检索结果-内蒙古大学图书馆

International Conference on control Systems and Computer Science (CSCS)

作者： Radu-Florin Negoiţă Theodor Borangiu Doctoral School of Automatic Control and Computers University Politehnica of Bucharest Bucharest Romania Dept. of Automatic Control and Industrial Informatics University Politehnica of Bucharest Bucharest Romania

Coordinating service capacity with dynamic varying, market-driven customer demand in a service business imposes correlating and synchronizing front-office and back-office processes - the first addressing customer relationship management and the second inventory planning, forecasting demand, analytics, and strategic decision making. Front office management (FOM) contributes substantially in coordinating the services requested by guests, and needs to be integrated in an Operations Management Software system specific for hotel business. Research efforts are currently directed towards automating repetitive, time consuming operations included in front office processes that are in great number, initiated by random events and customer actions with variable timing. The paper presents a solution to automate FOM operations that are kept consistent with the business strategy of the organization, and assist front-office workflows involving customers (service requests, service quality assessment) and front line personnel (registration, check in, check out, taxation and invoicing). The solution is based on the Robotic Process Automation (RPA) technology extended with AI-based functionalities for the intelligent process automation and integration with back-office workflows.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Trajectory Extraction from Online Mapping Platforms: Empowering Vehicle Dynamics and Intelligent Functionalities 27

Trajectory Extraction from Online Mapping Platforms: Empower...

引用

27th International Conference on System Theory, control and Computing, ICSTCC 2023

作者： Pauca, Georgiana-Sinziana Caruntu, Constantin-Florin Department of Automatic Control and Applied Informatics Gheorghe Asachi Technical University of Iasi Iasi Romania Safety and Motion Continental Automotive Romania Iasi Romania Software and Central Technologies Continental Automotive Romania Iasi Romania

ISBN: (纸本)9798350337983

The development, enhancement, and integration of intelligent functionalities aimed at automating vehicles are increasingly becoming a fundamental aspect of modern life. There is a growing emphasis on improving the everyday driving experience and reaping the benefits that these advanced cars offer. In light of these advancements, this study proposes a novel method for extracting trajectories, which serves as a valuable tool in implementing and evaluating complex algorithms and functionalities. Obtaining a real trajectory enables the observation of how a vehicle moves along a given road. Moreover, the extracted trajectory can also facilitate the development of additional functionalities such as lane keeping, velocity profile, and other advanced techniques. This multifaceted approach allows for the exploration and refinement of various intelligent systems, ultimately contributing to the overall improvement of autonomous driving capabilities. The proposed method of trajectory extraction opens up new possibilities for advancing the field, providing a solid foundation for implementing and evaluating intricate algorithms. Through the utilization of real trajectories, valuable insights into vehicle behavior can be gained, which can further enhance the performance of autonomous vehicles. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Polynomial and Parallelizable Preconditioning for Block Tridiagonal Positive Definite Matrix

arXiv

引用

arXiv 2025年

作者： Yang, Shaohui Ohtsuka, Toshiyuki Plancher, Brian Jones, Colin N. Automatic Control Laboratory EPFL Switzerland Department of Informatics Graduate School of Informatics Kyoto University Kyoto Japan Barnard College Columbia University New York United States

The efficient solution of moderately large-scale linear systems arising from the KKT conditions in optimal control problems (OCPs) is a critical challenge in robotics. With the stagnation of Moore’s law, there is growing interest in leveraging GPU-accelerated iterative methods, and corresponding parallel preconditioners, to overcome these computational challenges. To improve the computational performance of such solvers, we introduce a parallel-friendly, parametrized multi-splitting polynomial preconditioner framework that leverages positive and negative factors. Our approach results in improved convergence of the linear systems solves needed in OCPs. We construct and prove the optimal parametrization of multi-splitting theoretically and demonstrate empirically a 76% reduction in condition number and 46% in iteration counts on a series of numerical benchmarks. Copyright © 2025, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Towards independent SMA actuators: A novel analog two-state control system for flexible robots

Towards independent SMA actuators: A novel analog two-state ...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Florian-Alexandru Brasoveanu Adrian Burlacu Department of Automatic Control and Applied Informatics "Gheorghe Asachi" Technical University of Iasi Iasi Romania

