检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Xinyu Knoedler, Luzia Mathiesen, Frederik Baymler Alonso-Mora, Javier The Cognitive Robotics Department Delft University of Technology Delft2628 CD Netherlands The Delft Center for Systems and Control Delft University of Technology Delft2628 CD Netherlands

control Barrier Functions (CBFs) that provide formal safety guarantees have been widely used for safety-critical systems. However, it is non-trivial to design a CBF. Utilizing neural networks as CBFs has shown great success, but it necessitates their certification as CBFs. In this work, we leverage bound propagation techniques and the Branch- and-Bound scheme to efficiently verify that a neural network satisfies the conditions to be a CBF over the continuous state space. To accelerate training, we further present a framework that embeds the verification scheme into the training loop to synthesize and verify a neural CBF simultaneously. In particular, we employ the verification scheme to identify partitions of the state space that are not guaranteed to satisfy the CBF conditions and expand the training dataset by incorporating additional data from these partitions. The neural network is then optimized using the augmented dataset to meet the CBF conditions. We show that for a non-linear control-affine system, our framework can efficiently certify a neural network as a CBF and render a larger safe set than state-of-the-art neural CBF works. We further employ our learned neural CBF to derive a safe controller to illustrate the practical use of our framework. Copyright © 2023, The Authors. All rights reserved.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attacks Against Uncertainty Quantification

Adversarial Attacks Against Uncertainty Quantification

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Emanuele Ledda Daniele Angioni Giorgio Piras Giorgio Fumera Battista Biggio Fabio Roli Department of Computer Control and Management Engineering Sapienza University of Rome Italy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genova Italy Department of Electric and Electronic Engineering University of Cagliari Italy

Machine-learning models can be fooled by adversarial examples, i.e., carefully-crafted input perturbations that force models to output wrong predictions. While uncertainty quantification has been recently proposed to detect adversarial inputs, under the assumption that such attacks exhibit a higher prediction uncertainty than pristine data, it has been shown that adaptive attacks specifically aimed at reducing also the uncertainty estimate can easily bypass this defense mechanism. In this work, we focus on a different adversarial scenario in which the attacker is still interested in manipulating the uncertainty estimate, but regardless of the correctness of the prediction; in particular, the goal is to undermine the use of machine-learning models when their outputs are consumed by a downstream module or by a human operator. Following such direction, we: (i) design a threat model for attacks targeting uncertainty quantification; (ii) devise different attack strategies on conceptually different UQ techniques spanning for both classification and semantic segmentation problems; (iii) conduct a first complete and extensive analysis to compare the differences between some of the most employed UQ approaches under attack. Our extensive experimental analysis shows that our attacks are more effective in manipulating uncertainty quantification measures than attacks aimed to also induce misclassifications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Model-Free control for Tendon-Driven Continuum Robotic Arms

Intelligent Model-Free Control for Tendon-Driven Continuum R...

引用

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Nima Maghooli Omid Mahdizadeh S. Ali A. Moosavian Department of Mechanical Engineering Center of Excellence in Robotics and Control Advanced Robotic and Automated Systems (ARAS) K. N. Toosi University of Technology Tehran Iran

Continuum manipulator modeling is always associated with structured and unstructured uncertainties. Therefore, model-based control system design for this class of robotic systems will be very challenging. On the other hand, the performance quality of model-free controllers is completely dependent on their hyperparameters; they are also very sensitive to the considered trajectory for the system. As a result, using model-free controllers will require setting parameters for different scenarios. In this research, the design of a model-free controller with comparable performance to model-based control strategies is presented. To this end, various parameters are determined online by the gain adjustment system. The research innovation is to use a supervised machine learning method, fuzzy inference system (FIS), to implement the intelligent gain adaptation system to achieve this goal. The Modified Transpose Jacobian (MTJ) performs well in trajectory tracking due to its approximated feedback linearization tool. In addition, the PID controller structure makes it a locally robust control strategy. An adaptive gain adjustment system can greatly increase algorithm potential and establish the capability to follow trajectories in different work points in the system work space. This research aims to improve the performance of the MTJ model-free control strategy in tracking trajectories starting from arbitrary initial conditions in the system work space. This is achieved by the gain adjustment system design using a fuzzy inference system. Both simulation and experimental results reveal the merits of the proposed controller.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tangled Program Graphs as an alternative to DRL-based control algorithms for UAVs

arXiv

引用

arXiv 2024年

作者： Szolc, Hubert Desnos, Karol Kryjak, Tomasz Embedded Vision Systems Group Department of Automatic Control and Robotics AGH University of Krakow Kraków Poland Univ Rennes INSA Rennes CNRS IETR UMR 6164 RennesF-35000 France

