检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Zhenchang Hao, Mingrui Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

This paper studies a heterogeneous Unmanned Aerial Vehicles (UAVs) cooperative search approach suitable for complex environments. In the application, a fixed-wing UAV drops rotor UAVs to deploy the cluster rapidly. Meanwhile, the fixed-wing UAV works as a communication relay node to improve the search performance of the cluster further. The distributed model predictive control and genetic algorithms are adopted to make online intelligent decisions on UAVs’ search directions. On this basis, a jump grid decision method is proposed to satisfy the maneuverability constraints of UAVs, a parameter dynamic selection method is developed to make search decisions more responsive to task requirements, and a search information transmission method with low bandwidth is designed. This approach can enable UAVs to discover targets quickly, cope with various constraints and unexpected situations, and make adaptive decisions, significantly improving the robustness of search tasks in complex, dynamic, and unknown environments. The proposed approach is tested with several search scenarios, and simulation results show that the cooperative search performance of heterogeneous UAVs is significantly improved compared to homogeneous UAVs. © 2023, CC BY.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Attention-enhanced Relation Network for Few-shot Image Classification 23

Attention-enhanced Relation Network for Few-shot Image Class...

引用

6th International Conference on Image and Graphics Processing, ICIGP 2023

作者： Li, Jinyang Tong, Jiahui Gao, Guangyu Xu, Wenbin School of Computer Science and Technology Beijing Institute of Technology China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Optical Radiation Laboratory Beijing Institute of Environmental Characteristics Beijing100854 China

ISBN: (纸本)9781450398572

Traditional deep learning models firmly rely on a large amount of labeled data during pre-training. Whereas it lacks generalization in the face of unfamiliar categories. Recently, few-shot learning is a hot topic in computer vision to classify unseen classes with limited labels. A representative approach is to extract features from the support and query sets, respectively, and compare similarities via metric learning. However, convolutional neural networks often focus only on a local region and ignore the global region, which severely reduces the accuracy of the matching. Specifically, in this paper, we pile lightweight attention-based blocks in the embedding module, which combines an adaptive kernel size 2D convolutional network with a cross-channel attention mechanism to encode multi-scale features and implicitly increase the receptive field. The SE-relation module chooses to construct learnable non-linear comparators to compare the relationship utilizing channel information. Finally, we show experimental results on standard few-shot testing benchmarks such as mini-ImageNet and tiered-ImageNet to demonstrate effectiveness. © 2023 ACM.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Estimation of smoke echo signal using single-photon lidar 13

Estimation of smoke echo signal using single-photon lidar

引用

13th International Conference on Information Optics and Photonics, CIOP 2022

作者： Zhang, Yinbo Li, Sining Sun, Jianfeng Jiang, Peng Zhou, Shuaijun Zhang, Xin Hou, Yue Zhang, Hailong National Key Laboratory of Science and Technology on Tunable Laser Institute of Opto-Electronic Harbin Institute of Technology Heilongjiang Harbin150001 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China Beijing Aerospace Automatic Control Institute Beijing100854 China

ISBN: (纸本)9781510660632

The non-uniform distribution of smoke and laser spot seriously limits the imaging ability of single-photon lidar through smoke. To this end, based on the collision theory between photons and smoke particles, this paper establishes the time-domain distribution model of scattered photons (Gamma), which considers the lidar system parameters and the characteristics of smoke particles. The shape parameter and inverse scale parameter are defined as the maximum scattering number K and the average scattering number β, respectively. The indoor test effectively illustrates the estimation ability of the model for smoke. The parameter estimation results show that the average scattering number β and the maximum scattering number K increase linearly with the increase of attenuation coefficient. This study is of great significance for the suppression of smoke backscattering and is expected to improve the weather adaptability of single-photon lidar. © 2022 SPIE.

