检索结果-内蒙古大学图书馆

ieee symposium on Position Location and Navigation (PLANS)

作者： Jormpon Chaisakulsurin Shariff Manuthasna Tanawish Masri Thanayuth Panyalert Kritsada Palee Pakawat Prasit Patcharin Kamsing Peerapong Torteeka Thai Space Consortium Project National Astronomical Research Institute of Thailand (Public Organization) Chiang-Mai Thailand Center of Observatory Operation and Engineering National Astronomical Research Institute of Thailand (Public Organization) Chiang-Mai Thailand Faculty of Engineering Program in Robotics and Computational Intelligence Systems International Academy of Aviation Industry King Mongkut's Institute of Technology Ladkrabang Bangkok Thailand Department of Aeronautical Engineering Air-Space Control Optimization and Management Laboratory International Academy of Aviation Industry King Mongkut's Institute of Technology Ladkrabang Bangkok Thailand

This paper proposes a Hardware-in-the-Loop sim-ulation (HiLs) tested via square Helmholtz coils as a relative magnetic field generator. In technical terms, the HiLs is an indispensable tool for engineering design during rapid proto-typing of attitude determination and control algorithms for the turning parameters that control the attitude of the satellite, since most of the satellite's mission relies on its attitude, making this system one of the most essential to the satellite's operation. More-over, performing controlled experiments with the parameters for developing adaptive control algorithms improves the overall efficiency of the satellite's kinematic system. The conceptual design of a proposed system architecture can be composed of the electrical currents of 2.4-meter square Helmholtz coils produced by a low-level microcontroller equipped with a DC-motor driver by a pulse-width modulation (PWM) signal through real-time connection to an orbit propagator using a high-level computer. This research focuses on the attitude dynamic of satellites through the interaction between the Earth's magnetic field (EMF) and the magnetotorque in the satellite. To apply this phenomenon, the intensity and the direction of the magnetic field must be identified through Biot-Savart's law. Along with the EMF, the reference position is calculated using the standard general perturbations satellite orbit model (SGP4), and the intensity is modeled based on coefficients from the 13 th edition of the International Geo-magnetic Reference Field (IGRF). Therefore, this paper presents a detailed development of a HiLs testbed for distributed attitude determination and control systems (hardware and software co-design, protocol, and control theory). Furthermore, it discusses a classic cooperative control case for the output of magnetic field intensity and direction, which was undertaken to explain the integrated simulation process and validate the effectiveness of the co-simulation tested to be

关键词：

来源：评论

学校读者我要写书评

暂无评论

A memory of motion for visual predictive control tasks

A memory of motion for visual predictive control tasks

引用

ieee International Conference on Robotics and automation (ICRA)

作者： Paolillo, Antonio Lembono, Teguh Santoso Calinon, Sylvain Idiap Res Inst Martigny Switzerland USI SUPSI Dalle Molle Inst Artificial Intelligence IDSIA Lugano Switzerland

ISBN: (纸本)9781728173955

This paper addresses the problem of efficiently achieving visual predictive control tasks. To this end, a memory of motion, containing a set of trajectories built off-line, is used for leveraging precomputation and dealing with difficult visual tasks. Standard regression techniques, such as k-nearest neighbors and Gaussian process regression, are used to query the memory and provide on-line a warm-start and a way point to the control optimization process. The proposed technique allows the control scheme to achieve high performance and, at the same time, keep the computational time limited. Simulation and experimental results, carried out with a 7-axis manipulator, show the effectiveness of the approach.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

A Virtual-Real Interaction Approach to Object Instance Segmentation in Traffic Scenes

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2021年第2期22卷 863-875页

作者： Zhang, Hui Luo, Guiyang Tian, Yonglin Wang, Kunfeng He, Haibo Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Univ Sci & Technol China Dept Automat Hefei 230027 Peoples R China Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China Univ Rhode Isl Dept Elect Comp & Biomed Engn Kingston RI 02881 USA