The soft robotics field offers a large variety of actuators and robots, complex structures and designs able to behave in a required way, offering speed and resistance and at the same time reducing the contact damage chance. The control of such structures using mathematical methods requires complex methods which evolved over time in the form of predictive control and even neural networks and genetic algorithms. The current paper presents ongoing research that can be found at the intersection of meta-materials and sensor technology. It approaches a simpler method of controlling a flexible actuator based on a shape memory alloy, the regulator being a two-state switch controller steered by a pressure force sensor. We propose a complete analogical electrical structure and analyze the performance of the outcome, focusing on time response. The present work also contains a brief description of a mechanical design proposal able to optimize the impact of the shape memory alloy used, in order to obtain an amplified actuation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Channel Congestion for V2V Safety Communication in Multiplatooning Applications

Evaluation of Channel Congestion for V2V Safety Communicatio...

引用

International Symposium on Electronics in Marine (ELMAR)

作者： Razvan-Gabriel Lazar Constantin-Florin Caruntu Department of Automatic Control and Applied Informatics Gheorghe Asachi Technical University of Iasi Iasi Romania

The applications related to cooperative automated driving need to share periodic safety information with neighboring vehicles in a reliable and low-latency manner. However, the performance of vehicular ad-hoc technologies degrades substantially when the channel becomes congested. Therefore, this paper presents a channel congestion evaluation method for V2V safety communication for the IEEE 802.11p protocol. The evaluation addresses multiplatooning applications, in which the vehicles' density is a defining element. To illustrate the negative effects of the channel load level, a number of relevant performance metrics were analyzed, such as Channel Busy Ratio (CBR), Packet Loss Rate (PLR), and Inter-Packet Delay (IPD).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Challenges and Solutions in Designing a Network Architecture for Red and Blue Cybersecurity Competitions

Challenges and Solutions in Designing a Network Architecture...

引用

International Conference on System Theory, control, and Computing (ICSTCC)

作者： Cristian Chindrus Constantin F. Caruntu Department of Automatic Control and Applied Informatics Gheorghe Asachi Technical University of Iasi Iasi Romania

With the increasing importance of cybersecurity in our digital age, cybersecurity competitions have become a popular way to test the incident response abilities of participants. This paper proposes a network architecture to test the vulnerabilities that may appear in a Red and Blue cybersecurity competition. The network architecture is designed to simulate a real-world cyber-attack scenario and includes a router, a core system, and multiple subnets representing different teams. Each subnet contains vulnerable systems that must be protected by the teams, who must also launch attacks on the other teams to identify flags. The architecture presents several challenges, including the large number of rules required for router configuration, which prohibit direct access to opposing teams’ virtual machines (VMs) and restrict/block access to specific phases of the competition. The VMs used in the competition include various vulnerabilities related to cryptocurrency wallet operation, medical clinics, chat services, X-ray clinics, SCADA communication protocols, and industrial power plants. Overall, the network architecture and VMs used in this competition provide a challenging and realistic scenario for participants to test their skills in identifying and mitigating cybersecurity threats.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reproducibility in Deep Reinforcement Learning with Maximum Entropy

Reproducibility in Deep Reinforcement Learning with Maximum ...

引用

International Conference on System Theory, control, and Computing (ICSTCC)

作者： Tudor-Andrei Paleu Carlos Pascal Department of Automatic Control and Applied Informatics “Gheorghe Asachi” Technical University of Iasi Iasi Romania

The latest work in the field of deep reinforcement learning speaks highly about the advanced exploration techniques which avoid the greedy decisions of agents. Usually, reinforcement learning works by finding the optimal policy for a Markov Decision Process. In off-policy algorithms the agent learns a value function for this optimal policy, separate of the action choice, an example being the deep Q-learning algorithm. Algorithms based on a maximum entropy framework, like soft Q-learning, overcome the greedy behavior of the agent, effectively combining exploration and exploitation by adding an entropy term to the Bellman equation. This method, applied to the Lunar Lander environment, was compared to the classic deep Q-learning, using the same set of different random seeds and averaging multiple runs. An implicit exploration strategy proves to compensate for disturbances caused by intrinsic sources of non-determinism, such as random seeds. This paper highlights the sensitivity to intrinsic and extrinsic influences for deep reinforcement learning, with respect to exploration and repeatability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time Pricing Mechanism for V2G Using Distributed Bilevel Optimization 63

Real-time Pricing Mechanism for V2G Using Distributed Bileve...

