检索结果-内蒙古大学图书馆

5th International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2024

作者： Zhuang, Yutao National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing China

ISBN: (纸本)9798331528911

In modern warfare, maneuver penetration is an essential aspect of unmanned aerial vehicle (UAV) combat operations. As the capabilities of both offensive and defensive sides continue to improve, the operational patterns of maneuver penetration scenarios are constantly evolving. This paper first introduces the maneuver capabilities and detection characteristics of both offensive and defensive systems in contemporary warfare, providing a macro definition of the maneuver penetration problem. Then, it conducts a survey and analysis of the applications of traditional and new artificial intelligence algorithms in maneuver penetration decision-making. Finally, it discusses the future research directions and challenges of artificial intelligence algorithms in this field and envisions the development of maneuver penetration decision-making. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Optimized Gaussian kernel regression for X-ray pulsar signal profile construction 3

Optimized Gaussian kernel regression for X-ray pulsar signal...

引用

3rd International Conference on Environmental Remote Sensing and Geographic Information Technology, ERSGIT 2024

作者： Dong, Yan Zhuang, Yutao Wang, Ruoning National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing100071 China

ISBN: (纸本)9781510690219

With the continuous advancement of pulsar-based navigation technology, signal processing issues in X-ray pulsar navigation applications have received increasing attention. One of the key factors limiting the improvement of navigation accuracy is the low signal-to-noise ratio (SNR) of epoch-folded profiles. Pulsar profiles contain many important characteristic features, such as pulse shape symmetry and multi-pulse structures. To facilitate further study, it is necessary to reduce noise and obtain high-SNR pulsar profiles. This study addresses this issue by proposing a method for high-precision pulsar profile construction based on optimized Gaussian kernel regression. The constructed profiles are evaluated and analyzed in terms of profile quality and phase information estimation based on the profile. The results show that the SNR of the epoch-folded profiles after denoising is significantly better than that of the original profiles, providing an important reference for signal processing in X-ray pulsar navigation applications. © 2025 SPIE.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Interval analysis for neural networks with application to fault detection

引用

Science China(Information Sciences) 2024年第11期67卷 222-237页

作者： Zhenhua WANG Youdao MA Song ZHU Thach Ngoc DINH Yi SHEN Department of Control Science and Engineering Harbin Institute of Technology National Key Laboratory of Complex System Control and Intelligent Agent Cooperation School of Mathematics China University of Mining and Technology The CEDRIC-Lab Conservatoire National des Arts et Métiers (CNAM)

This paper investigates an interval analysis method for neural networks and applies it to fault detection for systems with unknown but bounded measurement noise. First, a novel interval analysis method is presented, which can compute the bounds of the output of a feedforward neural network subject to a bounded input. By applying the proposed interval analysis method to a network trained with fault-free system data, adaptive thresholds for fault detection are computed. Finally, one can acquire fault detection results via a fault detection strategy. The proposed method can achieve tight bounds of the network output and employ simple operations, which leads to accurate fault detection results and a low computational burden.A numerical simulation and an experiment on an AC servo motor are given to illustrate the effectiveness and superiority of the proposed method.

关键词： interval analysis feedforward neural network fault detection adaptive thresholds

来源：评论

学校读者我要写书评

暂无评论

Linear-quadratic and norm-bounded combined differential game guidance scheme with obstacle avoidance for attacking defended aircraft in three-player engagement

引用

Defence Technology（防务技术） 2024年第12期42卷 136-155页

作者： Xintao Wang Ming Yang Songyan Wang Mingzhe Hou Tao Chao Control and Simulation Center Harbin Institute of TechnologyHarbin 150001China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Harbin 150001China Center for Control Theory and Guidance Technology Harbin Institute of TechnologyHarbin 150001China

A differential game guidance scheme with obstacle avoidance,based on the formulation of a combined linear quadratic and norm-bounded differential game,is designed for a three-player engagement scenario,which includes a pursuer,an interceptor,and an *** confrontation between the players is divided into four phases(P1-P4)by introducing the switching time,and proposing different guidance strategies according to the phase where the static obstacle is located:the linear quadratic game method is employed to devise the guidance scheme for the energy optimization when the obstacle is located in the P1 and P3 stages;the norm-bounded differential game guidance strategy is presented to satisfy the acceleration constraint under the circumstance that the obstacle is located in the P2 and P4 ***,the radii of the static obstacle and the interceptor are taken as the design parameters to derive the combined guidance strategy through the dead-zone function,which guarantees that the pursuer avoids the static obstacle,and the interceptor,and attacks the ***,the nonlinear numerical simulations verify the performance of the game guidance strategy.

关键词： Active defense aircraft Differential game theory Three-player confrontation Energy optimization Acceleration constraint Obstacle avoidance

来源：评论

学校读者我要写书评

暂无评论

Cooperative Search Strategy of Multi-UAVs Based on Hexagonal Grid 7th

Cooperative Search Strategy of Multi-UAVs Based on Hexagonal...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Zhao, Hongyin Hao, Mingrui Zhang, Hang Dong, Xiaofei Liu, Yuting Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9789819733316

Aiming at the cooperative search problem in a wide-area unknown region, a cooperative search strategy of multi-UAVs based on hexagonal grid is proposed for the fairness of decision-making, This strategy is trained by reinforcement learning method, and adopts centralized training and distributed execution, and deals with the dynamic environment problem by fusing pheromone models. Simulation shows that the cooperative search algorithm has the functions of unknown region cooperative search and online threat avoidance replanning. Compared with the square grid training method, the reinforcement learning search algorithm based on the hexagonal grid after training expands the feasible directions in each decision planning cycle, which is more suitable for low-slow-small UAVs, and the performance is more stable after convergence. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Low-Light Image Enhancement Method for Consistency Judgment of Multi-view Multi-target for UAV Swarm 7th

