检索结果-内蒙古大学图书馆

第43届中国控制会议

作者： Shuwei Yu Jing Li Tianwei Niu Junzheng Wang Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This paper proposes a tightly-coupled lidar-GNSS-inertial fusion system that achieves accurate state estimation and mapping for robot *** system effectively fuses lidar points,GNSS measurements,and IMU data using the iterated error state Kalman filter algorithm to obtain precise,drift-free,and real-time *** optimize computational efficiency,an incremental tree structure,ikdtree,is employed for managing a local map,and different Kalman gain formulas are utilized to process GNSS and lidar point observations separately to lower the computation ***,a factor graph is introduced to optimize the pose *** selectively introducing keyframes based on the odometry estimation,the graph incorporates odometry,GNSS measurements,and loop closure constraints to optimize all keyframe poses,resulting in a precise trajectory and global ***,extensive experiments are conducted using the KITTI dataset and several real-world scenarios to validate the proposed *** experimental results demonstrate that our method achieves precise localization and mapping across diverse environments.

关键词： State estimation Mapping Sensor fusion Robot navigation

来源：评论

学校读者我要写书评

暂无评论

The Model of Managing a Group of UAVs by a Single Operator for Tasks Requiring Increased Attention

The Model of Managing a Group of UAVs by a Single Operator f...

引用

2023 International Conference on Industrial Engineering, Applications and Manufacturing, ICIEAM 2023

作者： Khachumov, Mikhail Khachumov, Vyacheslav Intelligent Control Laboratory Ailamazyan Program Systems Institute of Ras Pereslavl-Zalessky Russia Rudn University Moscow Russia Federal Research Center Computer Science and Control of Ras Moscow Russia

ISBN: (纸本)9781665475952

The problem of optimizing the load on an operator of unmanned aerial vehicles (UAVs), which performs real-time tasks of researching and monitoring territories in an unstable environment is considered. Working load depends on the intensity of the information exchange between onboard and ground control stations and is determined by the agreed limit that leads to a limitation in the number of managed vehicles. As a mathematical model of the multi-functional control system, we use a closed-loop queuing system, which allows to establish coordination among its major elements (onboard computing complex, ground control station and operator) and reduce the loss of service requests. The latter is one of the main requirements to functioning of the system during emergencies. Of considerable interest are optimization statements for the problems of distribution of functions between elements and choosing the load modes. We gave formulations of some optimization problems in a general form and made appropriate conclusions. It is assumed that as an applied task, the problem of monitoring fire sites in forest areas can be considered, which requires increased attention from the operator to process information coming to the ground control station. © 2023 IEEE.

关键词： Distribution functions

来源：评论

学校读者我要写书评

暂无评论

Time Series Anomaly Detection Using Temporal 2D-Variation Multi-Layer Feature Fusion Times Network 14

Time Series Anomaly Detection Using Temporal 2D-Variation Mu...

引用

14th IEEE International Conference on Cyber Technology in automation, control, and Intelligent systems, CYBER 2024

作者： Cui, Tao Zhu, Yueming Liu, Yao Liu, Jindi Pipechina Southwest Pipeline Company Sichuan Chengdu China Chinese Academy of Sciences Key Laboratory of Networked Control Systems Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Instrumentation Technology and Economy Institute Beijing China

ISBN: (纸本)9798331506056

With the popularity of the Internet of Things (IoT) technology, people are beginning to monitor the safety and stability of the system by establishing a sensing network so that anomalies can be detected and disposed of at an early stage. The resulting large amount of time series data has triggered scholars' interest in multivariate time series anomaly detection. In the past, this task was usually achieved by directly using one-dimensional time series, but due to the complexity of time series, it is difficult to perform effective data mining. To solve this problem, we use timesNet to convert one-dimensional sequences into two-dimensional tensors for time series modelling. At the same time, improvements are also made in terms of both block and overall network architecture so that the model can fuse multi-layer features to obtain stronger characterisation and anomaly detection. Experiments on real-world datasets show that our improvement is 0.16%, 1.88% and 1.19% higher than the precision, recall and f1-score of baseline. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Solution to the Problem of Passing Over the Given Targets by an Unmanned Aerial Vehicle in an Unstable Environment

Solution to the Problem of Passing Over the Given Targets by...

