检索结果-内蒙古大学图书馆

Eurocon

作者： Filip Jukić Damir Sumina Luka Pravica Igor Kuzle Department of Electric Machines Drives and Automation Faculty of Electrical Engineering and Computing Zagreb Croatia

ISBN: (纸本)9781509038442

Recently, there has been a lot of researches on various methods for a sensorless control of permanent magnet generators (PMG) in wind turbines. The sensorless control of the PMG considers estimations of a rotor angle and speed which are based on the PMG parameters estimation. The parameters that have been estimated are stator resistance, rotor flux, d-axis and q-axis inductance. For more precise rotor angle and speed estimation, it is essential to determinate values of the PMG parameters in every operating point as accurately as possible. A change of the operating point (different rotor speed, shaft torque etc.) causes the change of the PMG parameters due to stator currents and temperature variation. Accordingly, the PMG parameters could be measured during a PMG commissioning. In this work, the stator resistance is measured while taking into considering a dead time compensation and voltage drop on a power switching devices. A determination of the d-axis and q-axis inductances is based on PMG voltage equations in a dq synchronous reference frame. Thus, the measurements of the rotor speed, stator currents and voltages are required. The experimental measurements are carried out on a 375 kW interior permanent magnet generator. Finally, the measured values could be saved on a digital signal processor (DSP) as look-up tables and used for the sensorless control of the PMG.

关键词： Stators Rotors Voltage measurement Electrical resistance measurement Resistance Current measurement Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Human intention estimation based on hidden Markov model motion validation for safe flexible robotized warehouses

arXiv

引用

arXiv 2018年

作者： Petković, Tomislav Puljiz, David Marković, Ivan Hein, Björn University of Zagreb Faculty of Electrical Engineering and Computing Department of Control and Computer Engineering Laboratory for Autonomous Systems and Mobile Robotics Unska 3 ZagrebHR-10000 Croatia Karlsruhe Institute of Technology Institute for Anthropomatics and Robotics Intelligent Process Automation and Robotics Lab Kaiserstraße 12 Deutschland KarlsruheDE-76131

With the substantial growth of logistics businesses the need for larger warehouses and their automation arises, thus using robots as assistants to human workers is becoming a priority. In order to operate efficiently and safely, robot assistants or the supervising system should recognize human intentions in real-time. Theory of mind (ToM) is an intuitive human conception of other humans' mental state, i.e., beliefs and desires, and how they cause behavior. In this paper we propose a ToM based human intention estimation algorithm for flexible robotized warehouses. We observe human's, i.e., worker's motion and validate it with respect to the goal locations using generalized Voronoi diagram based path planning. These observations are then processed by the proposed hidden Markov model framework which estimates worker intentions in an online manner, capable of handling changing environments. To test the proposed intention estimation we ran experiments in a real-world laboratory warehouse with a worker wearing Microsoft Hololens augmented reality glasses. Furthermore, in order to demonstrate the scalability of the approach to larger warehouses, we propose to use virtual reality digital warehouse twins in order to realistically simulate worker behavior. We conducted intention estimation experiments in the larger warehouse digital twin with up to 24 running robots. We demonstrate that the proposed framework estimates warehouse worker intentions precisely and in the end we discuss the experimental results. Copyright © 2018, The Authors. All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Visual Place Recognition in Long-term and Large-scale Environment based on CNN Feature

Visual Place Recognition in Long-term and Large-scale Enviro...

引用

2018 IEEE Intelligent Vehicles Symposium, IV 2018

作者： Zhu, Jianliang Ai, Yunfeng Tian, Bin Cao, Dongpu Scherer, Sebastian School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Cloud Computing Center Chinese Academy of Sciences Dongguan523808 China Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada Robotics Institute Carnegie Mellon University PittsburghPA15213 United States

ISBN: (纸本)9781538644522

With the universal application of camera in intelligent vehicles, visual place recognition has become a major problem in intelligent vehicle localization. The traditional solution is to make visual description of place images using hand-crafted feature for matching places, but this description method is not very good for extreme variability, especially for seasonal transformation. In this paper, we propose a new method based on convolutional neural network (CNN), by putting images into the pre-trained network model to get automatically learned image descriptors, and through some operations of pooling, fusion and binarization to optimize them, then the similarity result of place recognition is presented with the Hamming distance of the place sequence. In the experimental part, we compare our method with some state-of-the-art algorithms, FABMAP, ABLE-M and SeqSLAM, to illustrate its advantages. The experimental results show that our method based on CNN achieves better performance than other methods on the representative public datasets. © 2018 IEEE.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

Goal-biased probabilistic foam method for robot path planning

Goal-biased probabilistic foam method for robot path plannin...

