检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Unmanned systems, ICUS 2021

作者： DIng, Yuanxue Qu, Yanchen Zhang, Qing Tong, Jiahui Yang, Xianhui Sun, Jianfeng Harbin Institute of Technology National Key Laboratory of Science and Technology on Tunable Laser Institution of Opto-Electronics Harbin China Beijing Electromechanical Engineering Institute Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9780738146577

In recent years, unmanned aerial vehicle (UAV) technology has developed rapidly, which plays an important role in both military and civil fields. While it brings convenience to all walks of life, there are also a lot of security problems. Therefore, it is necessary to study anti-UAV technology, but the detection of UAV is an important basis of anti-UAV technology. In this paper, by combining the three-dimensional range profile collected by Gm-APD (Geiger mode Avalanche Photo Diode) lidar with the deep learning method, a UAV detection method based on the improved YOLOv3 (You Only Look Once v3) network is proposed. Firstly, the data of UAV in low altitude real scene is collected by Gm-APD lidar, and range profile information is generated. Then, the YOLOv3 network is improved, and the SPP module can be added to combine the local features of the target with the global features to improve the detection accuracy. It is suitable for the detection of UAVs. Finally, the trajectory of the UAV is drawn based on the distance information. The experimental results show that the improved method can effectively detect UAV targets, and is better than the previous method, YOLOv3-Tiny method and YOLOv4 method. The farthest detection distance is 238m, the detection speed is fast, and the purpose of real-time detection and positioning can be achieved. Therefore, this method can be applied to anti-UAV technology and has important research significance. © 2021 IEEE.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Cooperative Search Strategy of Multiple UAVs Based on Matrix Game 19

Cooperative Search Strategy of Multiple UAVs Based on Matrix...

引用

19th International Bhurban Conference on Applied sciences and Technology, IBCAST 2022

作者： Song, Dalei Wang, Xiaoqian Dai, Aoliang Ma, Hongjun Wei, Donghui Shenyang University of Technology School of Information Science and Engineering Shenyang China Northeastern University School of Information Science and Engineering Shenyang China South China University of Technology School of Information Science and Engineering Guangdong China Beijing Research Institute of Mechanical & Electrical Technology Key Laboratory of Complex System Control and Intelligent Collaboration Technology Beijing100074 China

ISBN: (数字)9781665460514

ISBN: (纸本)9781665460514

For the regional search problem of multiple unmanned air vehicles (UAVs) ,a cooperative search strategy of multiple UAVs is proposed based on action matrix game (AMG) for intelligent moving targets on the ground in this paper. Based on the proposed AMG, the yaw angle and position information of the target is described in probability matrix, and the matrix is updated by Nash equilibrium and receding horizon control in every control cycle. Simulation results show that this strategy deduces the searching time for revisiting the reference target, and improves the success rate for moving targets searching. © 2022 IEEE.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Learning Pre-Grasp Manipulation of Flat Objects in Cluttered Environments using Sliding Primitives

Learning Pre-Grasp Manipulation of Flat Objects in Cluttered...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jiaxi Wu Haoran Wu Shanlin Zhong Quqin Sun Yinlin Li State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing China Department of Automation University of Science and Technology of China Heifei China State Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Science Beijing China Science and Technology on Thermal Energy and Power Laboratory Wuhan China

Flat objects with negligible thicknesses like books and disks are challenging to be grasped by the robot because of the width limit of the robot's gripper, especially when they are in cluttered environments. Pre-grasp manipulation is conducive to rearranging objects on the table and moving the flat objects to the table edge, making them graspable. In this paper, we formulate this task as Parameterized Action Markov Decision Process, and a novel method based on deep reinforcement learning is proposed to address this problem by introducing sliding primitives as actions. A weight-sharing policy network is utilized to predict the sliding primitive's parameters for each object, and a Q-network is adopted to select the acted object among all the candidates on the table. Meanwhile, via integrating a curriculum learning scheme, our method can be scaled to cluttered environments with more objects. In both simulation and real-world experiments, our method surpasses the existing methods and achieves pre-grasp manipulation with higher task success rates and fewer action steps. Without fine-tuning, it can be generalized to novel shapes and household objects with more than 85% success rates in the real world. Videos and supplementary materials are available at https://***/view/pre-grasp-sliding.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Solving Ascent Trajectory Optimization Problems by Radua Pseudospectral Method

Solving Ascent Trajectory Optimization Problems by Radua Pse...

引用

intelligent Robotics and systems (ISoIRS), International Symposium on

作者： Liaochao Deng Cheng Xu Weishuai You Beijing Institute of Mechanical and Electrical Engineering Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

Ascent trajectory optimization problem of air-breathing hypersonic vehicles is a highly nonlinear and nonconvex problems. Most of the early works focus on the traditional indirect method, which needs to derive the complete first-order necessary conditions of the trajectory optimization problem. The derivation process is too complicated and error-prone. Additionally, indirect method has a high demand on the initial guess, and it needs to give the initial guess of covariant variables without physical significance. In this paper, we solve the ascent trajectory optimization problem directly using Radau Pseudospectral Method (RPM). Firstly, the complex three-dimensional ascent trajectory optimization problem is established in detail. Conmmon inequality path constraints including those on dynamic pressure and aerodynamic bending moment are taken into account. The performance index is given as maximizing the final mass considering minimizing the fuel consumption. Subsequently, the ascent trajectory optimization problem is transformed into a nonlinear programming problem (NLP) by RPM. Finally, the ascent trajectory optimization for Generic Hypersonic Aerodynamic Model Example (GHAME) is solved by RPM and the optimal results demonstrate the rapidity, effectiveness and high precision of RPM. The comparison between optimal trajectories with and without path constraints shows that path constraints increase fuel consumption.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Simulation Technology of Cooperative Guidance for Aircraft Formation

Research on Simulation Technology of Cooperative Guidance fo...

