检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Kuros, Sylwia Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Kraków Poland

Quantum Neural Networks (QNNs) are an emerging technology that can be used in many applications including computer vision. In this paper, we presented a traffic sign classification system implemented using a hybrid quantum-classical convolutional neural network. Experiments on the German Traffic Sign Recognition Benchmark dataset indicate that currently QNN do not outperform classical DCNN (Deep Convolutuional Neural Networks), yet still provide an accuracy of over 90% and are a definitely promising solution for advanced computer vision. © 2022, CC BY.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

BigFeat: Scalable and Interpretable Automated Feature Engineering Framework

BigFeat: Scalable and Interpretable Automated Feature Engine...

引用

IEEE International Conference on Big Data

作者： Hassan Eldeeb Shota Amashukeli Radwa ElShawi Institute of Computer Science University of Tartu Tartu Estonia Computers and Automatic Control Department Faculty of Engineering Tanta University Tanta Egypt.

ISBN: (纸本)9781665480468

Feature engineering is a crucial step in building well-performing machine learning pipelines. However, manually constructing highly predictive features is time-consuming and requires domain knowledge. Although the research area of automated feature engineering has attracted much interest lately, both in academia and industry, the scalability and efficiency of the existing systems and tools are still practically unsatisfactory. This paper presents a scalable and interpretable automated feature engineering framework, BigFeat, that optimizes input features’ quality to maximize the predictive performance according to a user-defined metric. BigFeat employs a dynamic feature generation and selection mechanism that constructs a set of expressive features that improve the prediction performance while retaining interpretability. Extensive experiments are conducted, and the results show that BigFeat provides superior performance compared to the state-of-the-art automated feature engineering framework, AutoFeat, on a wide range of datasets. We show that BigFeat significantly improves the F1-Score of 8 classifiers by 4.59%, on average. In addition, the performance improvement achieved by integrating BigFeat into different AutoML frameworks is higher than that achieved by integrating AutoFeat into the same frameworks. Besides, the scalability of BigFeat is confirmed by its linear complexity, parallel design, and execution time which is, on average, 22x faster than AutoFeat.

关键词： Measurement Industries Scalability Pipelines Buildings Machine learning Big Data

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Classification Using Deep and Quantum Neural Networks

TechRxiv

引用

TechRxiv 2022年

作者： Kuros, Sylwia Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Kraków Poland

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Do We Run Large-scale Multi-Robot Systems on the Edge? More Evidence for Two-Phase Performance in System Size Scaling

Do We Run Large-scale Multi-Robot Systems on the Edge? More ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jonas Kuckling Robin Luckey Viktor Avrutin Andrew Vardy Andreagiovanni Reina Heiko Hamann Department of Computer and Information Science University of Konstanz Konstanz Germany Centre for the Advanced Study of Collective Behaviour University of Konstanz Germany Institute of Computer Engineering University of Lübeck Lübeck Germany Institute for Systems Theory and Automatic Control University of Stuttgart Stuttgart Germany Department of Computer Science and the Department of Electrical and Computer Engineering Memorial University of Newfoundland St. John’s Canada IRIDIA Université Libre de Bruxelles Brussels Belgium

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

With increasing numbers of mobile robots arriving in real-world applications, more robots coexist in the same space, interact, and possibly collaborate. Methods to provide such systems with system size scalability are known, for example, from swarm robotics. Example strategies are self-organizing behavior, a strict decentralized approach, and limiting the robot-robot communication. Despite applying such strategies, any multi-robot system breaks above a certain critical system size (i.e., number of robots) as too many robots share a resource (e.g., space, communication channel). We provide additional evidence based on simulations, that at these critical system sizes, the system performance separates into two phases: nearly optimal and minimal performance. We speculate that in real-world applications that are configured for optimal system size, the supposedly high-performing system may actually live on borrowed time as it is on a transient to breakdown. We provide two modeling options (based on queueing theory and a population model) that may help to support this reasoning.

