检索结果-内蒙古大学图书馆

63rd IEEE Conference on Decision and control, CDC 2024

作者： Gerasimov, Dmitry N. Ngo, Dang Hien Nikiforov, Vladimir O. Itmo University Faculty of Control Systems and Robotics Saint Petersburg Russia

ISBN: (纸本)9798350316339

The paper considers the problem of the state-feedback adaptive control of a class of discrete linear time-varying plant with multisinusoidal parameters. The plant is representable in the strict-feedback form, in which the parameters are on the main diagonal of the state matrix. The amplitudes, frequencies, and the phases of the multisinusoids are not known a priori, however the maximum numbers of sinusoids (harmonics) in each parameter are available. The problem is solved by design of periodic parameters observers recovering the parameters dynamics, the plant parameterization, and developing a discrete-time adaptive backstepping controller. In order to tune the controller parameters and improve the closed-loop transient performance, an adaptation algorithm with memory regressor extension is applied. The main results of the paper are demonstrated by simulation. © 2024 IEEE.

关键词： State feedback

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Highway Driving Decision-making Using CDR (Curriculum based Domain Randomization)

引用

Journal of Institute of control, robotics and Systems 2025年第2期31卷 114-123页

作者： Yong, Jae-Hyoung Kim, Min-Sung Park, Tae-Hyoung Department of Intelligent System and Robotics Chungbuk National University Korea Republic of Department of Control Robot Engineering Chungbuk National University Korea Republic of Department of Intelligent System and Robotics Chungbuk National University Chungbuk National University Hospital Korea Republic of

Incorrect autonomous driving decisions on highways can lead to traffic congestion and accidents. Therefore, accurate decision-making in highways is essential. However, decision-making in highways is a challenging task due to the complexity of traffic situations. Thus, reinforcement learning is an appropriate approach for decision-making in highways. However, a domain gap often arises between the training and testing environments due to differences in them. Therefore, a curriculum-based domain randomization approach is applied, which progressively adjusts the level of random parameters. The RL model is trained using the SUMO simulator and tested in the MORAI simulator, where white noise is added to simulate real-world conditions. Consequently, applying curriculum domain randomization has the lowest collision rate. © ICROS 2025.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Observer-Based Leader-Following Secure Consensus for Multi-Agent Systems with Nonlinear Dynamics and External Disturbance Under Denial of Service Attacks 5

Observer-Based Leader-Following Secure Consensus for Multi-A...

引用

5th International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2024

作者： Hu, Liduo Zhang, Wei Hu, Zhi Cai, Yuhang Shanghai University of Engineering Science Laboratory of Intelligent Control and Robotics Shanghai China

ISBN: (纸本)9798331528911

This paper introduces an Unknown Input Observer (UIO) for nonlinear systems with One-Sided Lipschitz (OSL) and Quadratic Inner-Boundedness (QIB) properties. The UIO enables unknown input reconstruction and state estimation. Besides the UIO show resilience against Denial of Service (DoS) attacks that can disrupt multi-agent communication. To counteract these attacks, the system uses buffer units to retain real-time data, allowing agents to access the latest states during disruptions. We present a control protocol that facilitates leader-follower consensus under simultaneous DoS attacks, detailing the upper limits on their frequency and duration. Numerical simulations demonstrate the approach's effectiveness. © 2024 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Efficient Multi-task Learning for Road Scene Classification: Scene, Time, and Weather Predictions 20

Efficient Multi-task Learning for Road Scene Classification:...