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： You, Jiawei Dai, Xinliang Jiang, Yuning Yin, Haoyu Shi, Yuanming Jones, Colin N. ShanghaiTech University School of Information Science and Technology China Epfl Switzerland Karlsruhe Institute of Technology Institute for Automation and Applied Informatics Germany Epfl Automatic Control Laboratory Switzerland Washington University in St. Louis Department of Electrical and Systems Engineering United States

ISBN: (纸本)9798350316339

This paper explores the impact of the burgeoning electric vehicle (EV) presence on distribution grid operations, highlighting the challenges they present to conventional pricing strategies due to their dual role as power consumers and suppliers, coupled with their energy storage capabilities. We propose an advanced real-time pricing model for the electricity market, employing a novel distributed bilevel optimization framework. This framework distinguishes between the distribution system operator (DSO) at the upper level and the EVs at the lower level, each aiming to optimize profit margins. The optimization includes power flow constraints at the upper level to ensure efficient operation within safe system limits, while model predictive control (MPC) is used to optimize lower-level EV responses. Additionally, we provide a rigorous convergence analysis of the proposed bilevel optimization method. Detailed convergence studies and simulation results demonstrate the effectiveness and superiority of the proposed algorithm. © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

FedAcc and FedAccSize: Aggregation Methods for Federated Learning Applications

FedAcc and FedAccSize: Aggregation Methods for Federated Lea...

引用

Mediterranean Conference on control and Automation (MED)

作者： Iuliana Bejenar Lavinia Ferariu Carlos Pascal Constantin F. Caruntu Department of Automatic Control and Applied Informatics “Gheorghe Asachi” Technical University of Iasi Iasi Romania

This paper presents the ability of the federated learning concept to create a collaboration between multiple devices using a shared global model, while still keeping data privacy to meet the General Data Protection Regulation (GDPR). In real-world application scenarios, this concept faces problems related to the defense of the global model from possible attacks and the compatibility with non-independent and identically distributed data (non-IID). This paper presents two aggregation algorithms compatible with non-IID data, which use a refined aggregation of the local model, based on their accuracy. Thus, the proposed algorithms can refine the confidence in each client, eliminate intruders and allow a safe aggregation of the global model. Testing scenarios performed for IID and non-IID data illustrate that the proposed algorithms are able to provide faster training and improved robustness against intruders, w.r.t. the well-known federated average algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time testing of vision-based systems for AGVs with ArUco markers

Real-time testing of vision-based systems for AGVs with ArUc...

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Filus, Katarzyna Sobczak, Lukasz Domanska, Joanna Domanski, Adam Cupek, Rafal Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Gliwice Poland

ISBN: (纸本)9781665480451

Automated Ground Vehicles (AGVs) use deep-learning-based vision systems to perceive the surrounding environment and extract relevant information about it. Although deep learning models offer high capabilities, they require large amounts of data to be properly trained and tested. Testing is especially important when off-the-shelf models are used by the AGVs - to examine whether they can meet the demands of complex environments such as the production halls of automated factories. One area of such perception algorithms is object recognition. To test such systems, we propose a solution based on ArUco fiducial markers used for automatic labeling of objects. Our solution can be used to test deep learning systems in real time directly on a robot. Our solution requires minimal interference with the environment and additional infrastructure - the desired objects only need to be marked with a marker printed on a home printer. Therefore, the presented testing procedure can be used for testing of AGVs in real-life environments during a real ride from an actual robot perspective. Data gathered during the online testing can be used for the offline comparison of the accuracy of different deep learning models. Although we focus on the online and offline testing in our study, we also incorporated a marker masking procedure. Therefore, the resulting datasets may also be used for training. © 2022 IEEE.

关键词： Object recognition

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：