引用

2023 International Russian automation Conference, RusAutoCon 2023

作者： Khachumov, Mikhail Intelligent Control Laboratory Ailamazyan Program Systems Institute of Ras Pereslavl-Zalessky Russia Federal Research Center "Computer Science and Control"of Ras Moscow Russia Rudn University Moscow Russia

ISBN: (纸本)9798350345551

The paper gives a statement and considers the solution to an urgent problem of flying over the given targets by an unmanned aerial vehicle (UAV) in unstable conditions. A criterion is formulated for constructing efficient routes and passing arbitrary located sites according to a given formal description of the terrain map with the presence of interferences. Heuristic rules are proposed aimed at minimizing the graph of the initial map and reducing the number of alternative flight routes, given the time constraints for completing the task. The search of the solution in this case can be carried out according to the base tree of routes. A heuristic algorithm for searching efficient routes in a limited time is considered, which has the complexity that ensures its implementation on the UAV onboard computer. It is substantiated that the proposed approach can significantly reduce the number of comparing alternatives for flying around given arbitrary located targets in comparison with the well-known methods for solving this problem. The paper describes a successful example of solving the UAV route planning problem with the proposed approach, which is complicated by the presence of wind flows affecting the speed and trajectory. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Physics-Guided State-Space Model Augmentation Using Weighted Regularized Neural Networks

arXiv

引用

arXiv 2024年

作者： Liu, Yuhan Tóth, Roland Schoukens, Maarten Control Systems Group Eindhoven University of Technology Eindhoven Netherlands Systems and Control Laboratory Institute for Computer Science and Control Budapest Hungary

Physics-guided neural networks (PGNN) is an effective tool that combines the benefits of data-driven modeling with the interpretability and generalization of underlying physical information. However, for a classical PGNN, the penalization of the physics-guided part is at the output level, which leads to a conservative result as systems with highly similar state-transition functions, i.e. only slight differences in parameters, can have significantly different time-series outputs. Furthermore, the classical PGNN cost function regularizes the model estimate over the entire state space with a constant trade-off hyperparameter. In this paper, we introduce a novel model augmentation strategy for nonlinear state-space model identification based on PGNN, using a weighted function regularization (W-PGNN). The proposed approach can efficiently augment the prior physics-based state-space models based on measurement data. A new weighted regularization term is added to the cost function to penalize the difference between the state and output function of the baseline physics-based and final identified model. This ensures the estimated model follows the baseline physics model functions in regions where the data has low information content, while placing greater trust in the data when a high informativity is present. The effectiveness of the proposed strategy over the current PGNN method is demonstrated on a benchmark example. © 2024, CC BY-NC-SA.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Recipe Retrieval With Fine-Grained Prompting Alignment and Evidential Semantic Consistency

引用

IEEE Transactions on Multimedia 2025年 27卷 2783-2794页

作者： Huang, Xu Liu, Jin Zhang, Zhizhong Xie, Yuan Tang, Yongqiang Zhang, Wensheng Cui, Xiaohui Wuhan University School of Computer Science Wuhan430072 China Ministry of Education Wuhan430062 China East China Normal University School of Computer Science and Technology Shanghai200062 China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China Wuhan University School of Cyber Science and Engineering Wuhan430072 China

Alignment between the food images and the corresponding recipes is an emerging cross-modal representation learning task. In this task, the recipes are composed of three components, i.e., food title, ingredient lists, and cooking instructions, which require a fine-grained alignment between the features of the two modalities. Existing methods usually aggregate the recipes into global embeddings and then align them with the global image embeddings. Meanwhile, semantic classification is frequently used in these methods to regularize the embeddings of the two modalities. While these methods are efficient, there remain two problems. (1) Forcing the alignment between the global images and recipes embeddings may result in losing the component-specific information. (2) The high diversity of food appearance leads to high uncertainty in the semantic classification of food images and recipes. To solve these problems, we propose a Fine-grained Prompting and Alignment (FPA) model to enhance the feature extraction and bring more component-specific information for fine-grained alignment. Furthermore, to regularize the semantic information contained in the cross-modal features, we design an Evidential Semantic Consistency (ESC) loss to keep the cross-modal semantic consistency. We have conducted comprehensive experiments on the benchmark dataset Recipe1M and the state-of-the-art results on the cross-modal recipe retrieval task demonstrate the effectiveness of our method. © 1999-2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning in Subsurface Flow Surrogate Model with Physics-Guided Neural Network

Transfer Learning in Subsurface Flow Surrogate Model with Ph...

引用

2024 SPE Annual Technical Conference and Exhibition, ATCE 2024

作者： Cheng, H.B. Qiao, J.H. Wei, Y.C. Li, S.C. Zeng, P. Yu, H.B. State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Institute for Interdisciplinary Information Sciences Tsinghua University Beijing China

