检索结果-内蒙古大学图书馆

Enhancing Deep Reinforcement Learning with Scenario-Based Modeling

SN Computer Science 2023年第2期4卷 1-13页

作者： Yerushalmi, Raz Amir, Guy Elyasaf, Achiya Harel, David Katz, Guy Marron, Assaf Department of Computer Science and Applied Mathematics Weizmann Institute of Science Rehovot 76100 Israel School of Computer Science and Engineering The Hebrew University of Jerusalem Jerusalem 91904 Israel Software and Information Systems Engineering Ben-Gurion University of the Negev Beer-Sheva 8410501 Israel

Deep reinforcement learning agents have achieved unprecedented results when learning to generalize from unstructured data. However, the “black-box” nature of the trained DRL agents makes it difficult to ensure that they adhere to various requirements posed by engineers. In this work, we put forth a novel technique for enhancing the reinforcement learning training loop, and specifically—its reward function, in a way that allows engineers to directly inject their expert knowledge into the training process. This allows us to make the trained agent adhere to multiple constraints of interest. Moreover, using scenario-based modeling techniques, our method allows users to formulate the defined constraints using advanced, well-established, behavioral modeling methods. This combination of such modeling methods together with ML learning tools produces agents that are both high performing and more likely to adhere to prescribed constraints. Furthermore, the resulting agents are more transparent and hence more maintainable. We demonstrate our technique by evaluating it on a case study from the domain of internet congestion control, and present promising results. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Deep reinforcement learning Domain expertise Machine learning Rule-based specifications Scenario-based modeling

来源：评论

学校读者我要写书评

暂无评论

GoLive A modular Mixed Reality Simulation for Semantic Plug and Play

GoLive A modular Mixed Reality Simulation for Semantic Plug ...

引用

International Conference on Control, Automation and systems ( ICCAS)

作者： Constantin Wanninger Thomas Badem Martin Schörner Christian Eymueller Alexander Poeppel Wolfgang Reif Institute for Software and Systems Engineering University of Augsburg Augsburg Germany

In the field of mobile robotics, the interaction of robots with their environment plays a key role. Simulations serve to simulate a part of the environment so that the partly complex hardware is not damaged in extensive field tests. However, the transition from simulation to reality can be difficult. This paper presents a modular simulation and visualization with mixed reality mechanisms that can be reconfigured at runtime using a new concept called MR devices. A MR device is a physical device that registers with the simulation through self-description mechanisms and can interact with real objects. MR devices themselves can be used as tangible user interfaces in mixed reality visualization, e.g. to influence the composition of the environment. This concept enables the stepwise transition from simulation to reality. The advantages of these intermediate steps are presented by means of three scenarios, on which drones, sensors, infrastructure and also gas emitters are used. GoLive builds on the self-description mechanisms resulting from the own preliminary work: Semantic Plug and Play, in which capabilities and properties can be described by Semantic Web mechanisms and linked to the execution logic of the hardware at runtime.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MEMS-Based Fingerprinting Architecture for Trustworthy Electronics

MEMS-Based Fingerprinting Architecture for Trustworthy Elect...

引用

2023 Smart systems Integration Conference and Exhibition, SSI 2023

作者： Meinel, Katja Schott, Christian Mayer, Franziska Gupta, Dhruv Mittag, Sebastian Hahn, Susann Weidlich, Sebastian Bulz, Daniel Forke, Roman Hiller, Karla Heinkel, Ulrich Kuhn, Harald Center for Microtechnologies Chemnitz University of Technology Chemnitz Germany Chemnitz University of Technology Faculty of Electrical Engineering and Information Technology Chemnitz Germany Multi Device Integration Fraunhofer Institute for Electronic Nano Systems Enas Chemnitz Germany Center for Microtechnologies Chemnitz University of Technology Fraunhofer Institute for Electronic Nano Systems Enas Chemnitz Germany

ISBN: (纸本)9798350325065

A fingerprint architecture based on a micro electro mechanical system (MEMS) for the use as a hardware security component is presented. The MEMS serves as a physically unclonable function (PUF) and is used for fingerprint ID generation, derived from the MEMS-specific parameters. The fingerprint is intended to allow the unique identifiability of electronic components and thus to ensure protection against unauthorized replacement or manipulation. The MEMS chip consists of 16 individual varactors with continuously adjustable capacitance values that are used for bit derivation ('analog' PUF). The focus is on the design-related forcing of random technological spread to provide a wide range of different parameters per chip or wafer to achieve a maximum key length. Key generation and verification is carried out via fingerprint electronics connected to the MEMS, which is realized by an FPGA. © 2023 IEEE.

关键词： Varactors

来源：评论

学校读者我要写书评

暂无评论

SensorClouds: A Framework for Real-Time Processing of Multi-modal Sensor Data for Human-Robot-Collaboration

SensorClouds: A Framework for Real-Time Processing of Multi-...

