检索结果-内蒙古大学图书馆

A pigeon-inspired optimization algorithm for many-objective optimization problems

science China(Information sciences) 2019年第7期62卷 131-138页

作者： Zhihua CUI Jiangjiang ZHANG Yechuang WANG Yang CAO Xingjuan CAI Wensheng ZHANG Jinjun CHEN Complex System and Computational Intelligence Laboratory Taiyuan University of Science and Technology Beijing Institute of Petrochemical Technology Faculty of Information Technology Beijing University of Technology State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy of Sciences School of Software University of Technology Sydney

Dear editor,Swarm intelligence optimization algorithms are inspired by the behaviour of biological groups in nature. Such algorithms have the advantages of a clear structure, simple operation, comprehensible principles, strong parallelism, effective search abilities, and strong robustness. They can effectively solve difficult problems that traditional methods cannot. Pigeon-inspired optimization (PIO), a novel biomimetic swarm intelligence optimization algorithm, was proposed by Duan and Qiao in

关键词： A pigeon-inspired optimization algorithm for many-objective optimization problems Pareto

来源：评论

学校读者我要写书评

暂无评论

A Fast Covariance Intersection Tracking Algorithm Based on CDKF

A Fast Covariance Intersection Tracking Algorithm Based on C...

引用

第三十八届中国控制会议

作者： Hang Zhang Chuang Song Mingrui Hao Linxiu Chen School of Software and Microelectronics Northwestern Polytechnical University Science and technology on complex system control and intelligent agent cooperation laboratory

With the enhancement of the anti-jamming ability of the target, it is difficult to track and strike the target stably and accurately by single guidance. It is necessary to use a variety of detectors as sensors to provide a variety of observation data to track the target stably and achieve accurate strike. In this paper, we mainly research the distributed multi-sensor estimation problem. First, the target motion model and observation model are established. Secondly, the central differential Kalman filter(CDKF) transformation is applied to address the non-linear filtering problem without the need for computation of Jacobian matrix. Then, a FCI fusion algorithm for the multi-sensor target tracking problem is proposed. Compared to the traditional covariance intersection fusion method, FCI is more efficient in computation without the need for complex optimization process. Finally, simulations are designed and implemented and the joint CDKF-FCI fusion estimation algorithm is validated.

关键词： central differential Kalman filter fast covariance intersection fusion information fusion target tracking

来源：评论

学校读者我要写书评

暂无评论

Network Parameter Generation for One-Shot Object Detection

Network Parameter Generation for One-Shot Object Detection

引用

2019 IEEE International Conference on Unmanned systems, ICUS 2019

作者： Wang, Kang Zhao, Jiajia Wang, Yang Zhou, Shuigeng Fudan University Shanghai Key Lab of Intelligent Information Processing School of Computer Science Shanghai200433 China Beijing Electro-Mechanical Engineer Institute Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Nanchang University School of Information Engineering 330031 China

ISBN: (纸本)9781728137926

Recent object detection models have achieved satisfactory performance by deep learning with large-scale annotated datasets. However, these models often perform poorly when the training examples are not sufficient enough, especially for one-shot object detection where there is only one training example of each target class. In this paper, we propose a network parameter generation framework for effective one-shot object detection. By leveraging the semantic relationship between the source-domain and the target-domain (new classes), our framework can generate network parameters for the new classes directly. Furthermore, we develop two implementation schemes for this framework: weighting-based parameter generation and regression-based parameter generation. These two schemes use different information to construct the relationship and transfer knowledge from the source-domain to the target-domain. Experiments on the PASCAL-OSCD benchmark show that our methods can significantly boost the performance of one-shot object detection. © 2019 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Attitude control of hypersonic vehicle based on optimized ADRC 8

Attitude control of hypersonic vehicle based on optimized AD...