关键词： Backscattering

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Image Matching Algorithm Based on Structure Feature 1

引用

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Wang, Xing Zhao, Jiajia su, Ang Guan, Banglei Dong, Jing Han, Songlai Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China College of Aerospace Science and Engineering National University of Defense Technology Changsha410073 China Research Institution of Aerospace Technology Central South University Changsha410083 China

ISBN: (数字)9789811966132

ISBN: (纸本)9789811966125

Multimodal image matching is a crucial technique for aircraft navigation in GPS denied environment. However, the nonlinear radiometric difference between multimodal images and significant image noise make this task considerably challenging. A multimodal image registration algorithm build on structural features is presented. The method can also accurately extract structural features in the case of severe noise distortion. Besides, A similarity measure method based on parallelism is presented for adapting nonlinear grayscale distortion. The evaluation show that the algorithm has significant superiority over other state-of-the-art algorithms. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Quantitative evaluation modeling of mobile Ad Hoc networkcommunication service availability under failure|

引用

International Journal of Modeling, Simulation, and Scientific Computing 2020年第6期11卷 250-267页

作者： Yanfang Fu Yichang Su Zan Wang Dengdeng Guo Fei Dai Lianjiong Zhong Jianing Wei Xi’an Technological University State and Provincial Joint Engineering Lab.of Advanced Network Monitoring and Control Xi’an 710021P.R.China Beijing Electromechanical Engineering Institute Beijing 100074 P.R.China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing 100074 P.R.China

The availability of network communication services is an important evaluation standard to measure the ability of the network to meet the user’s business *** current related research mostly focuses on the evaluation of network reliability,which cannot reflect the logical relationship between failure/maintenance and network performance *** Ad Hoc Network is a multi-hop,centerless and energy-constrained distributed *** to the dynamic change of communication environment and the instability of wireless link,Ad Hoc Network is facing great challenges in service avail*** this thesis,a fault-based quantitative evaluation model of traffic availability in Ad Hoc networks is *** studying the multi-state Markov fault model of communication networks and the performance analysis of delay index based on CSMA\CA protocol,the quantitative evaluation of traffic availability in Ad Hoc networks is *** the availability of tactical unit network under different typical network configuration conditions is analyzed through experiments.

关键词： Network reliability service availability fault model quantitative evaluation

来源：评论

学校读者我要写书评

暂无评论

Vehicle detection based on point cloud intensity and distance clustering 5

Vehicle detection based on point cloud intensity and distanc...

引用

2020 5th International Seminar on Computer technology, Mechanical and Electrical Engineering, ISCME 2020

作者： Wang, Zhao Wang, Xing Fang, Bin Yu, Kun Ma, Jie School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China National Key Laboratory of Multispectral Information Processing Technology Huazhong University of Science and Technology Wuhan430074 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

In the intelligent transportation system, vehicle detection is one of the essential technologies in obstacle avoidance and navigation, however the existing vehicle detection methods cannot meet the actual needs. This paper presents a vehicle detection method combines the intensity and distance information of point cloud, which improves the segmentation performance of nearby objects. Specifically, the data of point cloud collected by lidar is preprocessed first. Then the processed point cloud is clustered by combining its coordinate and intensity information. Finally, the clustered suspected targets are fed to the random forest classifier. Our method can efficiently detect and classify targets in large-scale disordered 3D point cloud with high accuracy. In the real-scanned Livox Mid-40 Lidar dataset, our proposed method improves the detection accuracy by 31% compared with the traditional Euclidean clustering. © Published under licence by IOP Publishing Ltd.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

A Cooperative Position Method of Two Aircraft Under the Condition of Giant Inertial Dispersion 11th

A Cooperative Position Method of Two Aircraft Under the Cond...

引用

11th China Conference on Command and control, C2 2023

作者： Peng, Siting Li, Lei Ren, Jun Zhu, Hongbo Yang, Jiabin Beijing Electro-Mechanical Engineering Institute Beijing100074 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China School of Electronics and Information Engineering Beihang University Beijing China

ISBN: (纸本)9789819990207

In this paper, based on the condition that the inertial navigation system loaded on the aircraft has giant dispersion, and the aircraft need to detect, track and attack a target, thus the relative position relation needs to be calculated precisely. How to estimate the problem becomes a difficult obstacle. This article describe the demand faced in the weapon engineer field and provide some solutions feasibly in the practical engineering, three mathematical method are modelled and the readers can choose the suitable scheme according to the detector performance. The un-linear filter method like unscented and cubature kalman filter are used in combination with the state and observation equation. The simulation results show that the modelling methods are observable and the filter method is adaptive to the motion method, therefore the algorithm elaborated in the thesis is of practical significance to the engineer project. © Chinese Institute of Command and control 2024.

