检索结果-内蒙古大学图书馆

Optical flow-based angular rate sensor fault detection on UAVs*

IFAC-PapersOnLine 2022年第14期55卷 46-51页

作者： Peter Bauer Szabolcs Kun Systems and Control Laboratory Institute for Computer Science and Control (SZTAKI) ELKH Budapest Hungary

The paper first extends the previous work of the authors dealing with optical flow-based angular rate estimation. Extension means consideration of camera position and orientation relative to the UAV body system (non-aligned camera). After the extension the proposed method is evaluated with virtual reality (Unreal-Carla) image sequences considering simulated aircraft flight trajectories and different frames per second (fps) rates. Based-on the results showing high fps requirements for agile flight scenarios a reversed method is proposed for angular rate sensor fault detection considering the integration of system dynamics based-on angular rate and velocity measurements and comparing the predicted image feature positions with the measured ones. The feature position differences are the error measures completed with up-down counters. The results are promising however, only basic evaluation of the proposed methods is done paving the way for detailed evaluation and development outlined in the conclusion.

关键词： angular rate fault detection optical flow UAV

来源：评论

学校读者我要写书评

暂无评论

Indoor vehicle-in-the-loop simulation of unmanned micro aerial vehicle with artificial companion

Indoor vehicle-in-the-loop simulation of unmanned micro aeri...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Antal Hiba Viktor Kortvelyesi Albert Kiskaroly Omkar Bhoite Patrik David Andras Majdik ELKH Computational Optical Sensing and Processing Laboratory Institute for Computer Science and Control (SZTAKI) Budapest Hungary ELKH Machine Perception Research Laboratory Institute for Computer Science and Control (SZTAKI) Budapest Hungary

Vehicle-in-the-loop simulation is an extension of the well-known hardware-in-the-loop technique, where a vehicle moves in real space while a simulator generates input for onboard sensors real-time. VIL frameworks designed for unmanned aerial vehicles have many open challenges. This paper introduces an indoor VIL for micro aerial vehicles in a drone arena equipped with precise positioning system and reliable wireless communication. This indoor setup stands as a prototype and predecessor for other outdoor VIL simulators for large scale applications. The raw optical navigation performance is tested which is the building block for sensor fusion and on-board fast sensor consistency check. A use-case of a companion drone in cooperative navigation is also presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Structurally Recursive Patterns in Data Modeling and Their Resolution 2nd

Structurally Recursive Patterns in Data Modeling and Their R...

引用

2nd International Workshop on Modelling to Program, M2P 2020

作者： Molnár, András J. Computer Science Institute Christian-Albrechts-University Kiel Kiel24098 Germany SZTAKI Institute for Computer Science and Control Budapest1111 Hungary

ISBN: (纸本)9783030726959

By allowing relationship types defined on top of relationship types, the Higher-Order Entity Relationship Model (HERM) enables modeling of complex conceptual structures in a layered way, which usually results in a more compact design than the traditional Entity-Relationship model. Identification of data instances is achieved by composition of the (inherited) key attributes of the referenced instances (foreign keys becoming part of natural keys of higher-order relationships). Well-formedness excludes cycles in the structure. In this paper, we look at the possibility to relax this by allowing structural recursion in the conceptual model. Although it is formally represented as a cycle in the type structure, it will not allow any cycle on the instance (data) level. After looking at some motivating cases and conventional alternatives to this design, and conditions when such a modeling decision is reasonable, we will show how a structurally recursive HERM model can be transformed into an equivalent, conventionally well-formed HERM model, with the utilization of list type construction and complex, variable-length key domains. The analysis reveals some non-trivial aspects of the way of transformation, which may be easily overlooked, but are important to formulate a translation rule for the general case, where derived attributes and aggregation needs are present. The result can be used as a rule for conceptual schema translation for structuring, to obtain an intermediate schema ready for further optimization, and eventually, code generation. © 2021, Springer Nature Switzerland AG.

