检索结果-内蒙古大学图书馆

IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)

作者： Dániel Fényes Tamás Hegedűs Balázs Németh Péter Gáspár Institute for Computer Science and Control (SZTAKI) Eötvös Loránd Research Network (ELKH) Budapest Hungary

ISBN: (纸本)9781665479226

The paper proposes an enhanced observer design method for autonomous vehicles, with which the unmeasurable states in vehicle and chassis motion can be estimated. The novelty of the method is that the learning-based observer and the linear parameter varying (LPV) observer in a joint observer design structure are incorporated, which results in an improved performance level on the estimation error. Nevertheless, the proposed design method is able to guarantee the limitation of the estimation error, even if the error of the learning-based observer under all scenarios cannot be verified. Thus, the proposed method handles the main disadvantage of the learning-based approaches, i.e. the lack of performance guarantees, while their advantages, i.e. the improved observation performance in the operation of the observer are taken. The proposed method is applied on a lateral path following control problem, where the goal of the observer is to provide an accurate lateral velocity signal for the vehicle. The effectiveness of the method is illustrated through simulation examples on high- fidelity vehicle dynamic simulator CarSim.

关键词： Estimation error Uncertain systems Systematics Design methodology Conferences Roads Observers

来源：评论

学校读者我要写书评

暂无评论

A probabilistic perspective on nearest neighbor for implicit recommendation

A probabilistic perspective on nearest neighbor for implicit...

引用

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Domokos M. Kelen Andras A. Benczúr Institute for Computer Science and Control (SZTAKI) Eötvös Loránd Research Network (ELKH) Budapest Hungary

ISBN: (纸本)9781665424288

Over the past years, the recommender systems community invented several novel approaches that reached better and better prediction accuracy. Remarkably, however, the classic k nearest neighbor algorithm appears to remain competitive, even when compared to much more sophisticated methods. In this paper, we attempt to explain the inner workings of the nearest neighbor using probabilistic tools, treating similarity as conditional probability and presenting a novel model for explaining and removing popularity ***, we provide a probabilistic formulation of similarity and the classic prediction formula. Second, by modeling user behavior as a combination of personal preference and global influence, we are able to explain the presence of popularity bias in the predictions. Finally, we utilize Bayesian inference to construct a theoretically grounded variant of the widely used inverse frequency scaling, which we use to mitigate the effect of popularity bias in the *** replacing the formerly ad hoc choices of nearest neighbor with probabilistically founded counterparts, we are able to improve prediction accuracy over a variety of data sets and gain an increased understanding of the theory behind the method.

关键词： Uncertainty Predictive models Nearest neighbor methods Probabilistic logic Prediction algorithms Data models Bayes methods

来源：评论

学校读者我要写书评

暂无评论

A tracking performance analysis method for autonomous systems with neural networks ⁎

引用

IFAC-PapersOnLine 2021年第1期54卷 696-701页

作者： Attila Lelkó Balázs Németh Péter Gáspár Systems and Control Laboratory Institute for Computer Science and Control (SZTAKI) Eötvös Loránd Research Network (ELKH) Kende u. 13-17 H-1111 Budapest Hungary

Intelligent manufacturing and automated systems several complex control tasks must be carried out. A possible way for improving the performance level of the systems is the application of machine-learning-based agents, e.g. neural networks in the control loop. A novel challenge of these complex systems is to provide analysis and synthesis methods, with which their performance levels can be assessed. The paper proposes analysis method for tracking control systems, whose control loop contains feed-forward neural networks. Through the method the asymptotic stability and the tracking performance through decay rate are assessed. The proposed method is based on the linear approximation of the closed-loop system, and thus, a polytopic set of linear systems is resulted. Using the resulted polytopic system an analysis method based on an optimization is formed, whose result approximates the decay rate of the system. The effectiveness of the method is illustrated through a benchmark example, i.e. the torque control of a one-degree-of-freedom robotic arm.

关键词： performance analysis neural network control systems robotic arm

来源：评论

学校读者我要写书评

暂无评论

Design of learning-based control with guarantees for autonomous vehicles in intersections

引用

IFAC-PapersOnLine 2021年第2期54卷 210-215页

作者： Balázs Németh Péter Gáspár Systems and Control Laboratory Institute for Computer Science and Control (SZTAKI) Eötvös Loránd Research Network (ELKH) Kende u. 13-17 H-1111 Budapest Hungary

This paper proposes a design method for the coordination of velocity profiles of autonomous vehicles in non-signalized intersection scenarios. The coordination is motivated by the avoidance of vehicle collision and the minimization of their energy loss resulted by stop and go maneuvers in the intersection. Therefore, the coordinated design is formed as an optimal control problem, which is solved through two optimization tasks. A quadratic optimization task with online solution is formed, which provides guarantees on the avoidance of the collision. Moreover, a reinforcement-learning-based optimization task with offline solution is formed, which is able to improve the economy performances of the autonomous vehicles. The optimization tasks are interconnected, i.e. the quadratic optimization with the vehicle model is used as an environment during the training process. The effectiveness of the proposed coordinated control through simulation examples with three number of autonomous vehicles is illustrated.