引用

International Conference on Autonomous Robots and Agents, ICARA

作者： Alexander Poeppel Christian Eymüller Wolfgang Reif Institute for Software and Systems Engineering University of Augsburg Augsburg Germany

Human-robot-collaboration (HRC) requires fast and reliable sensor data to ensure the safety of humans in the workspace. Current solutions for processing multi-modal sensor data in HRC are either highly performant in specific scenarios or offer more flexibility at the cost of decreased performance. Our GPU accelerated SensorClouds framework, however, combines both high flexibility and real-time performance. The architecture aids developers in quickly implementing complex HRC applications with multiple sensors by encapsulating all functionality into reusable modules. The resulting pipeline is optimized by the framework and executed in real-time.

关键词： Solid modeling Multimodal sensors Pipelines Graphics processing units Computer architecture Robot sensing systems Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Identifying Challenges for OSS Vulnerability Scanners - A Study & Test Suite (Short Summary)

Identifying Challenges for OSS Vulnerability Scanners - A St...

引用

Fachtagung des GI-Fachbereichs softwaretechnik, software engineering 2022 - Conference of the GI software engineering Section, software engineering 2022

作者： Dann, Andreas Plate, Henrik Hermann, Ben Ponta, Serena Elisa Bodden, Eric The Secure Software Engineering Group Heinz Nixdorf Institute Paderborn University Germany SAP Security Research Mougins France Technical University of Dortmund Germany Paderborn University Germany Software Engineering IT-Security at Fraunhofer IEM Paderborn Germany

ISBN: (纸本)9783885797142

This short paper5 presents a study investigating the impact of typical development practices, like re-compilation, re-bundling, on the performance of vulnerability scanners to detect known vulnerabilities in used open-source dependencies. In particular, the paper studies (i) types of modifications that affect the detection of vulnerable open-source dependencies and (ii) their impact on the performance of vulnerability scanners through an empirical study on 7024 Java projects developed at SAP. © 2022 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Combining Simulation and Recurrent Neural Networks for Model-Based Condition Monitoring of Machines

Combining Simulation and Recurrent Neural Networks for Model...

引用

Simulation Winter Conference

作者： Alexander Wuttke Markus Rabe Joachim Hunker Jan-Philipp Diepenbrock Dept. IT in Production and Logistics TU Dortmund University Dortmund GERMANY Fraunhofer Institute for Software and Systems Engineering Dortmund GERMANY IVA Schmetz GmbH Menden GERMANY

ISBN: (数字)9798331534202

ISBN: (纸本)9798331534219

Maintenance is pivotal in industry, with condition-based maintenance emerging as a key strategy. This involves monitoring the machine condition through sensor data analysis. Model-based approaches compare observed data with expected values from models, which requires high-quality models. An established method is to use simulation models, which in many cases produce good results but may lack precision due to uncertainties. Alternatively, models created by machine learning can detect patterns directly from data. This paper proposes combining simulation models with machine learning models, leveraging the simulation's a-priori knowledge and machine learning's data patterns to enhance models for condition monitoring. Recurrent neural networks are suggested as the machine learning method. The paper outlines a systematic approach and demonstrates its application in an industrial use case, which investigates vacuum processes in industrial furnaces.

关键词： Condition monitoring Industries Recurrent neural networks Vacuum systems Uncertainty Systematics Machine learning Data models Maintenance Monitoring

来源：评论

学校读者我要写书评

暂无评论

Architecture for Emergency Control of Autonomous UAV Ensembles∗∗This work is partly funded by the German Research Foundation (DFG) under the COMBO grant 3

Architecture for Emergency Control of Autonomous UAV Ensembl...

引用

3rd IEEE/ACM International Workshop on Robotics software engineering, RoSE 2021

作者： Schorner, Martin Wanninger, Constantin Hoffmann, Alwin Kosak, Oliver Reif, Wolfgang Institute for Software and Systems Engineering University of Augsburg Germany

ISBN: (纸本)9781665444743

Applying unmanned aerial vehicles (UAV) has benefits for many different use-cases. Existing implementations of ground control stations (GCS) to manage UAVs in such scenarios already provide some support for the operation of multi-unit systems, i.e., ensembles. However, since they are usually designed for the operation of only one copter at once, this is often not sufficient to react quickly in dangerous situations, e.g., search and rescue scenarios. To address this problem, we propose an approach for easy observation and control of complete autonomous UAV ensembles: The Intention of our approach is to greatly reduce the number of personnel required for the operation of an UAV ensemble. Thereby, we generate the possibility for rapid intervention in potentially dangerous situations in order to prevent damage to the UAVs and the environment. In this paper, we present a software architecture for this safety-critical multi UAV ground control station including a fully implemented prototype which we also tested in a realistic environment. © 2021 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Applications for Resilience in Manufacturing — A Systematic Literature Review