Object instance segmentation in traffic scenes is an important research topic. For training instance segmentation models, synthetic data can potentially complement real data, alleviating manual effort on annotating real images. However, the data distribution discrepancy between synthetic data and real data hampers the wide applications of synthetic data. In light of that, we propose a virtual-real interaction method for object instance segmentation. This method works over synthetic images with accurate annotations and real images without any labels. The virtual-real interaction guides the model to learn useful information from synthetic data while keeping consistent with real data. We first analyze the data distribution discrepancy from a probabilistic perspective, and divide it into image-level and instance-level discrepancies. Then, we design two components to align these discrepancies, i.e., global-level alignment and local-level alignment. Furthermore, a consistency alignment component is proposed to encourage the consistency between the global-level and the local-level alignment components. We evaluate the proposed approach on the real Cityscapes dataset by adapting from virtual SYNTHIA, Virtual KITTI, and VIPER datasets. The experimental results demonstrate that it achieves significantly better performance than state-of-the-art methods.

关键词： Image segmentation Annotations computational modeling automation Object detection Visualization Instance segmentation virtual-real interaction synthetic images distribution discrepancy autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

A Single-Stream Segmentation and Depth Prediction CNN for Autonomous Driving

引用

ieee INTELLIGENT SYSTEMS 2021年第4期36卷 79-85页

作者： Aladem, Mohamed Rawashdeh, Samir A. Univ Michigan Dearborn Dearborn MI 48128 USA

Convolutional neural networks (CNN) have been used successfully in solving many challenging visual perception tasks facing mobile robots and self-driving cars. To facilitate deploying such models on embedded hardware onboard mobile robots that have limited resources, multitask learning approaches have become common. In typically used multitask learning, a shared encoder network extracts features from inputs whereas multiple task-specific decoders transform these features into their target output. However, properly combining different tasks' losses into the final network loss such that each task is making progress learning is a major challenge in these approaches. In this article, we present an innovative approach to extend a typical single-task network with the capability of performing two tasks without multiple decoders, i.e., a single-stream two-task network. The two output tasks are semantic segmentation and monocular depth prediction which are essential tasks in visual perception for autonomous driving. The method is centered on solving semantic segmentation with a regression loss function rather than a classification one. With our approach, we seize multitask learning benefits of reduced overhead and enhanced generalization while alleviating the need to balance different loss functions. Experimental evaluations with baseline single tasks and a multitask network are presented.

关键词： Automobiles control Engineering Computing Convolutional Neural Nets Feature Extraction Image Segmentation Learning Artificial intelligence Mobile Robots Object Detection Traffic Engineering Computing Single Task Network Multiple Decoders Two Task Network Output Tasks Semantic Segmentation Monocular Depth Prediction Essential Tasks Autonomous Driving Regression Loss Function Multitask Learning Benefits Loss Functions Baseline Single Tasks Multitask Network Single Stream Segmentation Convolutional Neural Networks CNN Challenging Visual Perception Tasks Mobile Robots Self Driving Cars Embedded Hardware Typically Used Multitask Learning Shared Encoder Network Multiple Task Specific Decoders Target Output Different Tasks Final Network Loss Progress Learning Semantics Decoding Feature Extraction Image Segmentation computational Modeling Training Data Autonomous Vehicles Computer Vision For Transportation Deep Learning In Robotics And automation Semantic Scene Understanding

来源：评论

学校读者我要写书评

暂无评论

control science, AI and Robotics in Cyber Medicine: Featured topics of the Cybermedical Competence Center at Óbuda University

Control science, AI and Robotics in Cyber Medicine: Featured...

