检索结果-内蒙古大学图书馆

3rd International Conference on Intelligence Science, ICIS 2018

作者： Xie, Yi Shang, Xiuqin Li, Yuqing Liu, Xiwei Zhu, Fenghua Xiong, Gang Pirttikangas, Susanna Zhou, Jiehan School of Electrical and Electronic Engineering The University of Manchester ManchesterM13 9PL United Kingdom The 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 DongguanGuangdong China College of Information Science and Technology Beijing University of Chemical Technology Beijing China Qingdao Academy of Intelligent Industries Qingdao China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing100190 China The Center for Ubiquitous Computing University of Oulu Oulu Finland

ISBN: (纸本)9783030013127

For personalized design it is important to be able to collect, measure and evaluate individual properties of human beings. This paper proposes registration for the point clouds during foot 3D scanning. In the experiment, we get the point clouds of the human foot from the Artec 3D scanner and complete the registration of the point clouds from different visual angles. Dealing with the customized footwear, we choose a novel algorithm, which combines the NARF key point detector and the FPFH descriptor, to improve the efficiency of the initial iteration and reduce the computation burden of matching process. © IFIP International Federation for Information Processing 2018.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Near minimum-time feedback attitude control with multiple saturation constraints for agile satellites

引用

Chinese Journal of Aeronautics 2016年第3期29卷 722-737页

作者： Liu Xiangdong Xin Xing Li Zhen Chen Zhen Sheng Yongzhi School of Automation Beijing Institute of Technology National Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology

Agile satellites are of importance in modern aerospace applications, but high mobility of the satellites may cause them vulnerable to saturation during attitude maneuvers due to limited rating of actuators, This paper proposes a near minimum-time feedback control law for the agile satellite attitude control system. The feedback controller is formed by specially designed cascaded sub-units. The rapid dynamic response of the modified Bang Bang control logic achieves the near optimal property and ensures the non-saturation properties on three-axis. To improve the dynamic performance, a model reference control strategy is proposed, in which the oniline near optimal attitude maneuver path is generated by the cascade controller and is then tracked by a nonlinear back-stepping controller. Furthermore, the accuracy and the robustness of the control system are achieved by momentum-based on-line inertial identification. The rapid attitude maneuvering can be applied for tasks including the move to move case. Numerical simulations are conducted to verify the effectiveness of the proposed control strategy in terms of the saturation-free property and rapidness.

关键词： Actuator saturation Attitude control Identification Momentum transfer Satellites

来源：评论

学校读者我要写书评

暂无评论

High-accuracy carrier frequency acquisition algorithm of GNSS signal based on numerical approximation method 5

High-accuracy carrier frequency acquisition algorithm of GNS...

引用

5th International Workshop on Advanced Computational Intelligence and intelligent Informatics, IWACIII 2017

作者： Wang, Guangjun Deng, Xuening Wu, Min School of Automation China University of Geosciences Wuhan430074 China China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System Wuhan430074 China

The bandwidth of the Doppler frequency shift under high dynamic environment that the GNSS receivers need to search is 5-10 times than the conventional receivers, a large frequency step is generally chosen to improve the satellite signal acquisition speed. Aiming at the problem that acquisition carrier frequency deviation caused by the large step search cannot meet the requirement of the tracking loop design, a fine frequency estimation method based on numerical approximation is proposed in this paper. The proposed method applied the preferred frequency slot and approximated the capture correlation peak combined with the curve fitting method, which can reduce the frequency deviation, and improve the accuracy of acquisition, then simplify the complexity of tracking loop design. Simulation results show that it has higher accuracy than the other two algorithm at different SNR (Signal to Noise Ratio).