引用

8th IEEE Data Driven control and Learning systems Conference, DDCLS 2019

作者： Piao, Minnan Sun, Mingwei Huang, Jian Wang, Zenghui Chen, Zengqiang Science and Technology on Complex System Control Intelligent Agent Cooperation Laboratory Beijing100074 China College of Artificial Intelligence Nankai University Tianjin300350 China Beijing Automatic Control and Equipment Institute Beijing100074 China University of South Africa Department of Electrical and Mining Engineering Florida1710 South Africa

ISBN: (纸本)9781728114545

In this paper, two types of practical angle of attack control schemes are proposed for hypersonic vehicle which is subject to large unmodeled, parametric uncertainties and external disturbances. In the first scheme, the pitch angle control method based on the second-order linear active disturbance rejection control is directly applied to the angle of attack control through simple command transformation. Inner-loop pitch angular rate feedback is performed first to enhance the damping in the second scheme, and then first-order linear active disturbance rejection control is designed for the overdamped plant. Both schemes provide simple and robust solutions to the angle of attack control. To achieve desired stability and performance robustness, non-smooth $H-{\infty}$ synthesis technique is utilized to optimize the controller within the designed flight envelope. Nonlinear simulations are performed to validate the advantages of the proposed methods. © 2019 IEEE.

关键词： Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

Error Analysis of Object Depth Measurement Method Based on Feature Line Segments

Error Analysis of Object Depth Measurement Method Based on F...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Chuanqi Zhang Yunfeng Cao Meng Ding Donghui Wei College of Astronautic Nanjing University of Aeronautics and Astronautics Nanjing China College of Civil Aviation Nanjing University of Aeronautics and Astronautics Nanjing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute Beijing China

ISBN: (数字)9781728180250

ISBN: (纸本)9781728180267

This paper focuses on the problem of object depth measurement in ultra-low altitude flight, which has always been a research hotspot in the field of machine vision. Compared with the previous object depth measurement method based on a single handcrafted feature point, the method based on feature line segments can effectively weaken the adverse effect caused by the feature matching error. However, since this method involves both image processing algorithms and the use of position data provided by navigation devices, various errors will be introduced. To this end, this paper points out the error sources of that may affect the accuracy of the object depth measurement results under this method. Then, through numerical simulation, the errors are simulated and their influence rules are analyzed, with the qualitative and quantitative results presented. Finally, we also give the allowable value range of each error under the minimum requirement that the object depth measurement error in ultralow altitude flight missions does not exceed 20%, which provides a reference and guidance for both algorithm selection and practical application.

关键词： Feature extraction Atmospheric modeling Pipelines Object segmentation Measurement uncertainty Measurement errors Intelligent agents

来源：评论

学校读者我要写书评

暂无评论

Failure mode and effects analysis based on intuitionistic fuzzy sets and evidential correlation coefficient

Failure mode and effects analysis based on intuitionistic fu...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Hang Zhang Chan Huang Mingsheng Lu Xiaofei Dong Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory School of Software Northwestern Polytechnical University Xi’an Beijing China School of Electronics and Information Northwestern Polytechnical University Xi’an China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9781728137933

As an effective implement, failure mode and effects analysis (FMEA) is widely applied in the security of system for practical application. Nowadays, many methods determine the order of fault mode by a crisp risk priority number (RPN). However, these methods exist several shortcomings, for instance, the correlation of the assessments given by team members are not fully considered. In this article, a new method for risk assessment and sequence for failure modes in FMEA is proposed on account of the D-S evidence theory and the evidential correlation coefficient. By using the proposed approach, the weights of team members for each failure mode and risk factor is obtained. Then the weighted assessments are used to perform the aggregation process by Intuitionistic fuzzy weighted averaging (IFWA) operator. A classic application regarding risk assessment is used to verify the effectiveness of the proposed method.

关键词： Correlation Fuzzy sets Risk management Uncertainty Aggregates Linguistics control systems

来源：评论

学校读者我要写书评

暂无评论

Cross-cycle iterative unmanned aerial vehicle reentry guidance based on reinforcement learning

Cross-cycle iterative unmanned aerial vehicle reentry guidan...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Yang Cheng Zunshi Shui Cheng Xu Tianyu Feng Yiyang Jiang Beijing Aerospace Technology Research Institute Beijing China Science and technology on complex system control and intelligent agent cooperation laboratory Beijing China

The traditional predictive correction algorithm requires a large number of iterative calculations for the predicted trajectory, which greatly occupies a large amount of computing resources, so that the real-time solution of the guidance command can not be guaranteed, and the guidance accuracy will have a large impact. And the prediction correction guidance requires the algorithm to have the ability of selfadaptation and intelligent learning. Therefore, this paper proposes a cross-cycle iterative hypersonic UAV predictive correction guidance method based on reinforcement learning. The parametric control variable (CVP) method is used to construct the parametric model of the guidance command. The actor-critic-based reinforcement learning method is used to solve the guidance command in real time, and the guidance information is effectively transmitted in the adjacent guidance solution cycle. The guidance error converges to within the allowable accuracy range during the cross-cycle iteration. Monte Carlo simulation shows that the proposed method has good adaptability to initial conditions and flight parameter uncertainty, and can guarantee the real-time performance of the guidance command while achieving high-precision guidance.

