检索结果-内蒙古大学图书馆

42nd Chinese control Conference, CCC 2023

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

ISBN: (纸本)9789887581543

In the engineering field, there is a requirement for re recognition, including the identity recognition of cooperative and non-cooperative targets, that is, different sensors shoot targets in the same scene, and the identity recognition of targets from two perspectives is required, also known as target accurate retrieval. This method is widely used in fields such as automatic driving and military strikes. In the actual application scenario, deploying the re-recognition algorithm on the embedded processor needs to ensure the real-time computing speed and accuracy, so the complexity of the deep learning algorithm must be reduced, and pruning and lightweight processing are required. In the engineering field, when the image acquired by the sensor is subject to natural interference such as cloud and fog weather or fire and smoke, the difficulty of re-recognition increases. This paper adopts the lightweight improvement of ConvNeXt network model, and fine-tuned it on the basis of its original feature extraction function, so that it can successfully migrate to infrared image classification and also complete the extraction of infrared image target detail distinguishing features, and at the same time introduce the alignment of similar targets in infrared cross-view recognition. In the original similarity calculation, the average value is directly obtained from the spatial dimension of the output feature layer, which is replaced by the weight of the position in each space for estimation. The feature information of the multi-view marine ship target is extracted from the multi-sensor marine image, and its similarity is calculated, so as to determine the identity, thus reducing the support conditions and reconnaissance costs, and improving the accurate detection and tracking ability under the diverse dynamic reconnaissance conditions. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Tightly-Coupled Lidar-Visual-Inertial Odometry and Mapping in Real Time 42

Tightly-Coupled Lidar-Visual-Inertial Odometry and Mapping i...

引用

42nd Chinese control Conference, CCC 2023

作者： Ma, Wenyu Tian, Bailing Lu, Hanchen Shen, Hongming School of Electrical and Information Engineering Tianjin University Tianjin300072 China Beijing Electro-Mechanical Engineering Institute Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789887581543

We proposed a tightly-coupled Lidar-visual-inertial odometry and mapping method, which takes advantage of measurement of Lidar, visual and inertial sensors to achieve highly accurate, real-time 6DoF state estimation and map-building in GNSS-denied environments. The proposed odometry is a tightly-coupled optimization-based method, obtains robust and low drift odometry by fusing pre-integrated IMU measurements, visual features from the image, and geometric features from Lidar data. Further, we adapt an online method to mitigate degeneracy in optimization problems to improve robustness in environmentally degenerate cases. Simulation and real-world experiments show that the proposed method exhibits similar or better robustness and accuracy with the state-of-the-art SLAM methods. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Static Unstable STT Overload control on High-order Fully Actuated system Theory

Static Unstable STT Overload Control on High-order Fully Act...

引用

International Symposium on Autonomous systems (ISAS)

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

This article proposes a joint overload controller for pitch and yaw channels on the high-order fully actuated system theory for a nonlinear lateral and longitudinal static unstable STT aircraft model. Firstly, a second-order fully actuated system model for aircraft overload was derived, and an optimal control method for lateral and longitudinal overload was designed. Through mathematical simulation verification of this controller and traditional PID controller, it is shown that the PID control method has significant shortcomings in nonlinear aircraft with coupling. However, high-order fully actuated system theory control method can better adapt to nonlinear and static instability problems, achieve stable tracking of aircraft overload commands, and have better rapidity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel Terminal Guidance Law for Blended Aero and Reaction-Jet Missile Based on Nonlinear Disturbance Observer 1

引用

International Conference on Autonomous Unmanned systems, ICAUS 2021

作者： Zhao, Hui Xu, Cheng Qin, Hehong Wang, Hao Hu, Ying Institute of Mechanical and Electrical Engineering Beijing100072 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100072 China

ISBN: (数字)9789811694929

ISBN: (纸本)9789811694912

In this paper, an effective terminal guidance law is proposed for intercepting large maneuvering targets for the reaction jet control (RCS) missile. The guidance law takes the real dynamic characteristics of the control system into account, not only including the second order bandwidth filtering response of the autopilot, but also containing the discrete reaction jet force characteristics. For the target maneuver in the guidance loop, a new nonlinear disturbance observer (NDO) with fast convergence is presented on the premise of not obtaining the prior information of the target. Target acceleration and other uncertainties are estimated and compensated in the guidance law as a feed-forward input. Then the global stability of the system is proved by the appropriate Lyapunov function. The simulation results show that the guidance law can effectively intercept the maneuvering target and obtain good guidance precision. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Event Trigger Mechanism-Based Robust control for Cyber-Physical systems under DoS Attack

Event Trigger Mechanism-Based Robust Control for Cyber-Physi...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Tian, Peng Xu, Huiling Zhao, Jiajia Dong, Lewei Nanjing University of Science and Technology School of Mathematics and Statistics Nanjing210094 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100000 China

ISBN: (纸本)9781665465335

In this paper, the event trigger mechanism-based robust control problem is investigated for cyber-physical systems under denial of service attacks and disturbances. The effects of DoS attacks are regarded as a type of data packet loss. An event trigger mechanism is introduced into the control scheme design to effectively compensate the packet loss data. The robust attenuation technology is composited into control scheme to reduce the impact of disterbances. Then, by modeling the cyber-physical systems under denial of service(DoS) attack as a class of bounded sequential switching system, and constructing the corresponding Lyapunov function, the stability of the system is verified and analyzed. Finally, simulation experiments are given to verify the correctness of the above theoretical results. © 2022 IEEE.