Low-Light Image Enhancement Method for Consistency Judgment ...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Li, WeiXue Song, Chuang Hao, MingRui Zhang, Hang Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789819733392

To address the challenges posed by low-light images in multi-drone detection tasks, which lead to significant differences in target image features across different perspectives and poor accuracy in target association under multiple viewpoints, this paper proposes an enhanced network architecture based on MIRNet for low-light image enhancement. The goal is to improve the stability of target features in multi-view scenarios. By incorporating Sobel convolution to capture target edges and texture features, and by designing a residual contextual block combined with an attention mechanism and a pixel loss function that emphasizes the central region, the model not only acquires richer features but also focuses more on the central region's target characteristics. Experimental results demonstrate that the proposed approach effectively enhances image brightness, contrast, and target texture, exhibiting substantial advantages in both objective and subjective evaluation metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Collaborative Search Method of Heterogeneous UAVs in Gray Area 1

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Wang, Hongmin Bu, Yunong Zhao, Jiajia Hao, Mingrui Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (数字)9789819733323

ISBN: (纸本)9789819733316

A collaborative search planning method based on an information map is proposed for the problem of multi-moving target detection in gray areas using a heterogeneous UAV swarm. This method takes into account the detection probability and false alarm probability of sensors, the heterogeneity and flight constraints of UAVs, and the random movement of targets. The mathematical planning model for the collaborative search of multiple UAVs is built by balancing short-term gain, long-term gain, and coordination gain. An information map for search is designed, incorporating target existence probability, environmental uncertainty, and revisiting pheromones. Different planning schemes are designed based on the heterogeneous characteristics of UAVs. Through numerical simulations in typical collaborative search scenarios, the effectiveness of the proposed method is validated. The simulation results show that the proposed method can make search trajectory decisions for each UAV within seconds. The organic combination of short-term, long-term, and coordination gain can guide the UAV swarm to capture more targets. Comparative simulation results demonstrate that the proposed method can capture more targets with fewer false alarms, effectively improving the task efficiency of heterogeneous multi-UAV collaborative search. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Common Aircraft Formation control Methods and Application Prospects of High Order Fully Actuated system Theory in Aircraft Formation control 7th

Common Aircraft Formation Control Methods and Application Pr...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Liu, Xinyu Hao, Mingrui Fan, Yu Zhen, Yan Yue, keyuan Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789819733279

This article provides a review of formation control for multiple aircrafts. Firstly, several commonly used aircraft formation control methods were introduced, including leader-follower approach, behavior based formation control, virtual structure method, and artificial potential field method. Considering that the controller design of these methods is mostly based on first-order differential equations and state space methods or uses fuzzy theory or neural networks, further solutions are needed in issues such as model accuracy, controller anti-interference, and controller stability analysis. Therefore, this article proposes the possibility of applying high-order fully actuated (HOFA) system theory in aircraft formation control. In response to the nonlinear, coupled, and real-time aircraft formation control problems, the development of HOFA system theory is introduced, and it is pointed out that fully actuated system (FAS) method has outstanding advantages in dealing with nonlinear, time-varying, hysteresis problems. The article summarizes the current research and practice of FAS theory in the field of single aircraft control and multi-spacecraft formation control, and then propose a new idea of designing FAS formation control method for multiple aircrafts. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Aircraft

来源：评论

学校读者我要写书评

暂无评论

A Combat Intention Reasoning Method for Warship Formation Targets Based on Deep Learning 1

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Xu, Hongfeng Zhao, Jiajia Zhang, Hang Jiang, Jixiang Chen, Linxiu Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (数字)9789819733361

ISBN: (纸本)9789819733354

With the rapid development of science and technology, modern war presents the characteristics of mathematics and information. Grasping the operational intention of battlefield targets plays a crucial role in the trend of war. The target of warship formation is an important fighting force in modern war. How to analyze and reason the target’s fighting intention accurately and timely is one of the most important parts of modern battlefield situation cognition system. Aiming at the problems of too strong subjectivity, lack of objectivity and poor model robustness existing in traditional intention reasoning methods, this paper introduces the idea of deep learning data-driven, and takes the electromagnetic, state and formation characteristic information of ship formation targets as input, designs a deep learning-based ship formation target intention reasoning model. The effectiveness of the algorithm is verified by mathematical simulation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Combat Intention Recognition of Aerial Battlefield Targets Based on LSTM 3rd

Combat Intention Recognition of Aerial Battlefield Targets B...

引用

3rd International Conference on Autonomous Unmanned systems, ICAUS 2023

作者： Xu, Hongfeng Zhao, Jiajia Zhang, Hang Jiang, Jixiang Chen, Linxiu Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789819710867

In the course of military operations, the battlefield situation changes rapidly, and the combat time is fleeting. How to quickly and accurately identify the enemy’s combat intention is one of the important preconditions to ensure the commander’s correct command decision and obtain the initiative in the battlefield. In this paper, aiming at the problems of low accuracy and insufficient algorithm robustness of traditional target combat intention recognition methods in air battlefield, a combat intention recognition method based on LSTM is proposed according to the characteristics of sequence and multi-dimension of target characteristic data. Based on the historical and current state characteristics, electromagnetic characteristics and action characteristics of the target obtained by the sensor, the method uses the LSTM network to build the target combat intention recognition model, and learns the changes of the target characteristics through the network model to realize the target combat intention recognition. Simulation results show that the proposed method can effectively improve the accuracy of target combat intention recognition. © Beijing HIWING Scientific and Technological Information Institute 2024.

关键词： Military operations

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：