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

Learning ReLU networks on linearly separable data: Algorithm, optimality, and generalization

arXiv

引用

arXiv 2018年

作者： Wang, Gang Giannakis, Georgios B. Chen, Jie Digital Technology Center Department of Electrical and Computer Engineering University of Minnesota MinneapolisMN55455 United States State Key Lab of Intelligent Control Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Tongji University Shanghai200092 China

Neural networks with REctified Linear Unit (ReLU) activation functions (a.k.a. ReLU networks) have achieved great empirical success in various domains. Nonetheless, existing results for learning ReLU networks either pose assumptions on the underlying data distribution being e.g. Gaussian, or require the network size and/or training size to be sufficiently large. In this context, the problem of learning a two-layer ReLU network is approached in a binary classification setting, where the data are linearly separable and a hinge loss criterion is adopted. Leveraging the power of random noise perturbation, this paper presents a novel stochastic gradient descent (SGD) algorithm, which can provably train any single-hidden-layer ReLU network to attain global optimality, despite the presence of infinitely many bad local minima, maxima, and saddle points in general. This result is the first of its kind, requiring no assumptions on the data distribution, training/network size, or initialization. Convergence of the resultant iterative algorithm to a global minimum is analyzed by establishing both an upper bound and a lower bound on the number of non-zero updates to be performed. Moreover, generalization guarantees are developed for ReLU networks trained with the novel SGD leveraging classic compression bounds. These guarantees highlight a key difference (at least in the worst case) between reliably learning a ReLU network as well as a leaky ReLU network in terms of sample complexity. Numerical tests using both synthetic data and real images validate the effectiveness of the algorithm and the practical merits of the theory. Copyright © 2018, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Learning Approach: Stacked Evolutionary Auto-encoder

A Novel Deep Learning Approach: Stacked Evolutionary Auto-en...

引用

International Joint Conference on Neural Networks

作者： Yaoming Cai Zhihua Cai Meng Zeng Xiaobo Liu Jia Wu Guangjun Wang School of Computer Science China University of Geosciences Wuhan China Qinzhou University Guangxi China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Department of Computing Macquarie University Sydney NSW Australia

Deep neural networks have been successfully applied to many data mining problems in recent works. The training of deep neural networks relies heavily upon gradient descent methods, however, which may lead to the failure of training due to the vanishing gradient (or exploding gradient) and local optima problems. In this paper, we present SEvoAE method based on using Evolutionary Multiobjective Optimization (EMO) algorithm to train single layer auto-encoder, and sequentially learning deeper representation in a stacking way. SEvoAE is able to achieve accurate feature representation with good sparseness by globally simultaneously optimizing two conflicting objective functions and allows users to flexibly design objective functions and evolutionary optimizers. We compare results of the proposed method with existing architectures for seven classification problems, showing that the proposed method is able to outperform existing methods with a reduced risk of overfitting the training data.

关键词： Training Optimization Decoding Neural networks Linear programming Feature extraction Stacking

来源：评论

学校读者我要写书评

暂无评论

A fast test and compensation system for optical encoders based on extreme learning machine — Fourier Neural Network

A fast test and compensation system for optical encoders bas...

引用

Youth Academic Annual Conference of Chinese Association of automation (YAC)

作者： Jiachen Zhao Jie Chen Fang Deng Hongda Li Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing China School of Automation Beijing Institute of Technology BeiJing

ISBN: (纸本)9781538629024

This paper describes fast test and compensation system for optical encoders. The resolution of system is 0.375", and it can measure the actual accuracy of an optical encoder in four minutes. Furthermore, a method called Extreme Learning Machine - Fourier Neural Network (ELM-FNN) are proposed to compensate the error. Fourier neural network (FNN) is chosen to fit the curve of the optical encoder's output, and the weights of FNN is calculated by Extreme Learning Machine (ELM). Experimental results demonstrate that ELM-FNN effectively improve the accuracy of the optical encoder. Compared to a back propagation neural network (BP net) and a standard FNN, ELM-FNN has advantages of higher accuracy and less training time.

