检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Ayodeji, Abiodun Wang, Wenhai Su, Jianzhong Yuan, Jianquan Liu, Xinggao State Key Laboratory of Industrial Control Technology Control Department Zhejiang University Hangzhou310027 China Tianjin Jinhang Technical Physics Institute Tianjin300192 China Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory Beijing100074 China

A single unit (head) is the conventional input feature extractor in deep learning architectures trained on multivariate time series signals. The importance of the fixed-dimensional vector representation generated by the single-head network has been demonstrated for industrial machinery condition monitoring and predictive maintenance. However, processing heterogeneous sensor signals with a single-head may result in a model that cannot explicitly account for the diversity in time-varying multivariate inputs. This work extends the conventional single-head deep learning models to a more robust form by developing context-specific heads to independently capture the inherent pattern of each sensor reading in multivariate time series signals. Using the turbofan aircraft engine benchmark dataset (CMAPSS), an extensive experiment is performed to verify the effectiveness and benefits of multi-head fully connected neurons, recurrent networks, convolution network, the transformer-style stand-alone attention network, and their variants for remaining useful life estimation. Moreover, the effect of different attention mechanisms on the multi-head models is also evaluated. In addition, each architecture's relative advantage and computational overhead are analyzed. Results show that utilizing the attention layer is task-sensitive and model dependent, as it does not provide consistent improvement across the models investigated. The result is further compared with five state-of-the-art models, and the comparison shows that a relatively simple multi-head architecture performs better than the state-of-the-art models. The results presented in this study demonstrate the importance of multi-head models and attention mechanisms to improved understanding of the remaining useful life of industrial assets. © 2021, CC BY.

关键词： Recurrent neural networks

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

SeqEnhance: A Lightweight Image Processing PipeLine for Low-Light Image Enhancement

SeqEnhance: A Lightweight Image Processing PipeLine for Low-...

引用

Artificial Intelligence technology (ACAIT), Asian Conference on

作者： Runlin Zhou Peiliang Huang Dingwen Zhang Jun Ren AHU-IAI AI Joint Laboratory Anhui University Hefei China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei China School of Automation Northwestern Polytechnical University Xi’an China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9798350359145

ISBN: (纸本)9798350359152

Low-light image enhancement (LLIE) is an important task in computer vision, aiming to improve the visual perception or interpretability of images captured in poorly illuminated environments. Recently, deep learning based methods have been extensively explored to address this issue. While many of these methods have achieved significant advancements in various evaluation metrics for LLIE, only a few have made progress in improving inference speed for the resulting images. As a result, achieving both high-quality enhancements and efficient inference speed remains a challenge. To tackle this challenge, we propose SeqEnhance, a fast LLIE method based on a predefined parameterized image processing pipeline. Our approach combines the inference capabilities of deep neural networks for parameter estimation and the efficient processing capabilities of image processing pipelines to generate enhanced images in an end-to-end manner. The experimental results demonstrate that the proposed method achieves competitive performance on image quality evaluation metrics such as PSNR and SSIM with a fast inference speed.

关键词： Measurement Image quality Deep learning Computer vision Parameter estimation Pipelines Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimization of Missile Path Planning Based on APMO-HV Algorithm

Optimization of Missile Path Planning Based on APMO-HV Algor...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Hu Zhang Shuai Wang Tonglin Liu Aimin Zhou Yi Zhang Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-mechanical Engineering Institute Beijing China School of Mechanical Engineering Changzhou University Changzhou China Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology East China Normal University Shanghai China

In this paper, with considerations of low efficiency of missile path planning (MPP) by traditional aggregation technology, it uses affinity propagation based multi-objective evolutionary algorithm with hypervolume environment selection (APMO-HV) to solve the problem of MPP after establishing the MPP model. The experimental part compares and analyzes APMO-HV with six state-of-the-art algorithms, and applies it to address the MPP problem. The experimental results show that compared with the other six algorithms, APMO-HV has achieved the best solution performance in both the GLT test suite and MPP problem. This not only validates the effect of the proposed algorithm, but also enriches and improves the research results of MPP.

关键词： Missiles Optimization Path planning Turning Planning Target tracking Sociology

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

A belief rule-based fault diagnosis method for Multi-UAVs under missing attribute data

A belief rule-based fault diagnosis method for Multi-UAVs un...

引用

Cyber-Physical Social Intelligence (ICCSI), International Conference on

作者： ErKai Zhao MingRui Hao RuoHan Yang KeYuan Yue DeLin Yu School of Computer Science and Information Engineering Harbin Normal University Harbin China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China School of Electronics and Information Northwestern Polytechnical University Xi’an China School of Mathematics and Statistics Northwestern Polytechnical University Xi’an China

To reasonably improve the missing attribute data and effectively integrate sample data and uncertain expert knowledge, this paper proposes a new fault diagnosis method based on a belief rule base (BRB). In the case of missing attribute data, the maximum likelihood estimation (MLE) method is used to complete the missing attribute data, and the fault diagnosis method of the multi-UAVs is constructed by using other complete attribute data as the input information of BRB. Finally, the effectiveness of the proposed method is verified by experimental simulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on guidance method based on angle description

Research on guidance method based on angle description

引用

Chinese Automation Congress (CAC)

作者： Hui Wang Ruiming Hao Yan Zhen Wugang Wang Yong Wei School of Aerospace Engineeringline Beijing Institute of Technology Beijing China Science and technology on complex system control and intelligent agent cooperation laboratory Beijing China Northwest Industries Group Co.LTD Xian China 672 Test Ground Hua An Industry Group Co. LTD Qiqihaer China

Based on the derivation of optimal proportional navigation, the new expressions with line of sight angle and trajectory angle for proportional navigation, integral proportional navigation and velocity pursuit are proposed. The guidance model with initial heading error is developed when considering a high order dynamics system for the integral proportional navigation and velocity pursuit. Comparative analysis results of miss distance demonstrate the guidance performance of integral proportional navigation and velocity pursuit.