引用

IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

作者： Luis B. P. Nascimento Diego S. Pereira Pablo J. Alsina Mauricio R. Silva Daniel H. S. Fernandes Válber C. C. Roza Armando S. Sanca Departament of Computing Engineering and Automation Federal University of Rio Grande do Norte (UFRN) Natal RN Brazil Department of Information Science and Technology Instituto Universitário de Lisboa (ISCTE-IUL) Lisboa Portugal Department of Technology State University of Feira de Santana Feira de Santana Bahia Brazil

This paper presents an improved variation of Probabilistic Foam Method (PFM) for robot path planning. In PFM, a structure named probabilistic foam, formed by bubbles propagate through the free space from initial configuration to goal as a breadth-first search, obtaining a collision-free path. Although the method is able to obtain a navigable path, it is computationally expensive. We propose a new foam propagation approach inspired on random tree growth from RRT. Results from simulation experiments using 2D and 3D map show benefits with the new method.

关键词： Probabilistic logic Collision avoidance Conferences Autonomous robots Path planning Mathematical model

来源：评论

学校读者我要写书评

暂无评论

An Open Source Map Optimization Platform for Efficient Navigation

An Open Source Map Optimization Platform for Efficient Navig...

引用

IEEE International Conference on Computational Science and engineering, CSE

作者： Liangming Cai Chunqiang Chen Xiaoling Wang Shurui Lin Kai Cheng Jiefeng Huang Jinping Jiang Minchen Zhu Min Du Rituparna Datta Yurong Li Jingshan Huang Zhicheng College College of Physics and Information Engineering Fuzhou University Fuzhou China University of South Alabama HaiXi Institutes Chinese Academy of Science Fuzhou China Zhicheng College Zhicheng College Fuzhou University Fuzhou China College of Allied Health Professions University of South Alabama Mobile USA Department of Respiratory Medicine Fujian Medical University Fuzhou China College of Electrical Engineering & Automation Fuzhou University Fuzhou China College of Mathematics and Computer Science Fuzhou University Fuzhou China Provincial Key Laboratory of Eco-industrial Green Technology Wuyi College Wuyishan China Fuzhou University School of Computing University of South Alabama Mobile USA Fuzhou University Fuzhou China

Aiming at the problem that the map operation time occupies more resources in the embedded system. By studying the digital map, then the corresponding map is drawn and the map is optimized. Using the GPS/BEIDOU module to locate and use the Dijkstra algorithm to achieve the shortest path of the navigation module design, the use of the map database to remove the corresponding area of the data mapping map information, in a translation to a certain distance when the scene clear the data, draw a map. In this way, there will be no data left in the view. Since the Dijkstra algorithm is based on the graph, it is necessary to link the roads in the area to create an indirect graph to find the shortest path to the end point. If the point of the line as an indirect node, the composition of the indirect map will be very large. Moreover, the use of the line as an indirect node, we can reduce the number of nodes without the map, to improve the efficiency of Dijkstra algorithm traversal. Based on the open system platform and data standard, this paper designs and develops a secure, stable and low cost embedded GPS/BEIDOU navigation and navigation system. The experimental results are optimized. The results show that the proposed method is efficient for navigation.