关键词： Adaptive optics Optical computing Optical variables measurement Optical sensors Neural networks Ultraviolet sources Training

来源：评论

学校读者我要写书评

暂无评论

control method on serial type pump-valve coordinated electro-hydraulic servo system

引用

Journal of Beijing Institute of Technology 2016年第1期25卷 100-107页

作者：谢文汪首坤王军政吴建 Key Laboratory of Intelligent Control and Decision of Complex System School of AutomationBeijing Institute of Technology

In order to compromise the conflicts between control accuracy and system efficiency of conventional electro-hydraulic servo systems,a novel pump-valve coordinated electro-hydraulic servo system was designed and a corresponding control strategy was *** system was constituted of a pumpcontrolled part and a valve-controlled part,the pump controlled part is used to adjust the flow rate of oil source and the valve controlled part is used to complete the position tracking control of the hydraulic *** on the system characteristics,a load flow grey prediction method was adopted in the pump controlled part to reduce the system overflow losses,and an adaptive robust control method was adopted in the valve controlled part to eliminate the effect of system nonlinearity and parametric uncertainties due to variable hydraulic parameters and system loads on the control *** experimental results validated that the adopted control strategy increased the system efficiency obviously with guaranteed high control accuracy.

关键词： pump-valve coordinated grey prediction adaptive robust control efficiency

来源：评论

学校读者我要写书评

暂无评论

Novel algorithm of gait planning of hydraulic quadruped robot to avoid foot slidingand reduce impingement

引用

Journal of Beijing Institute of Technology 2016年第1期25卷 91-99页

作者：马立玲杨超峰王立鹏王军政 Key Laboratory of Intelligent Control and Decision of Complex System School of AutomationBeijing Institute of Technology

In order to solve kinematic redundancy problems of a hydraulic quadruped walking robot,which include leg dragging,sliding,impingement against the ground,an improved gait planning algorithm for this robot is proposed in this ***,the foot trajectory is designated as the improved composite cycloid foot ***,the landing angle of each leg of the robot is controlled to satisfy friction cone to improve the stability performance of the *** with the controllable landing angle of quadruped robot and a geometry method,the kinematic equation is derived in this ***,agait planning method of quadruped robot is proposed,a dynamic co-simulation is done with ADAMS and MATLAB,and practical experiments are *** validity of the proposed algorithm is confirmed through the co-simulation and *** results show that the robot can avoid sliding,reduce impingement,and trot stably in trot gait.

关键词： landing angle gait planning foot trajectory friction cone sliding impingement

来源：评论

学校读者我要写书评

暂无评论

Localization and mapping in urban area based on 3D point cloud of autonomous vehicles

引用

Journal of Beijing Institute of Technology 2016年第4期25卷 473-482页

作者：王美玲李玉杨毅朱昊刘彤 Key Laboratory of Intelligent Control and Decision of Complex System School of AutomationBeijing Institute of Technology

In order to meet the application requirements of autonomous vehicles, this paper proposes a simultaneous localization and mapping （SLAM） algorithm, which uses a VoxelGrid filter to down sample the point cloud data, with the combination of iterative closest points （ICP） algorithm and Gaussian model for particles updating, the matching between the local map and the global map to quantify particles＇ importance weight. The crude estimation by using ICP algorithm can find the high probability area of autonomous vehicles＇ poses, which would decrease particle numbers, increase algorithm speed and restrain particles＇ impoverishment. The calculation of particles＇ importance weight based on matching of attribute between grid maps is simple and practicable. Experiments carried out with the autonomous vehicle platform validate the effectiveness of our approaches.

关键词： simultaneous localization and mapping （SLAM） Rao-Blackwellized particle filter （ RB-PF） VoxelGrid filter ICP algorithm Gaussian model urban area

来源：评论

学校读者我要写书评

暂无评论

Cooperative transportation control of multiple mobile manipulators through distributed optimization

引用

Science China. Information Sciences 2018年第12期61卷 120201-1--120201-1--120201-17页

作者： Chen Jie Kai Shixiong School of Automation Beijing Institute of Technology Key Laboratory of Intelligent Control and Decision of Complex SystemsMOE Beijing 100081

This paper investigates the problem of distributed control of multiple redundant mobile manipulators to collectively transport an object tracking a desired trajectory with energy and manipulability optimized. To solve this optimization problem, formation control tasks are introduced as equality constraints with the variables being the velocities. In this paper, we propose a distributed proximal gradient algorithm searching for the optimal solution, with which the stability of the closed-loop system is proved. Simulations demonstrate the effectiveness of the proposed distributed optimization scheme and proximal algorithm.

关键词： multiple mobile manipulators cooperative transportation control motion planning energy and manipulability distributed optimization

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：