Deep reinforcement learning (DRL) is currently the most popular AI-based approach to autonomous vehicle control. An agent, trained for this purpose in simulation, can interact with the real environment with a human-level performance. Despite very good results in terms of selected metrics, this approach has some significant drawbacks: high computational requirements and low explainability. Because of that, a DRL-based agent cannot be used in some control tasks, especially when safety is the key issue. Therefore we propose to use Tangled Program Graphs (TPGs) as an alternative for deep reinforcement learning in control-related tasks. In this approach, input signals are processed by simple programs that are combined in a graph structure. As a result, TPGs are less computationally demanding and their actions can be explained based on the graph structure. In this paper, we present our studies on the use of TPGs as an alternative for DRL in control-related tasks. In particular, we consider the problem of navigating an unmanned aerial vehicle (UAV) through the unknown environment based solely on the on-board LiDAR sensor. The results of our work show promising prospects for the use of TPGs in control related-tasks. © 2024, CC BY.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Aircraft wing vibration parameters measurement system using MEMS IMUs and closed-loop optimal correction

引用

Aerospace systems 2022年第3期5卷 473-480页

作者： Maamo, M.S. Afonin, A.A. Sulakov, A.S. Department of Control Systems Informatics and Power Engineering Moscow Aviation Institute (National Research University) Volokolamskoe shosse 4 Moscow 125993 Russian Federation Faculty of Robotics and Mechatronics Moscow University for Industry and Finance «Synergy» Street Meshchanskaya 9/14 Moscow 129090 Russian Federation

Nowadays, there is still a need for the development of a high-precision measurement system for aircraft structural elements vibrations, this is due to the fact that many aviation problems are associated with analyzing vibration characteristics of aircraft mechanical structures during its main modes of operation, including flight, particularly the airplane wing health monitoring. This paper presents preliminary results of research carried out toward building a promising system designed to measure vibration parameters of airplane wing. Comparing it with the existing analogues systems, the proposed system features the use of approaches that are traditional for solving orientation and navigation problems for vibration measurements. The article discusses the principles of building such system based on micromechanical inertial measurements units, displacement sensors, on-board aircraft navigation system and sensor data fusion technology. The paper provides a brief overview of the existing solutions in this field of research, and substantiates the relevance and feasibility of the proposed technical solution. The paper presents the basic hardware components of the proposed system, presents the fundamentals of its operation based on the data collected from many sources, including displacement sensors, inertial units and the optimal Kalman estimation and correction algorithm. Besides, the paper presents the mathematical errors models of the system main components. The main algorithms of the system are shown, including algorithms for inertial measurements, estimation and correction in a closed-loop scheme for including optimal Kalman filter, and indirect calculations of vibration parameters. Finally, the initial simulation results of system operation are shown, demonstrating its operability and expected accuracy characteristics, which confirms the system effectiveness and the prospects of the chosen direction of research. © 2022, Shanghai Jiao Tong University.

关键词： Airplane wing Closed-loop optimal correction MEMS IMU Navigation and orientation Optimal Kalman filter Sensor data fusion Vibration measurement

来源：评论

学校读者我要写书评

暂无评论

Machine Learning in Predicting the Impact of Filter Parameters on the Accuracy of Biosignal Measurement

Machine Learning in Predicting the Impact of Filter Paramete...

引用

Digital Signal Processing and its Applications (DSPA), International Conference on

作者： Yeldos A. Altay Raisa K. Uskenbayeva Abu-Alim E. Ayazbay Alexey V. Fedorov Department of Robotics and Technical Means of Automation Satbayev University Almaty Kazakhstan Institute of Automation and Information Technologies Vice-Rector Satbayev University Almaty Kazakhstan Electronic engineering Almaty University of Power Engineering and Telecomunications Almaty Kazakhstan Faculty of Control Systems and Robotics ITMO University Saint-Petersburg Russian Federation

ISBN: (数字)9798331518752

ISBN: (纸本)9798331518769

In this scientific article under consideration, a machine learning model has been developed that allows predicting the impact of filter parameters on the accuracy of measuring a biosignal - an ECG (electrocardiography) signal. For the first time, quantitative results have shown the degree of influence and the error introduced into the measured biosignal and described through dependence. The results of assessing the obtained relationship of indicators demonstrate an inverse correlation relationship that characterizes a decrease in the accuracy of measurement at the output of a high-order digital filtering system. The machine learning model is based on the linear regression method the dependence of which is approximated by the method based on least squares and visualized using a scattergram. The adequacy of the developed machine learning model was confirmed by calculating the coefficient of determination and checking its statistical significance. The developed model can be used to create new or improve existing biomedical data processing systems to increase the reliability of the results.