引用

International symposium on computational intelligence and Informatics

作者： Péter Galambos Óbuda Univeersity Budapest Hungary

ISBN: (纸本)9781665426855

In March of 2020, with the leadership of Obuda University, we established the Cyber-medical Competence Center in cooperation with the Research Center for Natural Sciences and the 3DHISTECH Ltd. The primary mission of this profoundly interdisciplinary organization is to introduce radically new approaches in a wide range of modern medicine through the synergies of engineering and mathematics with modern cell biology, genetics, and other medical sciences. Besides the basic research, the consortium aims to develop market-ready methods, software- and hardware products. With our joint forces, four main topics are addressed: New cancer treatment protocols with individual smart therapy; Supportive technologies for diabetes patients; Tissue analysis through single-cell genome sequencing and digital imaging with advanced visualization; Flexible automation of life science laboratories using robots. In my presentation, I introduce the motivation behind the Cyber-medical Competence Center under the conceptual framework of Cyber-Medical Systems. The lecture will focus on featured topics and research results achieved with the major contribution of the research teams of Obuda University.

关键词： Robots computational intelligence Artificial intelligence Visualization Sequential analysis Protocols Organizations

来源：评论

学校读者我要写书评

暂无评论

Combined Selection and Parameter control of Meta-heuristics

Combined Selection and Parameter Control of Meta-heuristics

引用

ieee symposium Series on computational intelligence (ieee SSCI)

作者： Pukhkaiev, Dmytro Semendiak, Yevhenii Goetz, Sebastian Assmann, Uwe Tech Univ Dresden Fac Comp Sci Dresden Germany

ISBN: (纸本)9781728125473

Parameter control and online algorithm selection are well-studied problems in heuristic-based optimization. The former adapts algorithm parameters at runtime, improving its quality;while the latter is often tackled with hyper-heuristics: problem-independent optimization algorithms, operating problem-dependent heuristics. Combining these two approaches is challenging: parameter control is algorithm-dependent, while the search space comprising multiple algorithms and their parameters is highly hierarchical and hard to model and traverse. In this paper we provide an approach to automatically select the best-performing algorithm and its configuration at runtime, combining the benefits of both parameter control and hyper-heuristics. Parameter control is realized with a surrogatemodel-based approach, while the complex search space is treated by using individual surrogate models for each level in the hierarchy. We evaluate our approach with four instances of the symmetric traveling salesman problem. Our findings show that the presented approach is comparable with heuristics tuned offline and is highly recommended in cases when the best-performing heuristic is not known in advance.

关键词： parameter control surrogate models hyper-heuristics traveling salesman problem hierarchical search spaces

来源：评论

学校读者我要写书评

暂无评论

Soft control: A Novel Application of Internet of Things for Demand Side Management 52

Soft Control: A Novel Application of Internet of Things for ...

引用

52nd North American Power symposium (NAPS)

作者： Dhulipala, Surya Chandan Li, Xin Bretas, Arturo Wu, Dapeng Ruben, Cody Univ Florida Dept Elect & Comp Engn Gainesville FL 32611 USA

ISBN: (纸本)9781728181929

Demand side management (DSM) is the modulation of consumers' energy demand to ameliorate the power network at the consumer side. In case of contingency which leads to frequency falling below a preset value, traditional methods like load shedding, which de-energize one or more feeders, are implemented to prevent sustained interruptions. This approach is neither efficient nor reliable because this may lead to loss of energy to critical infrastructure and loss of distributed energy sources (DERs) injection. Implementation of home automation and communication systems in distribution networks enables optimization of energy consumption during a power system contingency. Energy controllers (EC) can achieve fine adjustment of consumers' power consumption which can be used to selectively de-energize certain consumers, instead of a whole region. In this paper, a real-time centralized under-voltage event-based DSM approach called Soft control (SC) that modulates energy consumption of each consumers' load utilizing Internet of Things (IoT) is presented. This DSM technique can be utilized for both active and passive distribution networks and is formulated as a utilization maximization problem. The performance of the proposed DSM approach is evaluated using the ieee 16 bus system. The ease of implementation and computational efficiency highlight potential aspects for practical implementation.

关键词： Internet of Things demand side management demand response distributed generation Markov process smart grid power quality

来源：评论

学校读者我要写书评

暂无评论

Research on Capacity Regulating Transformer System Based on Computer Artificial intelligence Load Forecasting Technology

Research on Capacity Regulating Transformer System Based on ...