ISBN: (纸本)9781959025375

It is a great challenge for reservoir engineers to accurately and quickly model the subsurface flow surrogate for oil and gas reservoirs. The traditional numerical simulation methods are high computational complexity and time-consuming. The widely used pure data- driven flow surrogate methods require massive high-quality data due to lack of theoretical foundation. Therefore, it is necessary to develop transfer learning methods integrating prior knowledge with data-driven deep learning methods to solve complex seepage problems. To reduce data requirements and improving modeling efficiency, a theory-guided and data-driven transfer learning method is proposed to build the fast and accurate subsurface flow surrogate model. Specifically, a data-driven machine learning method is first proposed to simulate and predict the flow processes and build the primary surrogate model. In addition, physical mechanism and constraints are embedded into the data-driven model to make the prediction results satisfy the prior domain knowledge. The transfer learning method based on physics-guided neural network (TL-PG) integrates the seepage theory with sparse spatial data to improve the prediction accuracy of the surrogate model. The proposed TL-PG method is verified by a subsurface flow problem in heterogeneous reservoir models. First, we build a flow field to simulate 50 years of production history. A physics-guided neural network model is trained based on the samples from the first 30 years and tested based on the last 20 years of data. The relative L2 loss and the coefficient of determination R2 are used for comparison. Compared with the purely data-driven method, the relative L2 loss of physics-guided neural network is increased by 16%, and the mean coefficient of determination R2 is up to 0.8932, which means the embedded physical mechanism can greatly improve the performance of neural networks. Secondly, the physics-guided neural network is selected as the pretraining model. Then, th

关键词： Seepage

来源：评论

学校读者我要写书评

暂无评论

Novel vision-LiDAR fusion framework for human action recognition based on dynamic lateral connection

引用

IET Cyber-systems and Robotics 2024年第4期6卷 21-31页

作者： Fei Yan Guangyao Jin Zheng Mu Shouxing Zhang Yinghao Cai Tao Lu Yan Zhuang The School of Control Science and Engineering Dalian University of TechnologyDalianChina Technology Centre of Dalian Customs Dalian CustomsDalianChina ZX‐YZ School of Network Science Haikou University of EconomicsHainanChina The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijingChina

In the past decades,substantial progress has been made in human action ***,most existing studies and datasets for human action recognition utilise still images or videos as the primary ***-based approaches can be easily impacted by adverse environmental *** this paper,the authors propose combining RGB images and point clouds from LiDAR sensors for human action recognition.A dynamic lateral convolutional network(DLCN)is proposed to fuse features from *** RGB features and the geometric information from the point clouds closely interact with each other in the DLCN,which is complementary in action *** experimental results on the JRDB-Act dataset demonstrate that the proposed DLCN outperforms the state-of-the-art approaches of human action *** authors show the potential of the proposed DLCN in various complex scenarios,which is highly valuable in real-world applications.

关键词： neural network-based pedestrian identification sensor fusion

来源：评论

学校读者我要写书评

暂无评论

Automated Linear Parameter-Varying Modeling of Nonlinear systems: A Global Embedding Approach

arXiv

引用

arXiv 2025年

作者： Olucha, E. Javier Koelewijn, Patrick J.W. Das, Amritam Tóth, Roland Control Systems Group Eindhoven University of Technology Eindhoven Netherlands Systems and Control Laboratory HUN-REN Institute for Computer Science and Control Budapest Hungary

In this paper, an automated linear parameter-varying (LPV) model conversion approach is proposed for nonlinear dynamical systems. The proposed method achieves global embedding of the original nonlinear behavior of the system by leveraging the second fundamental theorem of calculus to factorize matrix function expressions without any approximation. The implementation of the proposed method in the LPVcore toolbox for Matlab is discussed, and its performance is showcased on a comprehensive example of automated LPV model conversion of an unbalanced disk system, which is then used to design an LPV controller that is deployed on the original nonlinear system. In addition, the conversion capabilities are further demonstrated by obtaining an LPV embedding of a three-degree-of-freedom control moment gyroscope. All software implementations are available at ***. © 2025, CC BY.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Sampled-Data Iterative Learning control for Linear Time-Varying Switched systems

Event-Triggered Sampled-Data Iterative Learning Control for ...

引用

2023 China automation Congress, CAC 2023

作者： Ma, Xin Dai, Xisheng Zhou, Rusheng School of Automation Guangxi University of Science and Technology Liuzhou China School of Automation Institute of Intelligent Systems and Control Guangxi University of Science and Technology Liuzhou China School of Computer Science and Technology Guangxi University of Science and Technology Liuzhou China

ISBN: (纸本)9798350303759

Consider a class of continues linear time-varying switched systems and study its sampled-data iterative learning control output tracking problem under event triggering. Firstly, in order to reduce the update batch of the control input in the direction of the iteration axis, an event-triggered sampled-data iterative learning control law is designed and the event-triggered conditions are derived by the Lyapunov function method. Secondly, a fixed threshold method is proposed to accelerate the convergence of the system. Then, according to the activation intervals of the switched subsystem,triggered and untriggered are analyzed for convergence, and the sufficient conditions for consistent convergence of the system are derived by the compression mapping method. Finally, the effectiveness of the algorithm is verified by the numerical simulation. © 2023 IEEE.

关键词： Learning algorithms

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：