关键词： Conferences Scientific computing Ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

Towards human-like and transhuman perception in AI 2.0:a review

引用

Frontiers of Information Technology & Electronic engineering 2017年第1期18卷 58-67页

作者： Yong-hong TIAN Xi-lin CHEN Hong-kai XIONG Hong-liang LI Li-rong DAI Jing CHEN Jun-liang XING Xi-hong WU Wei-min HU Yu HU Tie-jun HUANG Wen GAO School of Electronics Engineering and Computer Science Peking University Institute of Computing Technology Chinese Academy of Sciences Department of Electronic Engineering Shanghai Jiao Tong University School of Electronic Engineering University of Electronic Science and Technology of China Department of Electronic Engineering and Information Sciences University of Science and Technology of China School of Optoelectronics Beijing Institute of Technology Institute of Automation Chinese Academy of Sciences

Perception is the interaction interface between an intelligent system and the real world. Without sophisticated and flexible perceptual capabilities, it is impossible to create advanced artificial intelligence （AI） systems. For the next-generation AI, called ＇AI 2.0＇, one of the most significant features will be that AI is empowered with intelligent perceptual capabilities, which can simulate human brain＇s mechanisms and are likely to surpass human brain in terms of performance. In this paper, we briefly review the state-of-the-art advances across different areas of perception, including visual perception, auditory perception, speech perception, and perceptual information processing and learning engines. On this basis, we envision several R＆D trends in intelligent perception for the forthcoming era of AI 2.0, including：（1） human-like and transhuman active vision; （2） auditory perception and computation in an actual auditory setting; （3） speech perception and computation in a natural interaction setting; （4） autonomous learning of perceptual information; （5） large-scale perceptual information processing and learning platforms; and （6） urban omnidirectional intelligent perception and reasoning engines. We believe these research directions should be highlighted in the future plans for AI 2.0.

关键词： Intelligent perception Active vision Auditory perception Speech perception Autonomous learning

来源：评论

学校读者我要写书评

暂无评论

Comparisons among Six Numerical Methods for Solving Repetitive Motion Planning of Redundant Robot Manipulators

Comparisons among Six Numerical Methods for Solving Repetiti...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Zhijun Zhang Lingdong Kong Ziyi Yan Ke Chen Shuai Li Xilong Qu Ning Tan School of Automation Science & Engineering South China University of Technology Guangzhou China School of Electronic & Information Engineering South China University of Technology Guangzhou China Department of Computing Hong Kong Polytechnic University Hong Kong China School of Information Technology & Management Hunan University of Finance and Economics Changsha China School of Data & Computer Science Sun Yat-sen University Guangzhou China

ISBN: (纸本)9781728103785;9781728103778

To ensure that each joint of redundant robot manipulators can return to its initial state when completes a closed-path tracking task, a repetitive motion planning (RMP) scheme is presented. On the basis of a quadratic programming (QP) framework, this RMP can be equivalently converted into a linear-variational-inequality (LVI) problem, and then into a piecewise linear projection equation (PLPE). In this paper, three novel numerical methods (i.e., M3, M5 and M6) and three traditional numerical methods (i.e., 94LVI, E47 and M4) are exploited, analyzed, and compared to solve PLPE, as well as RMP. The convergence of M5 method is theoretically proved, and that of M3 and M6 methods is analyzed by simulations. Moreover, comparative simulations of two complex path tracking tasks performed on a PUMA560 robot manipulator further verify the feasibility and effectiveness of the proposed numerical methods.

关键词： Robot kinematics Motion planning Quadratic programming Complex path tracking

来源：评论

学校读者我要写书评

暂无评论

Mobile Model Predictive Control for the Évora irrigation test canal

引用

IFAC-PapersOnLine 2017年第1期50卷 6570-6575页

作者： López Rodríguez F. Horváth K. García Martín J. Maestre J.M. Department of Systems and Automation University of Seville Avenida de los descubrimientos s/n 41092 Seville Spain Department of Mechanical Engineering Eindhoven University of Technology Building Gemini Zuid Groene Loper Eindhoven MB 5600 United States Department of Systems and Automation University of Seville Department of Computer Science School of Computing Tokyo Institute of Technology Avenida de los Descubrimientos s/n 41092 4259-J2-54 Nagatsuta-cho Midori-ku Seville Yokohama 226-8502 Spain

Mobile Model Predictive control is a novel control technique for irrigation canals that optimizes the actions carried out by human operators. In this paper it is assessed preliminary by means of the numerical model of a reduced scale laboratory irrigation canal located in the facilities of the University of Évora (Portugal). Other control algorithms have also been tested by using a numerical model of the canal and compared with the novel control method: proportional integral control, linear quadratic regulator and centralized model predictive control. The results show that mobile model predictive control offers a performance comparable to that of fully automatic control despite being based exclusively on human operation. © 2017