关键词： automated vehicles intersection reinforcement learning collision avoidance

来源：评论

学校读者我要写书评

暂无评论

Design of fault-tolerant cruise control in a hierarchical framework for connected automated vehicles

Design of fault-tolerant cruise control in a hierarchical fr...

引用

Conference on control and Fault-Tolerant Systems (SysTol)

作者： Balázs Németh András Mihály Péter Gáspár Institute for Computer Science and Control (SZTAKI) Eötvös Loránd Research Network (ELKH) H-1111 Budapest Hungary

This paper presents a design method for the cruise control of connected automated vehicles. The proposed control system contains layers with different functionalities, which are interconnected in a hierarchical structure. The reason for using layers is to separate the functionalities which require different computation efforts. The layer on the high level computes a reference speed signal for the vehicle, which considers the economy and time performance requirements. It requires the solution of a complex optimization problem, which is performed in a cloud with low frequency. There are two further layers on the level of the vehicle, such as the signal analysis and the local control layers. The purpose of the signal analysis layer is to examine the feasibility of the reference speed regarding vehicle safety performances. This layer is designed to require low computation effort and on-board sensor measurements, thus analysis can be performed with high frequency. The proposed hierarchical cruise control is able to handle the priorities between the various performance requirements, thus safe motion of the vehicle is guaranteed under every circumstances.

关键词： Fault tolerance Cloud computing Design methodology Fault tolerant systems Safety Frequency measurement High frequency

来源：评论

学校读者我要写书评

暂无评论

Fault-tolerant control of semi-active suspension in case of oil leakage of magnetorheological damper

Fault-tolerant control of semi-active suspension in case of ...

引用

European control Conference (ECC)

作者： Hakan Basargan Filip Jeniš András Mihály Péter Gáspár Department of Control for Transportation and Vehicle Systems Budapest University of Technology and Economics Stoczek u. 2 Budapest Hungary Faculty of Mechanical Engineering Institute of Machine and Industrial Designs Brno University of Technology Technicka 2 Brnos Czech Republic Systems and Control Laboratory Institute for Computer Science and Control (SZTAKI) Eötvös Loránd Research Network (ELKH) Kende u. 13-17 Budapest Hungary

The paper presents a reconfigurable fault-tolerant control strategy for a semi-active suspension using magnetorheological (MR) damper. The aim of the control reconfiguration is to handle the adverse behaviour of the MR damper due to oil leakage induced by the wear of the suspension component. The proposed method relies on the data driven model of the MR damper, using an estimation procedure to quantify the healthiness of the damper and to estimate the performance degradation due to the oil leakage. The reconfiguration control strategy is founded on the Linear Parameter Varying (LPV) framework, where a scheduling variable is defined to represent the healthiness level of the MR damper. By the scaling of the control action through the scheduling variable, the performance degradation of the MR damper can be compensated to match the behaviour of the healthy dampers. The proposed method is demonstrated through simulations, comparing the performance of the fault-tolerant LPV control to conventional semi-active control methods

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fault detection in GPU-enabled Cloud Systems – An Overview

Fault detection in GPU-enabled Cloud Systems – An Overview

引用

International Symposium on Applied Machine Intelligence and Informatics (SAMI)

作者： Farida Asadova Gá bor Kerté sz Ró bert Lovas Sá ndor Szé ná si Doctoral School of Applied Informatics and Applied Mathematics &#x00D3 buda University Hungary Institute for Computer Science and Control (SZTAKI) E&#x00F6 tv&#x00F6 s Lor&#x00E1 nd Research Network (ELKH) Hungary John von Neumann Faculty of Informatics &#x00D3

Fault detection and handling are crucial tasks in cloud systems. As these infrastructures are growing and evolving, manual monitoring and interaction have become less feasible. To deal with this issue, monitoring systems are developed to track the behavior of the various components (e.g. nodes) in cloud systems, as well as the served applications in the virtual environment. Nowadays, most cloud environments provide graphics accelerators for their users leading to different problems. However, the application of GPUs in deep learning could also help the detection of incorrect behavior. In this paper, a short overview of cloud monitoring and fault detection methods is given focusing on GPU-enabled nodes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrated adaptive velocity and semi-active suspension control for different road profiles

Integrated adaptive velocity and semi-active suspension cont...