关键词： Accuracy Shape Filtering Biological system modeling Machine learning Biomedical measurement Electrocardiography Distortion Distortion measurement Digital filters

来源：评论

学校读者我要写书评

暂无评论

Non-Axiomatic Reasoning for an Autonomous Mobile Robot

Non-Axiomatic Reasoning for an Autonomous Mobile Robot

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Patrick Hammer Peter Isaev Lei Feng Robert Johansson Jana Tumova Division of Robotics Perception and Learning KTH Royal Institute of Technology Stockholm Sweden Department of Computer and Information Systems Temple University Philadelphia PA USA Unit of Mechatronics and Embedded Control Systems KTH Royal Institute of Technology Stockholm Sweden Department of Psychology Stockholm University Stockholm Sweden

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

We present the integration of a Non-Axiomatic Reasoning System (NARS) with mobile robots for planning and decision making. NARS enables robots to effectively handle uncertainty in real-time with complete sensor and actuator integration, thereby ensuring adaptability to evolving scenarios. We discuss essential parts of the logic, the architecture and working principles of NARS, and the integration of NARS as a ROS node. A case study is provided demonstrating the system’s proficiency to carry out a garbage collection task in an open-air environment by operating a mobile robot with manipulator arm, and we demonstrate its ability to learn about the place-dependent accumulation of garbage items. Case study also reveals that our approach performs more effectively on the overall task than the Belief-Desire-Intention model we compared with.

关键词： Actuators Uncertainty Object detection Switches Robot sensing systems Manipulators Cognition

来源：评论

学校读者我要写书评

暂无评论

Resilient distributed optimization under mobile malicious attacks

引用

IFAC-PapersOnLine 2023年第2期56卷 997-1002页

作者： Yuan Wang Changxin Liu Hideaki Ishii Karl Henrik Johansson Department of Robotics Hunan University Changsha China Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology and Digital Futures Stockholm Sweden Department of Computer Science Tokyo Institute of Technology Yokohama Japan

This article addresses the distributed optimization problem in the presence of malicious adversaries that can move within the network and induce faulty behaviors in the attacked nodes. We first investigate the vulnerabilities of a consensus-based secure distributed optimization protocol under mobile adversaries. Then, a modified resilient distributed optimization algorithm is proposed. We develop conditions on the network structure for both complete and non-complete directed graph cases, under which the proposed algorithm guarantees that the estimates by regular nodes converge to the convex combination of the minimizers of their local functions. Simulations are carried out to verify the effectiveness of our approach.

关键词： Fault-tolerant distributed optimization multi-agent systems network security mobile adversary agents

来源：评论

学校读者我要写书评

暂无评论

Adaptive State Observers of Linear Time-varying Descriptor systems: A Parameter Estimation-Based Approach

arXiv

引用

arXiv 2024年

作者： Ortega, Romeo Bobtsov, Alexey Castaños, Fernando Nikolaev, Nikolay Department of Electrical and Electronic Engineering ITAM Ciudad de México Mexico The Hangzhou Dianzi University ITMO Joint Institute Xiasha Higher Education Zone Zhejiang Hangzhou China Faculty of Control Systems and Robotics ITMO University Kronverkskiy av. 49 St. Petersburg197101 Russia The Departamento de Control Automático IPN Cinvestav Mexico The Faculty of Control Systems and Robotics ITMO University Kronverkskiy av. 49 St. Petersburg197101 Russia

In this paper, we apply the recently developed generalized parameter estimation-based observer design technique for state-affine systems to the practically important case of linear time-varying descriptor systems with uncertain parameters. We give simulation results of benchmark examples that illustrate the performance of the proposed adaptive observer. © 2024, CC BY-NC-ND.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Joint Algorithm of Message Fragmentation and No-Wait Scheduling for Time-Sensitive Networks

引用

IEEE/CAA Journal of Automatica Sinica 2021年第2期8卷 478-490页

作者： Xi Jin Changqing Xia Nan Guan Peng Zeng Key Laboratory of Networked Control Systems Chinese Academy of SciencesShenyang 110016 Shenyang Institute of Automation Chinese Academy of SciencesShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China Department of Computing Hong Kong Polytechnic UniversityHong KongChina

Time-sensitive networks(TSNs)support not only traditional best-effort communications but also deterministic communications,which send each packet at a deterministic time so that the data transmissions of networked control systems can be precisely scheduled to guarantee hard real-time ***-wait scheduling is suitable for such TSNs and generates the schedules of deterministic communications with the minimal network resources so that all of the remaining resources can be used to improve the throughput of best-effort ***,due to inappropriate message fragmentation,the realtime performance of no-wait scheduling algorithms is ***,in this paper,joint algorithms of message fragmentation and no-wait scheduling are ***,a specification for the joint problem based on optimization modulo theories is proposed so that off-the-shelf solvers can be used to find optimal ***,to improve the scalability of our algorithm,the worst-case delay of messages is analyzed,and then,based on the analysis,a heuristic algorithm is proposed to construct low-delay ***,we conduct extensive test cases to evaluate our proposed *** evaluation results indicate that,compared to existing algorithms,the proposed joint algorithm improves schedulability by up to 50%.

关键词： Message fragmentation networked control system real-time scheduling time sensitive network

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：