关键词： Sequential switching

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Unmanned Aerial Vehicles Cooperative Search Approach for complex Environments

arXiv

引用

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

Scribble-Supervised Video Object Segmentation

引用

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 339-353页

作者： Peiliang Huang Junwei Han Nian Liu Jun Ren Dingwen Zhang Brain and Artificial Intelligence Laboratory School of AutomationNorthwestern Polytechnical UniversityXi’an 710072China IEEE Department of Engagement Services Mohamed Bin Zayed University of Artificial IntelligenceAbuDhabiUnited Arab Emirate Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory BeijingChina

Recently,video object segmentation has received great attention in the computer vision *** of the existing methods heavily rely on the pixel-wise human annotations,which are expensive and time-consuming to *** tackle this problem,we make an early attempt to achieve video object segmentation with scribble-level supervision,which can alleviate large amounts of human labor for collecting the manual ***,using conventional network architectures and learning objective functions under this scenario cannot work well as the supervision information is highly sparse and *** address this issue,this paper introduces two novel elements to learn the video object segmentation *** first one is the scribble attention module,which captures more accurate context information and learns an effective attention map to enhance the contrast between foreground and *** other one is the scribble-supervised loss,which can optimize the unlabeled pixels and dynamically correct inaccurate segmented areas during the training *** evaluate the proposed method,we implement experiments on two video object segmentation benchmark datasets,You Tube-video object segmentation(VOS),and densely annotated video segmentation(DAVIS)-*** first generate the scribble annotations from the original per-pixel ***,we train our model and compare its test performance with the baseline models and other existing *** experiments demonstrate that the proposed method can work effectively and approach to the methods requiring the dense per-pixel annotations.

关键词： Convolutional neural networks(CNNs) scribble self-attention video object segmentation weakly supervised

来源：评论

学校读者我要写书评

暂无评论

Minimal Curvature and Range Path Connecting Two Oriented Points

Minimal Curvature and Range Path Connecting Two Oriented Poi...

引用

International Conference on Autonomous Unmanned systems, ICAUS 2021

作者： Guo, Kun Xu, Cheng Wei, Zhenyan Xu, Heng Beijing Institute of Mechanical and Electrical Engineering Beijing100074 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Bejing100074 China

ISBN: (纸本)9789811694912

Time and acceleration constraints have been extensively considered in flight vehicle path planning area. However, the limits of the required acceleration guaranteeing the existence of a path has not been fully studied yet. This paper presents an algebraic proof of the minimax curvature path connecting two oriented points with one inflection point, and then the minimal required acceleration and flight time are analyzed for all planar scenarios. It is revealed that for some geometry conditions, there exists a specific combination of curvature and range limits, while for other conditions, this combination can change continuously by increasing one and decreasing another. For all cases, the optimal paths are concatenations of circular arcs of equivalent radii in different forms, which means that to reduce the acceleration and flight time to the utmost, the overload should be evenly distributed along the whole path. The results in this paper can support fast on-line path planning in the presence of incident direction constraint with limited maneuverability and fuel. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-target Association Tracking Algorithm Based on IMM

Research on Multi-target Association Tracking Algorithm Base...

引用

International Conference on Autonomous Unmanned systems, ICAUS 2021

作者： Siting, Peng Lei, Li Yichao, Ma Jun, Ren Beijing Electro-Mechanical Engineering Institute Beijing100074 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789811694912

Radar sensors are important detection and tracking equipment in national defense work. There are multiple targets in actual combat scenarios. It is necessary to quickly and accurately capture suspicious targets in the reconnaissance area and track them in real time. complex electromagnetic interference conditions and multi-target tracking requirements pose a great challenge to track correlation. This paper establishes a multi-target maneuver scenario and uses a joint probabilistic data interconnection algorithm based on interactive multi-model (IMM) to perform multi-target tracking. Correlation tracking, simulation results show that the algorithm is used to correlate the target maneuver and measurement information with good accuracy. Interactive multi-model filtering can mix the estimation results of each filter to generate a fused state estimation result. The description of the model is more accurate, which improves the tracking accuracy and tracking stability of the algorithm. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Error Modeling Method of Aircraft HWIL Simulation system Based on BP Wavelet Neural Network 18th

Error Modeling Method of Aircraft HWIL Simulation System Ba...

引用

18th Chinese intelligent systems Conference, CISC 2022

作者： Tong, Jiahui Liu, Jin Li, Jing Zhang, Qing Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100190 China Beijing Electro-Mechanical Engineering Institute Beijing102299 China

ISBN: (纸本)9789811962028

In order to ensure the confidence of hardware-in-the-loop(HWIL) simulation results, the simulation equipment and system are required to simulate the realistic flight environment;However, the additional error introduced by the simulation system in the guidance and control loop should be minimized. By studying the error model of the aircraft HWIL simulation system and analyzing the impact of the HWIL simulation system on the guidance and control quality, we can recognize the real performance of the guidance and control system, find out the key factors affecting the performance of the HWIL simulation system, provide decision-making basis for the development of simulation equipment, and improve and enhance the reliability of the simulation system. Based on BP wavelet neural network, the mathematical modeling of the aircraft HWIL simulation system error is carried out, and the modeling method and process are introduced in detail. A new method of aircraft HWIL simulation system error modeling with input and output data is proposed, and the applicability of modeling method is analyzed, and satisfactory accuracy results are obtained. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Errors

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：