关键词： Navigation Trajectory Missiles Mathematical model Analytical models Acceleration

来源：评论

学校读者我要写书评

暂无评论

A Multi-Robot Task Allocation Method Based on Graph Attention Network and Unsupervised Learning

A Multi-Robot Task Allocation Method Based on Graph Attentio...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Zirui Wu Zhen Li Dong Zhu Qiuhan Liao Weiran Yao School of Astronautics Harbin Institute of Technology Harbin China Beijing Electro-Mechanical Engineering Institute Beijing China Chengdu CHG Robots & Intelligent Equipment Institute Co. Ltd Chengdu China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing China

ISBN: (数字)9798350384185

ISBN: (纸本)9798350384192

The task allocation for multiple robots is a critical component in the coordination of unmanned clusters. The existing heuristic algorithms are hard to achieve satisfactory results in large-scale problems, and reinforcement learning-based methods face challenges in ensuring the rationality of reward design. This paper introduces a model based on multi-head attention and graph neural networks to address the schedule-dependent multi-robot task allocation problem, trained using unsupervised learning techniques. This model can be trained with varying numbers of robots and tasks without necessitating changes to its structure or parameters. In the experiment of this paper, the model is trained under two different conditions, and the performance is evaluated across six different problem scales. Comparing the proposed model against greedy algorithms and genetic algorithms, the results demonstrate that the proposed model has sianiflcant advantages in overall performance.

关键词： Greedy algorithms Robot kinematics Heuristic algorithms Computational modeling Reinforcement learning Graph neural networks Resource management Unsupervised learning Faces Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Cooperative Collision Avoidance Method for Multi-UAV Based on Kalman Filter and Model Predictive control

Cooperative Collision Avoidance Method for Multi-UAV Based o...

引用

International Conference on Unmanned systems and Artificial Intelligence

作者： Hanqiao Huang Huan Zhou Meiyun Zheng Cheng Xu Xiaofeng Zhang Wei Xiong Unmanned System Research Institute Northwest Polytechnical University Xi'an China Aeronautical Engineering College Air Force Engineering University Xi'an China School of Marine Science and Technology Northwest Polytechnical University Xi'an China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China UAV Researc Center Army Aviation Institute Beijing China

ISBN: (数字)9781728158594

ISBN: (纸本)9781728158600

Collision avoidance is the primary problem to be solved in formation flight of multiple Unmanned aerial vehicles(UAVs). Firstly, a cooperative collision avoidance architecture of multiple UAVs is designed according to the requirement of autonomous collision avoidance of single UAV. Then a new cooperative collision avoidance method of multiple UAVs based on Kalman filter and model predictive control(MPC) is proposed. In this method, extended Kalman filter(EKF) is used to estimate the state of obstacles and target points in uncertain environment space, and to predict the trajectory of obstacles and target points. At the same time, relevant performance index functions and constraints are set up. On the basis of sharing environmental information, model predictive control strategy is used to guide and make cooperative collision avoidance decisions for multiple UAVs. The simulation results show that the proposed method is effective in uncertain environment perception and UAV collision avoidance, and the cooperative mechanism has obvious advantages.

关键词： UAV cooperative decision collision avoidance Kalman filter state estimation MPC Collision avoidance Kalman filters Unmanned Aerial Vehicle State estimation Maximum Allowable Concentration drone honey bees environmental perception Formation flight

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Graph Search Method for Path Planning of Unmanned Ground Vehicle for Freight Transportation

A Hierarchical Graph Search Method for Path Planning of Unma...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Jianing Hu Zhen Li Sen Guo Weiran Yao School of Astronautics Harbin Institute of Technology Harbin China Beijing Electro-Mechanical Engineering Institute Beijing China CRRC Nanjing Puzhen Co. Ltd Nanjing China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing China

ISBN: (数字)9798350384185

ISBN: (纸本)9798350384192

For the problem of collision volume change when forklift unmanned vehicles work in complex storage environments, a multi-level graph search path planning method is proposed. The first level is the path planning of the Unmanned Ground Vehicle (UGV) body, which uses the grid map and the A * algorithm to plan the path of the UGV transferring in the scene; the second level is the joint path planning of the UGV and the object being carried, to avoid overcomplicating this issue, the unmanned vehicle will be limited to pushing the cargo only forwards. The third level is the path planning when the unmanned vehicle carries multiple objects, which decomposes the whole scene into multiple sub-scenes, plans the paths of the unmanned vehicle in the sub-scenes separately, and searches for the optimal combination of sub-scenes. Higher level searches will invoke lower level algorithms and provide a virtual scene and target as input. The experimental results show that this multilevel path planning method is optimal and complete in solving the forklift unmanned vehicle for handling a single object, and can give a feasible solution for handling multiple objects.

关键词： Costs Transportation Search problems Path planning Land vehicles complexity theory Autonomous vehicles

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：