检索结果-内蒙古大学图书馆

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

A cluster positioning architecture and relative positioning algorithm based on pigeon fock bionics

引用

Satellite Navigation 2023年第1期4卷 92-112,I0004页

作者： Zhongliang Deng Hang Qi Chengfeng Wu Enwen Hu Runmin Wang Beijing University of Posts and Telecommunications Beijing 100876China Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory Beijing 100074China.

Unmanned clusters can realize collaborative work,fexible confguration,and efcient operation,which has become an important development trend of unmanned *** positioning is important for ensuring the normal operation of unmanned *** existing solutions have some problems such as requiring external system assistance,high system complexity,poor architecture scalability,and accumulation of positioning errors over *** the aid of the information outside the cluster,we plan to construct the relative position relationship with north alignment to adopt formation control and achieve robust cluster relative *** on the idea of bionics,this paper proposes a cluster robust hierarchical positioning architecture by analyzing the autonomous behavior of pigeon *** divide the clusters into follower clusters,core clusters,and leader nodes,which can realize fexible networking and cluster *** at the core cluster that is the most critical to relative positioning in the architecture,we propose a cluster relative positioning algorithm based on spatiotemporal correlation *** the design idea of low cost and large-scale application,the algorithm uses intra-cluster ranging and the inertial navigation motion vector to construct the positioning equation and solves it through the Multidimensional Scaling(MDS)and Multiple Objective Particle Swarm Optimization(MOPSO)*** cluster formation is abstracted as a mixed direction-distance graph and the graph rigidity theory is used to analyze localizability conditions of the *** designed the cluster positioning simulation software and conducted localizability tests and positioning accuracy tests in diferent *** with the relative positioning algorithm based on Extended Kalman Filter(EKF),the algorithm proposed in this paper has more relaxed positioning conditions and can adapt to a variety of *** also has higher relative positioning accuracy

关键词： Cluster positioning architecture Cluster relative positioning Multidimensional scaling Multiple objective particle swarm optimization Unmanned aerial vehicles positioning Localizability analysis Rigid graph

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

A Formation control Method for Leader-Follower Aircraft Based on Particle Swarm Optimization 3rd

A Formation Control Method for Leader-Follower Aircraft Base...

引用

3rd International Conference on Autonomous Unmanned systems, ICAUS 2023

作者： Zhao, Yuxia Quan, Yanli Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory Beijing100074 China

ISBN: (纸本)9789819710829

As the defense system of military powers is becoming more and more complete, improving the aircraft’s penetration capabilities is particularly critical. Formation control is an effective way to improve the ability of penetration. Based on an uncontrollable situation, this paper proposes an angle-based formation control strategy for multiple aircraft. The leader’s trajectory inclination angle and trajectory deflection angle are used as the states of consistency, and the tilt angle is used as the control volume, to design the PI controller of the follower. The parameter optimization design is performed through the particle swarm optimization (PSO) algorithm. The simulation results show that the proposed angle-based formation control method can be well achieved and maintain the formation. © Beijing HIWING Scientific and Technological Information Institute 2024.

关键词： Aircraft

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

Cooperative Formation control of Fixed-Wing UAV Based on L1 Guidance Law Considering Collision Avoidance 7th

Cooperative Formation Control of Fixed-Wing UAV Based on L1 ...

引用

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

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

ISBN: (纸本)9789819733392

This article proposes a formation control scheme based on L1 guidance law for fixed wing unmanned aerial vehicle clusters while considering collision avoidance issues between them. The fixed wing aircraft cluster adopts L1 guidance and tracking method to track their respective desired waypoints. By controlling the speed of the fixed-wing UAVs, the entire cluster forms a formation configuration on their individual desired trajectories. During the formation and transformation processes, an improved artificial potential field method is proposed based on the characteristics of fixed-wing UAVs to achieve collision avoidance between clusters. The effectiveness of the proposed approach is validated through numerical simulations based on a six-degree-of-freedom nonlinear UAV model, providing a reference for practical engineering applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Fixed wings

来源：评论

学校读者我要写书评

暂无评论

Relative Navigation of Unmanned Aerial Vehicles Based on Data Link Ranging and Partial Guidance Information 1

引用

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

作者： Wang, Ziwen Song, Chuang Hao, Mingrui Liang, Xinkai Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (数字)9789819733323

ISBN: (纸本)9789819733316

In GNSS-denied environments, precise relative navigation between unmanned aerial vehicles (UAVs) is a key technology for achieving cooperative tasks. The relative navigation method based on data link ranging information combines altitude, airspeed measurements, and attitude information to ensure the observability of UAVs’ relative states. However, due to the significant constraints imposed by observability conditions, a novel approach is proposed that utilizes partial guidance information from the UAV swarm towards the target as additional measurements. This approach enhances the observability capability of relative navigation and alleviates the constraints imposed by the observability conditions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Observability

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

Target Tracking Method Based on LSTM-EKF 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)9789819733323

ISBN: (纸本)9789819733316

With the development of science and technology, target tracking technology has been widely used in many fields. Through target tracking technology, the accurate estimation of target state can be obtained, and the perception ability can be effectively improved. However, due to the increasing maneuvering ability of the target, the traditional target tracking algorithm is more and more difficult to meet the requirements of maneuvering target tracking. This article in view of the traditional filtering algorithm based on bayesian theory problems of nonlinear error model, in combination with the advantages of EKF and deep learning, introducing the idea of hybrid data model, puts forward the algorithm of target tracking based on LSTM - EKF, and design a mathematical simulation experiment on the performance of the algorithm is verified. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Cluster Collaborative Search Method Based on Dynamic Adjustment of Parameters 1

引用

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

作者： Si, JiaShuai Hao, MingRui Liu, ZhenChang Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (数字)9789819733361

ISBN: (纸本)9789819733354

In order to improve the ability of unmanned aerial vehicle(UAV) cluster collaborative search and obstacle avoidance, a multi-UAV collaborative search method based on dynamic parameter adjustment is proposed. Firstly, based on the distributed model predictive control (DMPC) model, a collaborative search problem model is designed considering the rapidity of target discovery, the rapidity of covering the task area and the obstacle avoidance between drones. Secondly, the jump grid decision method not only expands the feasible solution of the search decision, but also ensures that the UAV can track the navigation point of the decision smoothly. At last, a dynamic adjustment method of search parameters is proposed, which realizes threat avoidance in collaborative search process by adjusting search parameters online. The simulation results show that the cluster cooperative search method based on dynamic parameter adjustment can fully consider the maneuverability of UAVs and realize threat avoidance during cooperative search, and improve the robustness of the algorithm after some nodes are damaged. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Maneuverability

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：