关键词： automatic control control applications Predictive control

来源：评论

学校读者我要写书评

暂无评论

Pansharpening via detail injection based convolutional neural networks

arXiv

引用

arXiv 2018年

作者： He, Lin Rao, Yizhou Li, Jun Plaza, Antonio Zhu, Jiawei School of Automation Science and Engineering South China University of Technology Guangzhou510640 China Guangdong Provincial Key Laboratory of Urbanization and Geo-simulation School of Geography and Planning Sun Yat-sen University Guangzhou510275 Hyperspectral Computing Laboratory Department of Technology of Computers and Communications Escuela Politécnica University of Extremadura CaceresE-10071

Pansharpening aims to fuse a multispectral (MS) image with an associated panchromatic (PAN) image, producing a composite image with the spectral resolution of the former and the spatial resolution of the latter. Traditional pansharpening methods can be ascribed to a unified detail injection context, which views the injected MS details as the integration of PAN details and band-wise injection gains. In this work, we design a detail injection based CNN (DiCNN) framework for pansharpening, with the MS details being directly formulated in end-to-end manners, where the first detail injection based CNN (DiCNN1) mines MS details through the PAN image and the MS image, and the second one (DiCNN2) utilizes only the PAN image. The main advantage of the proposed DiCNNs is that they provide explicit physical interpretations and can achieve fast convergence while achieving high pansharpening quality. Furthermore, the effectiveness of the proposed approaches is also analyzed from a relatively theoretical point of view. Our methods are evaluated via experiments on real-world MS image datasets, achieving excellent performance when compared to other state-of-the-art methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Sequential Solution Polymerization of Poly(3,4-Ethylenedioxythiophene) Using V2O5 as Oxidant for Flexible Touch Sensors

SSRN

引用

SSRN 2018年

作者： Chen, Rui Sun, Kuan Zhang, Qi Zhou, Yongli Li, Meng Sun, Yuyang Wu, Zhou Wu, Yuyang Li, Xinlu Xi, Jialei Ma, Chi Zhang, Yiyang Ouyang, Jianyong MOE Key Laboratory of Low-grade Energy Utilization Technologies and Systems School of Energy & Power Engineering Chongqing University Chongqing400044 China MOE Key Laboratory of Dependable Service Computing in Cyber Physical Society School of Automation Chongqing University Chongqing400044 China School of Materials Science and Engineering Chongqing University Chongqing400044 China Chengdu Mobius Technology Sichuan610015 China Department of Materials Science and Engineering National University of Singapore Singapore117574 Singapore

Various in-situ synthesis methods have been developed for the polymerization of 3,4-ethylenedioxythiophene (EDOT) monomers, such as electro-polymerization (EP), oxidative chemical vapor deposition (OCVD) and vapor phase polymerization (VPP). Additional to these existing techniques, here a novel and facile method is introduced to fabricate highly conductive poly(3,4-ethylenedioxythiophene) (PEDOT) films in-situ by solution means. The process contains sequential deposition of oxidants and monomers. V2O5 is introduced as the oxidant in this synthetic route. Excess reactants and by-products can be completely removed from the PEDOT film by MeOH-rinsing. The obtained PEDOT films possess good crystallinity and high doping level, with carrier concentration three orders of magnitude higher than the commercial product (PH1000, Heraeus GmbH). The electrical conductivity of the as-cast PEDOT film reaches up to 1420 S/cm. In addition, this method is fully compatible with large-scale printing techniques. A 15 cm × 12 cm PEDOT film is printed on polyethylene terephthalate (PET) substrate by bar coating. These PEDOT conducting films enable the realization of flexible touch sensors, which demonstrate superior flexibility and sensitivity. The low-cost and highly efficient synthetic method shows great potential for large-scale production of PEDOT films that have wide applications in electromagnetic shielding, antistatic coating, sensor, etc. © 2018, The Authors. All rights reserved.

关键词： Monomers

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：