关键词： Trajectory Aircraft Atmospheric modeling Earth Mathematical model Iterative algorithms Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

A Multi-branch Parallel Simulation Method based on Symbiotic Potential

A Multi-branch Parallel Simulation Method based on Symbiotic...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Lu Zhao Tu Zhen-biao Wei Jia-ning Zhu Yu-tong Liu Tong-lin Liu Qing-hua Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineering Insititute Beijing China

A multi-branch parallel simulation method and an architecture of application system are proposed in this paper based on symbiotic potential, and method of construction and calibration of parallel battlefield based on real data, as well as generation of simulation branch based on situation interpretation etc. are proposed. Fast building and adjustment of situation of real time simulation are realized based on simulation to meet the requirements of consistency and parallel operation between virtual simulation and real systems. Multibranch operation management, multi-branch highperformance operation support and other methods are proposed to support the dynamic generation of massive parallel simulation copies based on real-time intelligence and ultra-realtime and large-sample operation to meet the requirements of advanced evaluation of real-time situation. At the same time, a set of simulation application verification frameworks for typical task situation is presented to support the construction of multibranch simulation operation environment, and provide technical verification means for real-time situation prediction and evaluation.

关键词： Data models Analytical models Predictive models Real-time systems Computational modeling Symbiosis Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Motion Parallax Estimation for Ultra Low Altitude Obstacle Avoidance

Motion Parallax Estimation for Ultra Low Altitude Obstacle A...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Changqing Wang Xinkai Liang Shan Zhang Chao Shen Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute Beijing China

ISBN: (纸本)9781728137933

By making full use of the curvature of the earth and ground clutter, the ultra-low altitude flight technique can significantly increase the difficulty of detecting and intercepting unmanned aerial vehicles (UAVs), and improve their penetration probabilities. However, unpredicted static/dynamic obstacles seriously threaten the flight safety of the ultra-low altitude UAVs. Therefore, fine autonomous spatial perception capability is essential for ultra-low altitude UAVs with limited loads and computing resources to avoid obstacles. To solve the difficult problem of spatial perception for ultra-low altitude obstacle avoidance, a motion parallax estimation algorithm is proposed by combing the deep learning and the epipolar geometry in this paper. By utilizing the deep neural network, the end-to-end mapping relationship from sequence images to depth values of pixels is constructed for spatial perception. At the same time, to overcome the interference caused by the image consistency hypothesis, the loss function is constructed based on the 3D geometric information of the scene rather than the re-projection error between images. Finally, the proposed algorithm is evaluated on the KITTI dataset and infrared image dataset to verify its effectiveness and generalization.

关键词： Motion parallax Deep learning Epipolar geometry component Motion Parallax Space Perception flight safety Unmanned Aerial Vehicle Obstacle avoidance Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

Observability Enhancement of the Target Tracking Model Based on Infrared Semi-strapdown Seeker

Observability Enhancement of the Target Tracking Model Based...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Peng Siting Zhao Qian Ma Yichao Xu Cheng Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory The Beijing Electro-Mechanical Engineering Institute Beijing China

ISBN: (纸本)9781728137933

As an important device for target interception, The seeker is used to search, recognize and track the target autonomously. Infrared semi-strapdown seekers are widely used in applications due to their low cost and small size. However, one non-negligible disadvantage of semi-strapdown infrared seekers is that the observability of target tracking model is poor, especially for the interception of high-speed maneuvering weapons. In this paper, the target tracking model ( i.e., the filtering estimation model) based on the infrared simi-strapdown seeker is established. The observability of the target tracking model is analyzed and the evaluation method of the observability is studied. Simulation results show that the observability of the filtering estimation model can be improved by increasing the relative motion between missile and target which results in faster changes of the line-of-sight (LOS) angle. According to the results on the observability analysis, the desired trajectory is obtained through the design of proper guidance law. Nonlinear filtering algorithm is also introduced for the trajectory design. Simulation experiments are conducted for the integrated filtering and guidance, and simulation results illustrate the effectiveness of the proposed observability enhancement method.

关键词： Observability Missiles Filtering Estimation Mathematical model Target tracking Navigation

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：