引用

20th IEEE International Conference on Intelligent Computer Communication and Processing Conference, ICCP 2024

作者： Prykhodchenko, Roman Skruch, Pawel Agh University of Science and Technology Department of Automatic Control and Robotics Cracow Poland

ISBN: (纸本)9798331539979

This paper addresses the task of road scene classification by leveraging multi-task learning (MTL) to improve model performance and computational efficiency. We employ the BDD100K dataset, which provides diverse driving scenarios, and apply data augmentation and balancing techniques to mitigate class imbalances. Our methodology integrates a ResNet18 backbone pre-trained on ImageNet, extended with task-specific heads for scene type, time of day, and weather classification. Uniform Manifold Approximation and Projection (UMAP) is used for dimensionality reduction and visualization of feature embeddings. Experiments demonstrate that our MTL approach significantly enhances classification accuracy across tasks, with notable performance in time-of-day classification. The proposed model achieves robust results despite class imbalances, validated through confusion matrices and UMAP visualizations. Our findings highlight the benefits of MTL in road scene classification, offering insights for future research in autonomous driving and computer vision. © 2024 IEEE.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Using Docker Containers in Teaching of Advanced Data Analytics Methods 11

Using Docker Containers in Teaching of Advanced Data Analyti...

引用

11th IEEE International Conference on E-Learning in Industrial Electronics, ICELIE 2024

作者： Gaweda, Bartlomiej Bauer, Waldemar Baranowski, Jerzy AGH University of Krakow Dept. of Automatic Control and Robotics Krakow Poland

ISBN: (纸本)9798350363654

In this paper we consider an important problem in teaching of advanced theory is that you need access to complicated software. In many cases in order to allow students to participate in more challenging classes, like Bayesian data analysis, or advanced FPGA programming you encounter an issue that setting up the relevant software on their machines consumes significant part of the course, and you need to troubleshoot issues that are irrelevant to the actual topic. We present a solution from our own experience that is using container software i.e. Docker and we show how it significantly improved our work when teaching data analytics and Bayesian methods in general. © 2024 IEEE.

关键词： containers probabilistic programming teaching statistical modeling

来源：评论

学校读者我要写书评

暂无评论

On Finite-Time Average Consensus for Three-Agent System

On Finite-Time Average Consensus for Three-Agent System

引用

2024 International Russian Automation Conference, RusAutoCon 2024

作者： Galkina, Daria Zhdanov, Victor Itmo University Faculty of Control Systems and Robotics St. Petersburg Russia

This paper addresses the problem of finite-time average consensus design for a system of three agents. Although this issue has been previously resolved for arbitrary order, this study offers new estimates for settling time. The primary objective is to evaluate the applicability of the proposed approach for more complex scenarios, including an arbitrary number of agents and agents with higher-order dynamics. By providing new insights and estimates, this research aims to enhance the understanding and implementation of finite-time average consensus protocols, potentially leading to more efficient and effective strategies in multi-agent systems across various applications, such as robotics, networked control systems, cooperative control and observer design. © 2024 IEEE.

关键词： Networked control systems

来源：评论

学校读者我要写书评

暂无评论

Maintenance of Operable Condition of a Flexible Production System Through the Development and Implementation of a Method for Cutting Tools and Workpieces Operational control

Maintenance of Operable Condition of a Flexible Production S...

引用

2024 International Russian Smart Industry Conference, SmartIndustryCon 2024

作者： Basova, Tatiana V. Andreev, Yuri S. ITMO University Faculty of Control Systems and Robotics St. Petersburg Russia

ISBN: (纸本)9798350395044

The objective of this research is to maintain the operational state of a flexible manufacturing system (FMS) within the required timeframe by developing and implementing a method for operational control of cutting tools and processed workpieces. A reliable technological system (TS) for the mechanical processing operation is to maintain the production of parts with the required quality and quantity within the specified time, particularly crucial when considering FMSs that eliminate personnel to constantly monitor the technological operation. Through the conducted analytical review, the relevance and immediacy of the work aimed at developing the method for operational control of cutting tools and workpieces are emphasized. This method involves the autonomous operation of the TS through multisensory integration of data on changes in geometric parameters of cutting tools and workpieces, with programming automation and management of information about cutting tools using a database of cutting and auxiliary tool parameters. Within the scope of the research, an experimental validation of the proposed method was conducted, along with solutions addressing issues related to predicting the technical condition of cutting tools for enterprises in the instrument-making and machinery industries under actual production conditions. The prediction of the technical condition of cutting tools was performed using artificial intelligence (AI) methods. The proposed approach for obtaining initial data for developing predictive models is characterized by its reliability, minimizing erroneous results from technical diagnostic and control systems operating independently. © 2024 IEEE.

