检索结果-内蒙古大学图书馆

UAV maneuvering decision-making algorithm based on deep reinforcement learning under the guidance of expert experience

引用

Journal of Systems Engineering and electronics 2024年第3期35卷 644-665页

作者： ZHAN Guang ZHANG Kun LI Ke PIAO Haiyin School of Electronics and Information Northwestern Polytechnical UniversityXi’an 710072China Science and Technology on Electro-Optic Control Laboratory Luoyang 471009China

Autonomous umanned aerial vehicle(UAV) manipulation is necessary for the defense department to execute tactical missions given by commanders in the future unmanned battlefield. A large amount of research has been devoted to improving the autonomous decision-making ability of UAV in an interactive environment, where finding the optimal maneuvering decisionmaking policy became one of the key issues for enabling the intelligence of UAV. In this paper, we propose a maneuvering decision-making algorithm for autonomous air-delivery based on deep reinforcement learning under the guidance of expert experience. Specifically, we refine the guidance towards area and guidance towards specific point tasks for the air-delivery process based on the traditional air-to-surface fire control ***, we construct the UAV maneuvering decision-making model based on Markov decision processes(MDPs). Specifically, we present a reward shaping method for the guidance towards area and guidance towards specific point tasks using potential-based function and expert-guided advice. The proposed algorithm could accelerate the convergence of the maneuvering decision-making policy and increase the stability of the policy in terms of the output during the later stage of training process. The effectiveness of the proposed maneuvering decision-making policy is illustrated by the curves of training parameters and extensive experimental results for testing the trained policy.

关键词： unmanned aerial vehicle(UAV) maneuvering decision-making autonomous air-delivery deep reinforcement learning reward shaping expert experience

来源：评论

学校读者我要写书评

暂无评论

Dynamic event-triggered fault-tolerant cooperative resilient tracking control with prescribed performance for UAVs

引用

science China(Information sciences) 2024年第8期67卷 67-84页

作者： Rong YUAN Zhengcai AN Shuyi SHAO Mou CHEN Mihai LUNGU College of Automation Engineering Nanjing University of Aeronautics and Astronautics Science and Technology on Electro-optic Control Laboratory Faculty of Electrical Engineering University of Craiova Aerospace Engineering Doctoral School University Politehnica of Bucharest

In this paper, a resilient tracking control scheme with cooperative collision avoidance performance is studied for the fixed-wing unmanned aerial vehicle(UAV) leader-follower formation in the presence of actuator failures and external disturbances. Firstly, based on the control objectives of UAV formation tracking and collision avoidance, the transformation tracking errors are obtained using the prescribed performance control technique. Next, a fault detection mechanism is introduced to determine if there is the actuator fault. Subsequently, the event-triggered resilient fault observers are designed based on a dynamic eventtriggered mechanism to estimate actuator faults. Furthermore, the prescribed performance functions and the H∞ performance index are employed to ensure the UAV formation collision-free and mitigate the impact of disturbances. Moreover, the resilient controller is designed to minimize the effect of the perturbations for the control gain and the fault observer gain on the system. The stability of the system is also proven through the Lyapunov stability analysis, and the controller gains are calculated by solving the linear matrix ***, the validity of the proposed control strategy is demonstrated by the simulation analysis.

关键词： UAV formation cooperative collision avoidance event-triggered fault observer prescribed performance resilient control

来源：评论

学校读者我要写书评

暂无评论

Design Method of Off-axis Infrared Television Composite optical System for Seekers

Design Method of Off-axis Infrared Television Composite Opti...

引用

2024 Applied optics and Photonics China: optical Sensing, Imaging technology, and Applications, AOPC 2024

作者： Tang, Changzheng Zhang, Hao Li, Anran Pang, Yibo Science and Technology on Electro-optic Control Laboratory Luoyang471000 China Luoyang Institute of Electro-optical Equipment Luoyang471000 China

ISBN: (数字)9781510687820

ISBN: (纸本)9781510687813

In the traditional coaxial infrared television optical system, the central aperture of the infrared imaging system will be blocked by the television imaging system, which will cause obvious loss of luminous flux and decrease of diffraction *** television imaging system is in the infrared channel, the infrared and television system size, configuration, performance, assembly will affect each other, which increases the design and assembly difficulty, as well as processing assembly and maintenance *** this paper, an off-axis infrared television composite optical system is designed. The infrared and television systems are decoupled from each other without interference. Two tilt lenses are added in front of the lens to correct the aberration of the television. The results show that the performance of off-axis infrared television composite optical system is better than that coaxial infrared television composite optical system. © 2024 SPIE.

关键词： Infrared television

来源：评论

学校读者我要写书评

暂无评论

optical Design of Transmission/Reflection Common Aperture Infrared/Laser Composite Seeker

Optical Design of Transmission/Reflection Common Aperture In...