Artificial Intelligence Applications for Resilience in Manuf...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Florian A. Maier Sivaphani Puppala Michael Oberle Software Defined Energy-Cell Manufacturing Fraunhofer Institute for Manufacturing Engineering and Automation IPA Stuttgart Germany Center for Digitalized Battery Cell Manufacturing Fraunhofer Institute for Manufacturing Engineering and Automation IPA Stuttgart Germany Centre for Digital Tools in Manufacturing Fraunhofer Institute for Manufacturing Engineering and Automation IPA Stuttgart Germany

This review provides a structured literature analysis of Artificial Intelligence (AI) applications in enhancing manufacturing resilience. The research is guided by three primary questions addressing the use cases, technologies, and benefits of AI across the five resilience phases: Prepare, Prevent, Protect, Respond, and Recover. Findings from 78 papers reveal that AI significantly contributes to predictive maintenance, risk mitigation, and quality control, with machine learning and deep learning being the predominant technologies. The study highlights the pivotal role of AI in advancing manufacturing towards proactive, resilient, and adaptable operations. The insights gleaned offer a roadmap for future research and practical AI integration in manufacturing, underscoring the value of AI in driving industrial innovation and efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sea Level Anomalies Prediction Via Two-Stage Spatiotemporal Transformer 21

Sea Level Anomalies Prediction Via Two-Stage Spatiotemporal ...

引用

21st International Conference on Networking, Sensing and Control, ICNSC 2024

作者： Fang, Shaoteng Zhao, Yuehao Wang, Kefan Tian, Chenyu Kang, Qi Tongji University Department of Control Science and Engineering Shanghai China The School of Aerospace Mechanical and Mechatronic Engineering The University of Sydney Sydney Australia Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China School of Software Technology Dalian University of Technology Dalian China

ISBN: (纸本)9798350365221

This study successfully applies the spatiotemporal transformer-based model to sea surface height anomaly prediction task. An improved ResNet autoencoder, named SW-GD Autoencoder, is proposed based on Sliced-Wasserstein distance and Gradient Difference loss functions to extract spatial feature information. This autoencoder demonstrates a reduced complexity and training difficulty compared to GAN-based architectures while maintaining high data generation quality. Additionally, the VidHRFormer model is employed for inference, introducing a large receptive field spatial feed-forward network module that enhances information transmission between adjacent patches in the feature map, thereby improving the observability of prediction results. To simplify training, we used a two-stage approach: first training the autoencoder separately, then combining it with VidHRFormer for final training. Compared to state-of-the-art ConvLSTM models, our method yields superior results. © 2024 IEEE.

关键词： Sea level

来源：评论

学校读者我要写书评

暂无评论

Surface modification of tungsten carbide cobalt tool electrodes by heat treatment under nitrogen atmosphere for electro-discharge drilling 23

Surface modification of tungsten carbide cobalt tool electro...

引用

23rd International Conference of the European Society for Precision engineering and Nanotechnology, EUSPEN 2023

作者： Uhlmann, E. Camin, B. Polte, J. Polte, M. Streckenbach, J. Dinh, N.C. Fraunhofer Institute for Production Systems and Design Technology IPK Germany Institute for Machine Tools and Factory Management IWF Technische Universität Berlin Germany Faculty I Materials Engineering Hochschule Bremerhaven Germany

ISBN: (纸本)9781998999132

The requirements for high-precision components for tool and mould-making, automotive and aerospace industries are constantly increasing. Due to the strong mechanical properties of the used materials, such as tool steels and nickel-based alloys, conventional cutting processes are not always suitable. Instead, electrical discharge machining is used for cutting electrically conductive materials. One challenge even today is debris formation, causing arcs and short-circuits in the lateral working gap. This applies particularly to electro-discharge drilling with high aspect ratios and increased difficulties of debris removal. This leads to increased process instability, tool wear and conicity as well as decreased material removal rates. To reduce the effects of arcing and short-circuits in the lateral working gap, tungsten carbide-cobalt tool electrodes with an outer diameter of dO = 1.5 mm were heat-treated to increase the electrical resistivity of the electrode's surface. For this purpose, two different ambient atmospheres were selected, a nitrogen atmosphere and vacuum in comparison. Subsequently, the modified tool electrodes were used to produce boreholes in tool steel of the type Elmax Superclean with a depth of et = 6.75 mm by electrodischarge drilling. The surface modification in the nitrogen atmosphere led to a slightly higher material removal rate and a decrease in the linear tool wear of the tool electrode by up to 6.67 % compared to an untreated reference electrode. © 2023 Euspen Headquarters.

关键词： Heat treatment

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：