关键词： Aircraft

来源：评论

学校读者我要写书评

暂无评论

Research on Key Technologies of Cross-domain Guidance 8

Research on Key Technologies of Cross-domain Guidance

引用

8th Symposium on Novel Photoelectronic Detection technology and Applications

作者： Guo, Xiaoyun Wu, Chengfeng Fang, Xueli Xu, Cheng Li, Hui Beijing Institute of Mechanical and Electrical Engineering Beijing China Beijing Institute of Mechanical and Electrical Engineering Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory Beijing China Beijing Institute of Mechanical and Electrical Engineering Key Laboratory of Complex Aviation Simulation System Beijing China

ISBN: (数字)9781510653122

ISBN: (纸本)9781510653115

Cross-domain synergy and intelligence will become important features of future warfare. Cross-domain guidance is one of the typical forms of cross-domain synergy. It can significantly improve the ability to respond quickly to random targets and time-sensitive targets and enhance the anti-jamming ability in the case of confrontation. This article introduces the concept and winning mechanism of cross-domain guidance, analyzes the research progress of cross-domain guidance at home and abroad, combs the key technologies of cross-domain guidance, summarizes the current challenges and problems in cross-domain guidance research, and proposes development suggestions. © 2022 SPIE

关键词： Optical engineering

来源：评论

学校读者我要写书评

暂无评论

A Parallel Mapping and Planning Strategy for Micro Aerial Vehicle

引用

Guidance, Navigation and control 2022年第2期2卷 125-145页

作者： Zhuo Wang Qun Zong Hongming Shen Bailing Tian Hanchen Lu School of Electrical and Information Engineering Tianjin UniversityTianjin 300072P.R.China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute Beijing 100083P.R.China

Autonomous fight is a fundamental problem for various saplications of miaro aerial vehicles(MAVs).Thanks to the dewvelopment of *** and control(GNC)techndogle,the rsearch on this problem i abo becoming ***,safe fight in unknown,dut tered enviouments remains an open question,epeaially with real-time reguirement on onboard *** paper propoes a framnework including prlelly mapping and planning and implements it on Graphics Pmocessing Unit(GPU).First,a spherical coomlinate proijection is used in the ocupency grid map to avold menory *** that,in the planning phase,a method baed on latice state space sampling is applied to obtain mutiple rajectorfe ***,we design a series of aoft constraints to ensure that the MAV is in a safe known space with optimal *** solving the cost for each trajectory and comparison,the optimal trajectory can be *** efectivenes of the propeed strategy is demonstrated through simulation testa.

关键词： Motion planning lattice planner parallel processing

来源：评论

学校读者我要写书评

暂无评论

Practical Distance-Based Formation Stabilization and Tracking of Nonholonomic Multi-agent systems 7th

Practical Distance-Based Formation Stabilization and Tracki...

引用

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

作者： Tang, Xiangyu Yu, Jianglong Dong, Xiwang Yang, Xiangyu Ren, Zhang School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789819733279

This paper investigates practical distance-based formation stabilization and tracking issues for nonholonomic multi-agent systems (MASs). Firstly, the agent’s nonholonomic kinematics is represented as a left invariant system on a Lie group. Through the introduction of an auxiliary state and a virtual control guided by the transverse function method, the original system is effectively converted into a fully actuated one. Secondly, under the assumption of infinitesimal and minimal rigidity in the graph, a gradient-descent-based virtual controller is devised for the transformed MASs, facilitating practical rigid formation stabilization. Thirdly, a discontinuous distributed velocity estimator is designed for formation tracking. The nonholonomic MASs achieve the desired formation shape while effectively tracking the reference trajectory. Finally, the effectiveness of the proposed method is verified by numerical examples. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Multi agent systems

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：