引用

2024 Applied optics and Photonics China: optical Sensing, Imaging technology, and Applications, AOPC 2024

作者： Tang, Changzheng Yu, Shaoying Wu, Lequn Science and Technology on Electro-optic Control Laboratory Luoyang471000 China Luoyang Institute of Electro-optical Equipment Luoyang471000 China

ISBN: (数字)9781510687820

ISBN: (纸本)9781510687813

In order to realize the miniaturization and low cost of infrared/laser dual-mode seeker imaging system and simplify the optical system structure, a transmission/reflection common aperture infrared/laser composite seeker optical system is designed. Firstly, the structure, overall scheme and working principle of the system are studied. The optical system uses the common aperture design at the front, and the infrared and laser signals are separated by the spectroscope at the backend to enter the respective detectors[1]. The whole optical system shares the same receiving aperture, the structure is compact, and meets the requirements of miniaturization of the seeker. The system can not only meet the requirements of large field of view in the target searching stage, but also meet the requirements of accurate recognition and tracking of the target. Based on the design metrics and parameters, the infrared optical system and laser optical system are designed and analyzed respectively. Through the analysis of action distance, the aperture and focal length of infrared and semi-active laser subsystems are designed. Simulation results show that the transfer function MTF and optical transmittance of the infrared optical system meet the design requirements, and the spot energy, linear region and optical transmittance of the semi-active laser subsystem meet the requirements. © 2024 SPIE.

关键词： Infrared transmission

来源：评论

学校读者我要写书评

暂无评论

Measurement and Analysis of Infrared Radiation Characteristics of UAV 3

Measurement and Analysis of Infrared Radiation Characteristi...

引用

3rd International Computing Imaging Conference, CITA 2023

作者： Chen, Fupu Zhang, Peng Zheng, Guofeng Wang, Shaofei Luoyang Institute of Electro-Optical Equipment Luoyang471009 China Science and Technology on Electro-optic Control Laboratory Luoyang471009 China

ISBN: (纸本)9781510671409

Studying the infrared radiation characteristics of UAV is of great significance. This paper first completes the radiation calibration of the mid-wave infrared thermal imager, and then conducts multi-angle radiation characteristics tests on the ground static UAV. MODTRAN software is used to calculate the atmospheric transmittance and path radiation, and complete the inversion calculation of the UAV radiant intensity and atmospheric transmission revision. The test results show that the infrared radiation of UAV has directionality, and the radiation characteristics of UAV in the side tail direction are the strongest, which is mainly represented by engine radiation, and the radiant intensity of UAV increases significantly with the acceleration of engine speed. © 2023 SPIE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Measurement of infrared radiation based on real-time calibration of atmospheric correction parameters

Measurement of infrared radiation based on real-time calibra...

引用

2022 Conference on Infrared, Millimeter, Terahertz Waves and Applications, IMT 2022

作者： Chen, Fupu Qi, Tao Wang, Shaofei Zhang, Peng Luoyang Institute of Electro-Optical Equipment Luoyang471009 China Science and Technology on Electro-Optic Control Laboratory Luoyang471009 China

ISBN: (纸本)9781510662476

Infrared radiation characteristic measurement uses the infrared thermal imager that has been calibrated to measure and invert the infrared radiation characteristics of the target , which is a direct method to obtain the real radiation characteristics of the target. This paper proposes a method for infrared radiation characteristics based on real-time calibration of atmospheric correction parameters. This method first completes the radiation calibration of the long-wave thermal imager, then uses the surface blackbody as the standard radiation source, and uses the long-wave thermal imager to obtain the actual atmospheric transmittance. By establishing an exponential model, the correction factor between the theoretical atmospheric transmittance calculated by MODTRAN and the measured atmospheric transmittance is obtained, and the theoretical atmospheric transmittance calculated by MODTRAN is corrected by this correction factor, so that the measurement and inversion of the infrared radiation characteristics of the target to be measured can be realized. The experimental results show that the error of the target characteristic measurement result obtained by this method is less than 5%, which is higher than the traditional target radiation characteristic measurement accuracy obtained by directly using MODTRAN to correct the influence of atmospheric transmission. © 2023 SPIE.

关键词： Infrared radiation

来源：评论

学校读者我要写书评

暂无评论

Anchor-Free and Pixel-Wise Convolution for Visual Tracking

Anchor-Free and Pixel-Wise Convolution for Visual Tracking

引用

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Luo, Yihang Zhao, Zhenyu Hu, Yinji Jie, Feiran Science and Technology on Electro-Optical Control Laboratory Luoyang471000 China Luoyang Institute of Electro-Optic Equipment AVIC Luoyang471000 China