引用

Chinese intelligent systems Conference, CISC 2020

作者： Tong, Jiahui Liu, Jin Li, Jing Zhan, Tianming Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Beijing Electro-Mechanical Engineering Institute Beijing China TAIJI Computer Corporation Limited Beijing China

ISBN: (纸本)9789811584572

This paper analyzed the structure and characteristics of cooperative guidance system of aircraft formation, puts forward a multi-level simulation system architecture of centralized/distributed driving to solve the cooperative guidance for aircraft formation, realized the modeling of aircraft formation members and interaction by using multi-agent method, discussed the simulation methods of data link networking transmission and positioning, space-time registration of simulation system, and so on. The simulation is carried out based on a certain combat scenario, and the results show that the simulation system constructed in this paper can simulate the whole process of cooperative guidance of aircraft formation. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Knowledge-driven material design platform based on the whole-process simulation and modeling

引用

International Journal of Modeling, Simulation, and Scientific Computing 2022年第2期13卷 1-15页

作者： Gongzhuang Peng Tie Li Xiang Zhai Wenzheng Liu Heming Zhang National Engineering Research Center for Advanced Rolling Technology University of Science and Technology Beijing Beijing 100083 P.R.China Shanghai Electro-Mechanical Engineering Institute Shanghai 201109 P.R.China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System Engineering Beijing 100854 P.R.China Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing Simulation Center Beijing 100854P.R.China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing 100854P.R.China National CIMS Engineering Research Center Tsinghua University Beijing 100084P.R.China

In order to realize the agility,collaboration and visualization of alloy material devel-opment process,a product development platform based on simulation and modeling technologies is established in this *** this platform,the whole-process simulation module builds multi-level simulation models based on metallurgical mechanisms from the production line level,the thermo-mechanical coupling field level and the microstructure evolution *** design knowledge management module represents the multi-source heterogeneous material design knowledge through ontology model,including customers’requirement knowledge,material component knowledge,process design knowledge and quality inspection knowledge,and utilizes the case-based reasoning approach to reuse the *** data-driven modeling module applies machine learning algorithms to mine the relationships between product mechanical properties,material components,and process parameters from historical samples,and utilizes multi-objective optimiza-tion algorithms to find the optimal combination of process *** of the developed platform in actual steel mills shows that the proposed method helps to improve the efficiency of product design process.

关键词： Product development knowledge-based engineering multi-scale simulation performance prediction model

来源：评论

学校读者我要写书评

暂无评论

Identity Re recognition Technology Based on Improved Lightweight ConvNetx Model

Identity Re recognition Technology Based on Improved Lightwe...

引用

Chinese Control Conference (CCC)

作者： Peng Siting Li Lei Hongbo Zhu Ren Jun Song Zhichao Jiabing Yang 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

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-objective Bat Algorithm for Software Defect Prediction 14th

A Multi-objective Bat Algorithm for Software Defect Predicti...

引用

14th International Conference on Bio-inspired Computing: Theories and Applications, BIC-TA 2019

作者： Wu, Di Zhang, Jiangjiang Geng, Shaojin Cai, Xingjuan Zhang, Guoyou Complex System and Computational Intelligent Laboratory Taiyuan University of Science and Technology Taiyuan030024 China

ISBN: (纸本)9789811534249

Both the class imbalance of datasets and parameter selection of support vector machine (SVM) play an important role in the process of software defect prediction. To solve these two problems synchronously, the false positive rate (pf) and the probability of detection (pd) are considered as two objective functions to construct the multi-objective software defect prediction model in this paper. Meanwhile, a multi-objective bat algorithm (MOBA) is designed to solve this model. The individual update strategy in the population is performed using the individual update method in the fast triangle flip bat algorithm, and the non-dominated solution set is used to save the better individuals of the non-defective module and the support vector machine parameters. The simulation results show that MOBA can effectively save resource consumption and improve the quality of software compared with other commonly used algorithms. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Gated Driver Attention Predictor

Gated Driver Attention Predictor

引用

International Conference on intelligent Transportation

作者： Tianci Zhao Xue Bai Jianwu Fang Jianru Xue College of Transportation Engineering Chang'an University Xi'an China Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory Beijing China College of Artificial Intelligence Xi'an Jiaotong University Xi'an China

Driver attention prediction implies the intention understanding of where the driver intends to go and what object the driver concerned about, which commonly provides a driving task-guided traffic scene understanding. Some recent works explore driver attention prediction in critical or accident scenarios and find a positive role in helping accident prediction, while the promotion ability is constrained by the prediction accuracy of driver attention maps. In this work, we explore the network connection gating mechanism for driver attention prediction (Gate-DAP). Gate-DAP aims to learn the importance of different spatial, temporal, and modality information in driving scenarios with various road types, occasions, and light and weather conditions. The network connection gating in Gate-DAP consists of a spatial encoding network gating, long-short-term memory network gating, and information type gating modules. Each connection gating operation is plug-and-play and can be flexibly assembled, which makes the architecture of Gate-DAP transparent for evaluating different spatial, temporal, and information types for driver attention prediction. Evaluations on DADA-2000 and BDDA datasets verify the superiority of the proposed method with the comparison with state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gated Driver Attention Predictor

arXiv

引用

arXiv 2023年

作者： Zhao, Tianci Bai, Xue Fang, Jianwu Xue, Jianru College of Transportation Engineering Chang’an University Xi’an China Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory Beijing China College of Artificial Intelligence Xi’an Jiaotong University Xi’an China

关键词： Forecasting

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：