关键词： Structural design

来源：评论

学校读者我要写书评

暂无评论

Recursive estimation of conditional kernel mean embeddings

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 12780-12814页

作者： Ambrus Tamás Balázs Csanád Csáji Institute for Computer Science and Control (SZTAKI) Hungarian Research Network (HUN-REN) Budapest Hungary Department of Probability Theory and Statistics Institute of Mathematics Eötvös Loránd University (ELTE) Budapest Hungary

Kernel mean embeddings, a widely used technique in machine learning, map probability distributions to elements of a reproducing kernel Hilbert space (RKHS). For supervised learning problems, where input-output pairs are observed, the conditional distribution of outputs given the inputs is a key object. The input dependent conditional distribution of an output can be encoded with an RKHS valued function, the conditional kernel mean map. In this paper we present a new recursive algorithm to estimate the conditional kernel mean map in a Hilbert space valued L2 space, that is in a Bochner space. We prove the weak and strong L2 consistency of our recursive estimator under mild conditions. The idea is to generalize Stone's theorem for Hilbert space valued regression in a locally compact Polish space. We present new insights about conditional kernel mean embeddings and give strong asymptotic bounds regarding the convergence of the proposed recursive method. Finally, the results are demonstrated on three application domains: for inputs coming from Euclidean spaces, Riemannian manifolds and locally compact subsets of function spaces.

关键词： conditional kernel mean embeddings recursive estimation reproducing kernel Hilbert spaces strong consistency nonparametric inference Riemannian manifolds

来源：评论

学校读者我要写书评

暂无评论

Length independent generalization bounds for deep SSM architectures

arXiv

引用

arXiv 2024年

作者： Rácz, Dániel Petreczky, Mihály Daróczy, Bálint Institute for Computer Science and Control HUN-REN SZTAKI Budapest Hungary Eötvös Loránd University Budapest Hungary Université de Lille CNRS Centrale Lille France Institute for Computer Science and Control HUN-REN SZTAKI Budapest Hungary Széchenyi István University Győr Hungary

Many state-of-the-art models trained on long-range sequences, for example S4, S5 or LRU, are made of sequential blocks combining State-Space Models (SSMs) with neural networks. In this paper we provide a PAC bound that holds for these kind of architectures with stable SSM blocks and the bound does not depend on the length of the input sequence. Imposing stability of the SSM blocks is a standard practice in the literature, and it is known to help performance. Our results provide a theoretical justification for the use of stable SSM blocks as the proposed PAC bound decreases as the degree of stability of the SSM blocks *** Codes 68 © 2024, CC BY.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity and Autonomous Driving: Experiments with LiDAR Sensor Spoofing

Cybersecurity and Autonomous Driving: Experiments with LiDAR...

引用

Communications, Information, Electronic and Energy Systems (CIEES), International Conference on

作者： Ernő Rigó Péter Árvai Valéria Póser Institute for Computer Science and Control (SZTAKI) Hungarian Research Network (HUN-REN) Budapest Hungary Biomatics and Applied Artificial Intelligence Institute Óbuda University Budapest Hungary

ISBN: (数字)9798350352863

ISBN: (纸本)9798350352870

This research investigates the vulnerability of onboard navigation sensors in autonomous vehicles to cybersecurity attacks. By exploiting the interconnectedness of these systems, adversaries can manipulate sensor data, compromise software, or physically interfere with sensors, potentially leading to serious consequences. This study describes cybersecurity experiments on a hardware-in-the-loop autonomous vehicle testbed, focusing on cyberattacks against LiDAR-based navigation, exploring various attack vectors, including jamming and various methods of spoofing. Experimental results demonstrate the feasibility of these attacks and highlight the need for robust security measures to protect autonomous vehicles from cyber threats. The findings emphasize the importance of ongoing research in developing effective countermeasures to ensure the safety and reliability of autonomous driving systems.

关键词： Laser radar Navigation Sensor systems Vectors Software Sensors Safety Reliability computer crime Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Enabling Technologies for Autonomous Robotic Systems in Manufacturing

引用

Transactions of Nanjing University of Aeronautics and Astronautics 2024年第4期41卷 403-431页

作者： ERDŐS Gábor ABAI Kristóf BEREGI Richárd CSEMPESZ János CSERTEG Tamás GODÓGábor HAJÓS Mátyás HÁY Borbála HORVÁTH Dániel HORVÁTH Gergely JUNIKIÁdám KEMÉNY Zsolt KOVÁCS András NACSA János PANITI Imre PEDONE Gianfranco TAKÁCS Emma TIPARY Bence ZAHORÁN László VÁNCZA József Institute for Computer Science and Control Hungarian Research Network(HUN-REN SZTAKI)BudapestHungary Department of Manufacturing Science and Technology Budapest University of Technology and Economics(BME)BudapestHungary EPIC InnoLabs Nonprofit Ltd. BudapestHungary Eötvös Loránd University(ELTE) BudapestHungary

Research of autonomous manufacturing systems is motivated both by the new technical possibilities of cyber-physical systems and by the practical needs of the *** operation in semi-structured industrial environments can now be supported by advanced sensor technologies,digital twins,artificial intelligence and novel communication *** enable real-time monitoring of production processes,situation recognition and prediction,automated and adaptive(re)planning,teamwork and performance improvement by *** paper summarizes the main requirements towards autonomous industrial robotics and suggests a generic workflow for realizing such *** case studies will be presented from recent practice at HUN-REN sztaki in a broad range of domains such as assembly,welding,grinding,picking and placing,and *** various solutions have in common that they use a generic digital twin concept as their *** making general recommendations for realizing autonomous robotic solutions in the industry,open issues for future research will be discussed.