ISBN: (纸本)9789811966125

Most of the existing trackers usually rely on a multi-scale searching schemes or predefined anchor boxes to accurately estimate the scale and aspect ratio of objects. However, this operation requires tedious and heuristic configurations to obtain ideal results, which is inefficiency. To solve this problem, we introduce an anchor-free and pixel-wise convolution algorithm (named SiamAPF). SiamAPF transforms the tracking problem into a classification problem and a regression problem, and directly performs classification and bounding box regression on the target in fully convolutional network. The proposed network architecture is simple, and does not need to set responsible hyper-parameters. Meanwhile, it can improve the network's ability to express spatial information through pixel-wise convolution. It achieves state-of-the-art performance on the test datasets OTB100, UAV123 and runs at 50 FPS. In order to achieve better engineering applications, we successfully deployed SiamAPF under the NVIDIA Jetson Xavier hardware platform and recorded video for verification. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Cooperative attack–defense decision-making of multi-UAV using satisficing decision-enhanced wolf pack search algorithm

引用

Soft Computing 2024年第17-18期28卷 9575-9586页

作者： Zhou, Tongle Chen, Mou Wang, Yuhui Zhu, Ronggang Yang, Chenguang College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing211106 China Key Laboratory of Avionics System Integrated Technology Shanghai200241 China Science and Technology on Electro-optic Control Laboratory Luoyang Institute of Electro-Optical Equipment of Avic Luoyang471000 China Bristol Robotics Laboratory University of the West of England BristolBS16 1QY United Kingdom

Unmanned aerial vehicles (UAVs) have shown their superiority for applications in complicated military missions. A cooperative attack–defense decision-making method based on satisficing decision-enhanced wolf pack search (SDEWPS) algorithm is developed for multi-UAV air combat in this paper. Firstly, the multi-UAV air combat mathematical model is provided and the attack–defense decision-making constraints are defined. Besides the traditional air combat situation, the capability of UAVs and target information including target type and target intention are all considered in this paper to establish the air combat superiority function. Then, the wolf pack search (WPS) algorithm is used to solve the attack decision problem. To improve efficiency, the satisficing decision theory is employed to enhance the WPS to obtain the satisficing solution rather than optimal solution. The simulation results show that the developed method can realize the cooperative attack decision-making. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Research on Ballistic Planning Method Based on Improved DDPG Algorithm

Research on Ballistic Planning Method Based on Improved DDPG...

引用

2023 International Conference on Cyber-Physical Social Intelligence, ICCSI 2023

作者： Xue, Shuai Han, Yun Bai, Hongyang Nanjing University of Science and Technology School of Energy and Power Engineering Nanjing China Science and Technology on Electro-Optic Control Laboratory Luoyang Institute of Electro-Optical Equipment Cavic Luoyang China

ISBN: (纸本)9798350312492

Aiming at the ballistic planning problem given the target position indication under the condition of satisfying the missile capability boundary and process constraints, an improved deep deterministic policy gradient (DDPG) algorithm is proposed. This method solves the problems of the traditional trajectory planning method, such as strong dependence on model, low adaptability to environment and lack of real-time performance. The agent is firstly trained by this algorithm at the initial stage in a simple environment through a guided training based on the slow training speed of deep neural network, and then the generated strategy is adopted as an initial strategy for retraining. In the process, the sampling strategy of experience-first playback is applied to the gradient algorithm of deep deterministic strategy, and the Ornstein-Uhlenbeck (OU) noise model is employed for increasing the exploration ability of the agent. Then, this work develops a comprehensive simulation model according to an actual environment, where an improved DDPG method is thus introduced into the ballistic planning field by combining with performance indicators for planning and the trajectory can also meet the constraints. In order to verify the effectiveness of this method, the Gaussian pseudo-spectrum method is also used to compare with the proposed method in this paper. The simulation results show that the ballistic planning time of this improved algorithm is only within 10ms, which is about 8 times shorter than that of Gaussian pseudo-spectrum method. The corresponding ballistics that satisfy the constraints can be quickly generated, which has a good convergence and robustness, and is also suitable for solving online ballistic planning problems. © 2023 IEEE.

关键词： Ballistics

来源：评论

学校读者我要写书评

暂无评论

Graph Influence Maximization Algorithm Based on Reinforcement Learning-PPO Algorithm 18th

Graph Influence Maximization Algorithm Based on Reinforcemen...

引用

18th Chinese Intelligent Systems Conference, CISC 2022

作者： Zhang, Wenxin Ma, Yaofei Science and Technology on Electro-optic Control Laboratory Beihang University Beijing100191 China

ISBN: (纸本)9789811962028

Information dissemination in social network has gained great attention in the study of complex networks. In this paper, we propose a novel network influence maximization algorithm incorporating graph representation learning and reinforcement learning, called RL-PPO, to select a set of seed nodes as the starter nodes and by which the information can be propagated as fast as could in the network,i.e., reaching the status of influence maximization. This algorithm take the feature matrix and adjacency matrix of the network as inputs, and the seed nodes as *** better represent the network, the graph representation learning method is employed to extract network features and to perform feature aggregation. The experiment results show that, compared with the traditional greedy algorithm, the seed nodes determined by this proposed algorithm GraphPPO exhibited higher propagation efficiency. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Complex networks

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：