引用

Mediterranean Conference on control and Automation (MED)

作者： Hakan Basargan Andrá s Mihá ly Pé ter Gá spá r Oliver Sename BME Department of Control for Transportation and Vehicle Systems Stoczek u. 2 Budapest Hungary Systems and Control Laboratory Institute for Computer Science and Control (SZTAKI) E&#x00F6 tv&#x00F6 s Lor&#x00E1 nd Research Network (ELKH) Budapest Hungary GIPSA-lab INPG Universit&#x00E9 Grenoble Alpes Grenoble France

ISBN: (数字)9781665406734

ISBN: (纸本)9781665406741

This study represents the integrated comfort-oriented velocity design, tracking control, and adaptive semi-active suspension control method. The velocity design approach is based on the ISO 2631-1 standard, while the proposed velocity tracking control method is based on the LPV control architecture. A road adaptive semi-active suspension control method, where a trade-off between vehicle stability and driving comfort is accomplishable to achieve desirable performance results at different road profiles and velocities. The trade-off is accomplishable due to flexibility and online reconfigurability of the LPV control method by online modification of scheduling variables. The design is based on the performance index, road profile, and the designed velocity of the velocity. The velocity designer, velocity tracking controller, and adaptive suspension controller have been integrated and simulated in the TruckSim environment to show the operation of the proposed method.

关键词： Suspensions (mechanical systems) Databases Roads ISO Standards Design methodology Stability criteria Dynamic scheduling

来源：评论

学校读者我要写书评

暂无评论

Tabular Q-learning Based Reinforcement Learning Agent for Autonomous Vehicle Drift Initiation and Stabilization

引用

IFAC-PapersOnLine 2023年第2期56卷 4896-4903页

作者： Szilárd H. Tóth Ádám Bárdos Zsolt J. Viharos Department of Automotive Technologies Budapest University of Technology and Economics Budapest Hungary Research Laboratory on Engineering and Management Intelligence Intelligent Processes Research Group Institute of Computer Science and Control Centre of Excellence in Production Informatics and Control Eötvös Loránd Research Network (ELKH) Centre of Excellence of the Hungarian Academy of Sciences (MTA) Budapest Hungary Department of Management and Business Law Faculty of Economics John von Neumann University Kecskemét Hungary

This paper aims to report on novel research results about developing a reinforcement learning agent for steady-state vehicle drift motion control. Based on the previous results of this research, the primary goal was to eliminate the problems causing learning instability experienced with the Soft Actor-Critic (SAC) algorithm applying Tabular Q-learning in this work. Trained in a MATLAB/Simulink-based simulation environment, the resulting agent succeeded in this task while being able to smoothly operate the vehicle to achieve and retain the desired target drift state, regardless of the discreet nature of the algorithm used for solving an inherently continuous task.

关键词： Motion control Autonomous Vehicles Vehicle Dynamics control Reinforcement Learning Vehicle Drifting Handling Limits

来源：评论

学校读者我要写书评

暂无评论

LPV-Based control Design with Guarantees: a Case Study for Automated Steering of Road Vehicles

LPV-Based Control Design with Guarantees: a Case Study for A...

引用

European control Conference (ECC)

作者： Balázs Németh Máté Fazekas Zoltán Bagoly Péter Gáspár Olivier Sename Eötvös Loránd Research Network (ELKH) Kende u. 13-17 Institute for Computer Science and Control (SZTAKI) Budapest Hungary Department of Control for Transportation and Vehicle Systems (KJIT) Budapest University of Technology and Economics (BME) Stoczek u. 2. Budapest Hungary Grenoble INP GIPSAlab Univ. Grenoble Alpes CNRS Grenoble France

This paper proposes a Linear Parameter Varying (LPV) based steering control design method, which contains data aided control elements, e.g., learning-based agents. The framework is based on a supervisory control structure, which contains a supervisor, a LPV controller and the data aided control element. The goal of this paper is to provide a safe steering control, with which the human steering intervention can be effectively imitated. Moreover, in the proposed framework the data aided control can be adapted to the actual requirements on driving style, without re-designing the LPV control. Thus, a general control structure with performance guarantees on path following constraints is provided, in which the data aided steering control element can be varied. The effectiveness of the proposed method through driver-in-the-loop scenarios is illustrated, in which different settings on the control system are analyzed.

关键词：

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：