关键词： Limiting System performance Space communications Scalability Sociology Swarm robotics Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Attitude Dynamics Modelling: Fractional Consensus Approach

Attitude Dynamics Modelling: Fractional Consensus Approach

引用

IEEE Conference on Decision and control

作者： Jerzy Baranowski Waldemar Bauer Karolina Dukała Dorota Mozyrska Małgorzata Wyrwas Department of Automatic Control and Robotics AGH University of Science & Technology Kraków Poland SWPS University of Social Sciences and Humanities Katowice Poland Faculty of Computer Science Bialystok University of Technology Bialystok Poland

In this paper we propose a consensus model using fractional calculus, which is an emerging topic in multi-agent modeling. Fractional models have infinite memory and can be understood as a relatively simple extension of traditional calculus. We propose a model structure motivating it by psychological research. For such model we also provide a stability analysis allowing results on possibilities of consensus arising in the modelled group of agents. To achieve this, we use fractional difference equations, which illustrate our considerations for agent groups of increasing complexity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Algorithm for Path Planning of Mobile Robot 24

Algorithm for Path Planning of Mobile Robot

引用

24th International Conference on Soft Computing and Measurements, SCM 2021

作者： Das, Nimai Chandra Uddin, Raihan Haque Zim, Md. Ziaul Skakun, Anastasiia D. Department of Automatic Control Systems Saint-Petersburg Electrotechnical University Leti Saint Petersburg Russia Daffodil International University Department of Software Engineering Dhaka Bangladesh Daffodil International University Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9781665439749

Research in Unmanned Surface Vehicles (USVs) and Autonomous Mobile Robots navigation has demonstrated some success in navigating flat indoor environments while avoiding obstacles. But in common resilience to unsafe conditions, unmanned surface vehicles (USVs) and autonomous mobile robots have wide applications in security reconnaissance, investigation of an obscure domain, and crisis reaction. Various examinations have been directed on the driving mechanism, motion planning, and trajectory tracking strategies for robots, yet restricted investigations have been led with respect to the obstacle detection and avoiding ability of robots. However, for little scale robots that contain sensitive surveillance sensors and can't afford to utilize heavy defensive shells, the nonappearance of obstacle avoidance solutions arrangements would leave the robot helpless before possibly risky hindrances. In this paper, we present an algorithm for obstacle detection and avoidance system has been developed for miniature Unmanned Surface Vehicles (USVs) and autonomous mobile robots. We show an investigation differentiating heading build rules and relative course directions dodging distinctive operators in multi-specialist conditions, estimating separation between the two robots. The integration of distance measurement and avoiding other robots or obstacles is our observation in a multi-robot environment, where obstacles are also available. In this paper, we have discussed two algorithms, one will try to avoid other robot or obstacles and another will try to measure the distance between main agents to another agent. It utilizes an algorithm so that the system is both compact and power efficient. The proposed system can detect not only the presence, but also the approaching direction of a ferromagnetic obstacle. Therefore, an intelligent avoidance behavior can be generated by adapting the trajectory tracking method with the detection information. Design optimization is conducted to enhance

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Path Planning Algorithm for Multiple UAVs Based on Artificial Potential Field

Path Planning Algorithm for Multiple UAVs Based on Artificia...

引用

IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC)

作者： Chongde Ren Jinchao Chen Chenglie Du Wenquan Yu School of Software Northwestern Polytechnical University Xi'an China Department of Computer Science Northwestern Polytechnical University Xi'an China Department of Land Unmanned System Research and Development North Automatic Control Technology Research Institute Taiyuan China

Due to the lower cost and higher maneuverability, unmanned aerial vehicles (UAVs) have found extensive use in both the civilian and military worlds. Path planning, as a crucial problem in the process of UAVs flight, aims to determine the optimal routes for multiple UAVs from various starting points to a single destination. However, because of the involvement of complex conditional constraints, path planning becomes a highly challenging problem. The path planning problem involving numerous UAVs is examined in this research, and a SAAPF-MADDPG algorithm based on Artificial Potential Field (APF) is suggested as a solution. First, a SA-greedy algorithm that can change the probability of random exploration by agents based on the number of steps and successful rounds to prevent UAVs from getting trapped in a local optimum. Then, we design complex reward functions based on APF to guide UAVs to destination faster. Finally, SAAPF-MADDPG is evaluated against the MADDPG, DDPG, and MATD3 methods in simulation scenarios to confirm its efficacy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Realization of Unmanned Vehicle Autonomous Navigation System Based on Binocular Camera

Design and Realization of Unmanned Vehicle Autonomous Naviga...