引用

ieee International Conference on automation, Electronics and Electrical Engineering (AUTEEE)

作者： Liangliang Zhao Hongmei Wang Decai Yuan State Grid Shanxi Electric Power Company Lvliang Power Supply Company Lvliang Shanxi China

ISBN: (数字)9781665471978

ISBN: (纸本)9781665471985

This paper analyzes the structure and capacity switching principle of the on-load capacity regulating transformer. At the same time, based on computer artificial intelligence load forecasting, this paper designs a transformer with automatic switching of single-chip control capacity. The system takes the single-chip microcomputer as the control center, and judges the current load of the transformer by monitoring the voltage and current of the low-voltage side of the transformer, and compares it with the set capacity threshold to switch between high and low-capacity gears to achieve the goal of energy saving. At the same time, this paper introduces the optimization method of the operation mode of the on-load capacity regulating transformer based on the attention mechanism's long and short-term memory network reduces the loss in the distribution network from the selection of the capacity regulating point and the planning of the operation mode. The experimental simulation shows that the method proposed in this paper has obvious improvement in the realization of energy saving and loss reduction of on-load capacity regulation and safe operation in complex environment.

关键词： Load forecasting computational modeling Switches Predictive models Transformers control systems Regulation

来源：评论

学校读者我要写书评

暂无评论

Calibration of agent-based model using reinforcement learning 1

Calibration of agent-based model using reinforcement learnin...

引用

1st ieee International Conference on Digital Twins and Parallel intelligence, DTPI 2021

作者： Song, Bing Xiong, Gang Yu, Songmin Ye, Peijun Dong, Xisong Lv, Yisheng Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex Systems Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Chinese Academy of Sciences Beijing China Fraunhofer Institute for Systems and Innovation Research Breslauer Germany

ISBN: (纸本)9781665433372

In the research and application of Agent-Based Models (ABM), parameter calibration is an important content. Based on the existing state transfer equations that link the micro-parameters and macro-states of the multi-agent system, this paper further proposes to introduce Reinforcement Learning when calibrating the parameters. The state transfer of the agent after learning is used to calibrate the micro-parameters of ABM, and the interaction between each agent and multiple other agents is expressed as the parameters of the agent. The application case study of population migration demonstrates that our method can achieve high accuracy and low computational complexity. © 2021 ieee.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

automation of Illuminance measurement in a large scene by an autonomous Mobile Robot

Automation of Illuminance measurement in a large scene by an...

引用

ieee symposium Series on computational intelligence (ieee SSCI)

作者： Tang, Cheng Inoue, Ryota Oshio, Kohei Tsujimoto, Makoto Taniguchi, Kazuhiko Kubota, Naoyuki Tokyo Metropolitan Univ Dept Mech Syst Engn Tokyo Japan Kyoto Inst Kinden Corp Kyoto Japan

ISBN: (纸本)9781728125473

In recent years, due to the shortage of labor caused by an aging population and low birth rate in Japan, various research on autonomous mobile robots has been conducted. There are many industries in which applying autonomous mobile robots are important, for instance, the illuminance measurement industry. Illuminance measurement is a time-consuming task and the accuracy in a vast environment is still a problem due to the accumulative error. Therefore, with the purpose of improving the accuracy of illuminance measurement in a large environment by an autonomous mobile robot, various methods have been proposed in the past, including loop closing, sensor fusion, and motion analysis. In this paper, we proposed a method that reduces the accumulative error simultaneously while measuring the illuminance of the surroundings. The proposed method is based on an occupancy grid map and evolution strategy (ES). We used the data gathered by laser range finders to calculate the fitness of robot position in both the ground-truth map and constructed map. By monitoring the fitness of the robot's position, the adjustments will be conducted using evolution strategy to overcome the accumulative error. The proposed method is analyzed and evaluated in terms of accuracy through a series of real robot experiments in real-world environments.

关键词： autonomous mobile robot illuminance measurement accuracy SLAM

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：