关键词： Cutting tools

来源：评论

学校读者我要写书评

暂无评论

Maintaining a Wireless Sensor Network Structure in a Variable Dynamic Environment

Maintaining a Wireless Sensor Network Structure in a Variabl...

引用

2024 International Russian Smart Industry Conference, SmartIndustryCon 2024

作者： Galkina, Daria Tomashevish, Stanislav Borisov, Oleg ITMO University Faculty of Control Systems and Robotics St. Petersburg Russia

ISBN: (纸本)9798350395044

This article discusses a wireless sensor network, in which elements are attached to a group of robots located on the surface of the water. Due to the group being exposed by constant and unpredictable environmental influences such as wind, waves and swell, the structure of the wireless sensor network can be disrupted to complete failure. Because of this, there is a need to synthesize a control algorithm that could support a predetermined structure of a wireless sensor network on the surface of the water. The proposed algorithm is quite simple to implement, is distinguished by its flexibility and allows to accurately specify the desired shape of the network structure in advance. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

ML-Based Inertial Navigation System Diagnosis for Underwater Vehicle

ML-Based Inertial Navigation System Diagnosis for Underwater...

引用

2024 International Russian Automation Conference, RusAutoCon 2024

作者： Galkina, Daria Margun, Alexey Iureva, Radda Faculty of Control Systems and Robotics Itmo University St. Petersburg Russia

This paper investigates ML methods for diagnosing failures in an integrated Inertial Navigation System (INS) of the underwater vehicle ODIN UAV. Using dynamic equations of motion and considering measurement noise, a dataset was generated during normal operation and during various failures. Data preprocessing, exploratory analysis and feature engineering were conducted. To solve the problem of INS technical state classification, multiple machine learning models were evaluated and optimized using training data and techniques to reduce the number of dimensions. A comparative analysis of the obtained results was carried out. The paper contributes insights into effective ML-based diagnostics for enhancing navigation system reliability in autonomous underwater robots. © 2024 IEEE.

关键词： Inertial navigation systems

来源：评论

学校读者我要写书评

暂无评论

Robustness to Disturbances of Ellipsoid-Shape Underwater Vehicle with Multi-Link Manipulator

Robustness to Disturbances of Ellipsoid-Shape Underwater Veh...

引用

2024 International Russian Automation Conference, RusAutoCon 2024

作者： Lipko, Ivan Dementiev, Kirill Kramar, Vadim Sevastopol State University Robotics and Intelligent Control Systems Laboratory Sevastopol Russia

This article is devoted to the issue of analyzing the influence of external disturbances on the underwater vehicle in the form of a flattened ellipsoid body with a multilink manipulator when performing technological operations. The relevance of the study is related to the automation of such operations as underwater welding, transfer of objects, twisting, bending, etc., performed underwater. For this purpose, we have built a mathematical model of the underwater apparatus with an ellipsoid shape, indicated the ways of influence of moments and forces arising in the manipulator on the apparatus body. It was found out that this influence leads to nonlinear effects in transients. This influence is different, depending on the axis in which the motion of the apparatus is performed. Since the body is flattened in the horizontal axis, the most unpleasant effect occurs in the vertical motion, due to the increased hydrodynamic resistance. The model is considered without a control loop in the apparatus, and it is the effect of the housing on the accuracy of movements of a multilink manipulator with a standard control system in the form of PID controllers that is important to us. © 2024 IEEE.

关键词： Underwater welding

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：