引用

computer Science, Electronic Information Engineering and Intelligent control Technology (CEI), IEEE International Conference on

作者： Tianxing Guo Lianlei Lin Huanyu Liu Junbao Li Department of Automatic Test and Control School of Electronics and Information Engineering Harbin Institute of Technology Harbin China Information Countermeasure Technique Institute School of Computer Science and Technology Harbin Institute of Technology Harbin China

ISBN: (数字)9798350372052

ISBN: (纸本)9798350372069

Aiming at the navigation problem of unmanned vehicles in extreme environments such as communication interference and limited GPS signals, this study proposes an autonomous navigation method based on binocular cameras. The method enables the unmanned vehicle to complete the task of localization and map building using only binocular images, without the need for other sensors or signal sources. Meanwhile, this study also proposes a local path planning obstacle avoidance method based on depth map, which, when combined with global localization information, can take into account both local obstacle avoidance and global path navigation, and can cope with random environmental changes. The system uses a single sensor for autonomous obstacle avoidance and navigation, which reduces the computational requirements and ensures the low cost of the navigation system. In order to verify the reliability and effectiveness of the system under signal-constrained conditions, the system is evaluated in a simulation environment and a real field scenario, respectively. The experimental results show that the system is able to achieve reliable localization and path planning under signal-constrained conditions.

关键词： Location awareness Navigation Reliability theory Path planning Sensor systems Sensors Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

MIMIR-UW: A Multipurpose Synthetic Dataset for Underwater Navigation and Inspection

MIMIR-UW: A Multipurpose Synthetic Dataset for Underwater Na...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Olaya Álvarez-Tuñón Hemanth Kanner Luiza Ribeiro Marnet Huy Xuan Pham Jonas le Fevre Sejersen Yury Brodskiy Erdal Kayacan Department of Electrical and Computer Engineering Artificial Intelligence in Robotics Laboratory (AiRLab) Aarhus University Aarhus C Denmark EIVA a/s Skanderborg Denmark Automatic Control Group (RAT) Paderborn University Paderborn Germany

This paper presents MIMIR-UW, a multipurpose underwater synthetic dataset for SLAM, depth estimation, and object segmentation to bridge the gap between theory and application in underwater environments. MIMIR-UW integrates three camera sensors, inertial measurements, and ground truth for robot pose, image depth, and object segmentation. The underwater robot is deployed within a pipe exploration scenario, carrying artificial lights that create uneven lighting, in addition to natural artefacts such as reflections from natural light and backscattering effects. Four environments totalling eleven tracks are provided, with various difficulties regarding light conditions or dynamic elements. Two metrics for dataset evaluation are proposed, allowing MIMIR-UW to be compared with other datasets. State-of-art methods on SLAM, segmentation and depth estimation are deployed and benchmarked on MIMIR-UW. Moreover, the dataset's potential for sim-to-real transfer is demonstrated by leveraging the segmentation and depth estimation models trained on MIMIR-UW in a real pipeline inspection scenario. To the best of the authors' knowledge, this is the first underwater dataset targeted for such a variety of methods. The dataset is publicly available online. https://***/remaro-network/MIMIR-UW/

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Stabilization of a Class of OSL Conformable Fractional Order Nonlinear Systems

On the Stabilization of a Class of OSL Conformable Fractiona...

引用

International Conference on Systems and control (ICSC)

作者： Ali Omar M. Alsharif A. Jmal O. Naifar Ausama H. Ahmed Hamdi Gassara A. Ben Makhlouf Electrical Engineering Department Control and energy management laboratory (CEM lab) Sfax University Engineering National School Sfax Tunisia Department of Electrical & Computer Engineering Faculty of Engineering Elmergib University Alkhums Libya Laboratory of Sciences and Techniques of Automatic Control and Computer Engineering National School of Engineering of Sfax University of Sfax Tunisia Department of Mathematics Faculty of Sciences of Sfax Sfax Tunisia

One-Sided Lipschitz (OSL) fractional order modeling is a top choice for solving the stabilization issue of nonlinear systems. Despite numerous studies on the subject, there remains a gap in understanding when it comes to fractional calculus. By providing a stabilizing strategy for a certain type of OSL fractional order nonlinear systems, this study fills the gap. A numerical example demonstrating the correctness of the suggested approach and demonstrating its efficacy for the tested class.

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：