关键词： industrial robotics autonomy digital twin enabling technology

来源：评论

学校读者我要写书评

暂无评论

Robust Independence Tests with Finite Sample Guarantees for Synchronous Stochastic Linear Systems

arXiv

引用

arXiv 2023年

作者： Tamás, Ambrus Bálint, Dániel Ágoston Csáji, Balázs Csanád SZTAKI: Institute for Computer Science and Control Eötvös Loránd Research Network Budapest Hungary Budapest Hungary

The paper introduces robust independence tests with non-asymptotically guaranteed significance levels for stochastic linear time-invariant systems, assuming that the observed outputs are synchronous, which means that the systems are driven by jointly i.i.d. noises. Our method provides bounds for the type I error probabilities that are distribution-free, i.e., the innovations can have arbitrary distributions. The algorithm combines confidence region estimates with permutation tests and general dependence measures, such as the Hilbert–Schmidt independence criterion and the distance covariance, to detect any nonlinear dependence between the observed systems. We also prove the consistency of our hypothesis tests under mild assumptions and demonstrate the ideas through the example of autoregressive systems. Copyright © 2023, The Authors. All rights reserved.

关键词： Linear time-invariant system

来源：评论

学校读者我要写书评

暂无评论

An improved side-slip estimation algorithm based on ultra-local model technique for autonomous vehicles

An improved side-slip estimation algorithm based on ultra-lo...

引用

International Conference on control, Decision and Information Technologies (CoDIT)

作者： Dániel Fényes Tamás Hegedűs Balázs Németh Vu Van Tan Péter Gáspár HUN-REN Institute for Computer Science and Control (SZTAKI) Budapest Hungary Department of Automotive Mechanical Engineering Faculty of Mechanical Engineering University of Transport and Communications Hanoi Vietnam

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

The paper presents a novel observer design method for estimating the front and rear wheel slips of the vehicle. The proposed observer design technique consists of two parts: A simple linear observer algorithm, which uses a reformulated lateral vehicle model to estimate the tire slips. The second part is based on an ultra-local model. The main goal of the ultra-local model is to eliminate the nonlinear, unmodeled, uncertain dynamics of the lateral vehicle model. In this way, the performance level of the linear observer can be significantly increased especially under critical circumstances such as high lateral acceleration maneuvers or driving on a low µ surface. The proposed observer algorithm is implemented in MATLAB/Simulink environment connected to the high-fidelity simulation software, CarMaker. The operation and the effectiveness of the proposed observer are demonstrated through several simulation examples.

关键词： Heuristic algorithms Software algorithms Wheels Observers Mathematical models Tires Software Vehicle dynamics MATLAB Information technology

来源：评论

学校读者我要写书评

暂无评论

Evaluating Transferability of BERT Models on Uralic Languages 7

Evaluating Transferability of BERT Models on Uralic Language...

引用

7th International Workshop on Computational Linguistics of Uralic Languages, IWCLUL 2021

作者： Ács, Judit Lévai, Dániel Kornai, András SZTAKI Institute for Computer Science and Control Hungary Department of Digital Humanities Eötvös Loránd University Hungary

ISBN: (纸本)9781954085824

Transformer-based language models such as BERT have outperformed previous models on a large number of English benchmarks, but their evaluation is often limited to English or a small number of well-resourced languages. In this work, we evaluate monolingual, multilingual, and randomly initialized language models from the BERT family on a variety of Uralic languages including Estonian, Finnish, Hungarian, Erzya, Moksha, Karelian, Livvi, Komi Permyak, Komi Zyrian, Northern Sámi, and Skolt Sámi. When monolingual models are available (currently only et, fi, hu), these perform better on their native language, but in general they transfer worse than multilingual models or models of genetically unrelated languages that share the same character set. Remarkably, straightforward transfer of high-resource models, even without special efforts toward hyperparameter optimization, yields what appear to be state of the art POS and NER tools for the minority Uralic languages where there is sufficient data for finetuning. © 2021 IWCLUL 2021 - 7th International Workshop on Computational Linguistics of Uralic Languages, Proceedings. All rights reserved.

关键词： Computational linguistics

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：