric dephasing, which is still vital for high-precision quantum manipulation. In this work, we experimentally demonstrate effective suppression of residual geometric dephasing with modified dynamic decoupling schemes,using a single trapped171 Ybtion. The experimental results show that the modified schemes can reduce dephasing rate up to more than one order of magnitude compared with traditional dynamic decoupling schemes, where residual geometric dephasing dominates. Besides, we also investigate the impact of intensity and correlation time of the low-frequency noise on coherence of the quantum system. And we confirm these methods can be used in many cases.

关键词： Geometric dephasing Berry phase Dynamic decoupling Ion trap

Manoeuvre decision-making of unmanned aerial vehicles in air combat based on an expert actor-based soft actor critic algorithm

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1608-1619页

作者： Bo Li Shuangxia Bai Shiyang Liang Rui Ma Evgeny Neretin Jingyi Huang School of electronics and Information Northwestern Polytechnical UniversityXi'anChina General department Avic Luoyang Electro-optical Equipment Research InstituteLuoyangChina General department Xi'an Electronic Engineering Research InstituteXi'anChina School of Robotic and Intelligent Systems Moscow Aviation InstituteMoscowRussia

The demand for autonomous motion control of unmanned aerial vehicles in air combat is boosted as taking the initiative in combat appears more and more *** aerial vehicles inability to manoeuvre autonomously during air combat that features highly dynamic and uncertain manoeuvres of the enemy;however,limits their combat capabilities,which proves to be very *** meet the challenge,this article proposes an autonomous manoeuvre decision model using an expert actor-based soft actor critic algorithm that reconstructs empirical replay buffer with expert ***,the algorithm uses a small amount of expert experience to increase the diversity of the samples,which can largely improve the exploration and utilisation efficiency of deep reinforcement *** to simulate the complex battlefield environment,a one-toone air combat model is established and the concept of missile's attack region is *** model enables the one-to-one air combat to be simulated under different initial battlefield *** results show that the expert actor-based soft actor critic algorithm can find the most favourable policy for unmanned aerial vehicles to defeat the opponent faster,and converge more quickly,compared with the soft actor critic algorithm.

关键词： artificial intelligence techniques autonomous drone deep neural networks

Design of Time-constrained Guidance Laws via Virtual Leader Approach

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2010年第1期23卷 103-108页

作者： Zhao Shiyu Zhou Rui Wei Chen Ding Quanxin School of Automation Science and Electrical Engineering Beijing University of Aeronautics and Astronautics Beijing 100191 China National Defense Key Lab of Fire Control Technique Luoyang Institute of Electro-optical Equipment of A VIC Luoyang 471009 China

Guidance problems with flight time constraints are considered in this article. A new virtual leader scheme is used for design of guidance laws with time constraints. The core idea of this scheme is to adopt a virtual leader for real missiles to convert a guidance problem with time constraints to a nonlinear tracking problem,thereby making it possible to settle the problem with a variety of control methods. A novel time-constrained guidance （TCG） law, which can control the flight time of missiles to a prescribed time,is designed by using the virtual leader scheme and stability method. The TCG law is a combination of the well-known proportional navigation guidance（PNG） law and the feedback of flight time error. What＇ s more, this law is free of singularities and hence yields better performances in comparison with optimal guidance laws with time constraints. Nonlinear simulations demonstrate the effectiveness of the proposed law.

关键词： guidance missiles salvo attack time constraint virtual leader

UAV Maneuvering Decision-Making Algorithm Based on Twin Delayed Deep Deterministic Policy Gradient Algorithm

在线全文

学校读者我要写书评

暂无评论

Journal of Artificial Intelligence and Technology 2022年第1期2卷 16-22页

作者： Bai Shuangxia Song Shaomei Liang Shiyang Wang Jianmei Li Bo Neretin Evgeny School of electronics and Information Northwestern Polytechnical UniversityXi’anChina Beijing electro-Mechanical Engineering institute BeijingChina avic luoyang electro-optical equipment Research institute LuoyangChina School of Robotic and Intelligent Systems Moscow Aviation InstituteMoscowRussia

Aiming at intelligent decision-making of unmanned aerial vehicle(UAV)based on situation information in air combat,a novelmaneuvering decision method based on deep reinforcement learning is proposed in this *** autonomous maneuvering model ofUAV is established byMarkovDecision *** Twin DelayedDeep Deterministic Policy Gradient(TD3)algorithm and the Deep Deterministic Policy Gradient(DDPG)algorithm in deep reinforcement learning are used to train the model,and the experimental results of the two algorithms are analyzed and *** simulation experiment results show that compared with the DDPG algorithm,the TD3 algorithm has stronger decision-making performance and faster convergence speed and is more suitable for solving combat *** algorithm proposed in this paper enables UAVs to autonomously make maneuvering decisions based on situation information such as position,speed,and relative azimuth,adjust their actions to approach,and successfully strike the enemy,providing a new method for UAVs to make intelligent maneuvering decisions during air combat.

关键词： air combat DDPG maneuvering decision-making TD3