检索结果-内蒙古大学图书馆

作者： Fung, Wai-Keung Lo, Wang-Tai Liu, Yun-Hui Xi, Ning Department of Automation and Computer-Aided Engineering Networked Sensors and Robotics Laboratory Chinese University of Hong Kong Shatin N. T. Hong Kong Department of Electrical and Computer Engineering Robotics and Automation Laboratory Michigan State University East Lansing MI 48824 United States

ISBN: (纸本)0780389123

This paper reports a case study of using single 3D stereoscopic visual feedback for real-time teleoperation of dexterous tasks. In traditional teleoperation systems, real-time visual feedbacks of multiple monoscopic views of the robot workspace are provided for remote operator. However, it is difficult for the operator to control remote robot to perform dexterous tasks by looking at multiple video feedbacks at the same time. During teleoperation, remote operators usually find multiple 2D visual feedbacks confusing, especially when performing dexterous tasks that require accurate positioning and orientating of robot end-effectors. In this paper, we propose to provide single real-time 3D stereoscopic visual feedback for remote operators so that they perceive remote robot workspace with the sense of depth. This sense of 3D empowers remote operators to accurately position and orient robot end-effector with confidence. Experiments have been conducted to reveal the usefulness of real-time 3D stereoscopic video feedback over multiple monoscopic video feedback in real-time teleoperation. © 2005 IEEE.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

NONLINEAR DISCRETE-TIME ROBUST OUTPUT REGULATION PROBLEM

引用

IFAC Proceedings Volumes 2005年第1期38卷 282-287页

作者： Weiyao Lan Jie Huang Department of Automation and Computer-Aided Engineering Chinese University of Hong Kong Hong Kong China

In this paper, we will establish a framework that can convert a robust output regulation problem for discrete-time nonlinear systems into a robust stabilization problem for an appropriately augmented system consisting of the given plant and a specific dynamic system called internal model. We then apply this framework to solve the local robust output regulation problem for a general class of discrete-time nonlinear systems. The results of this paper gives a discrete-time counterpart of the recent results on the continuous-time robust output regulation problem.

关键词： discrete-time system nonlinear system output regulation stabilization internal model

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS OF HUMAN WALKING TRAJECTORIES FOR SURVEILLANCE

引用

International Journal of Information Acquisition 2004年第2期1卷 169-189页

作者： KA KEUNG LEE YANGSHENG XU Department of Automation and Computer-Aided Engineering The Chinese University of Hong Kong Hong Kong China

Surveillance of public places has become a worldwide concern in recent years. The ability to identify abnormal human behaviors in real-time is fundamental to the success of intelligent surveillance systems. The recognition of abnormal and suspicious human walking patterns is an important step towards the achievement of this goal. In this research, we develop an intelligent visual surveillance system that can classify normal and abnormal human walking trajectories in outdoor environments by learning from demonstration. The system takes into account both the local and global characteristics of the observed trajectories and is able to identify their normality in real-time. By utilizing support vector learning and a similarity measure based on hidden Markov models, the developed system has produced satisfactory results on real-life data during testing. Moreover, we utilize the approach of longest common subsequence (LCSS) in determining the similarity between different types of walking trajectories. In order to establish the position and speed boundaries required for the similarity measure, we compare the performance of a number of approaches, including fixed boundary values, variable boundary values, learning boundary by support vector regression, and learning boundary by cascade neural networks.

关键词： Trajectory analysis intelligent surveillance learning from demonstration

来源：评论

学校读者我要写书评

暂无评论

A virtual circle method for kinematic mapping from human hand to a non-anthropomorphic robot hand

A virtual circle method for kinematic mapping from human han...

引用

8th International Conference on Control, automation, Robotics and Vision (ICARCV)

作者： Wang, Heng Low, K.H. Gong, Feng Wang, Michael Yu School of Mechanical and Production Engineering Nanyang Technological University Nanyang Avenue Singapore 639798 Department of Automation and Computer-Aided Engineering Chinese University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)0780386531

An investigation was initiated on the study of the kinematic mapping between human hand and the non-anthropomorphic robot hand. To account for the significant dissimilarities between them, a "Virtual Circle Mapping" method has been developed based on the fingertips' relative positions. The principle of the method is to find suitable parameters in the hand frame, transform them to the robot frame, and then compute the robot fingertip positions according to the transformed parameters. The preliminary results and the comparison with the point-to-point mapping results are presented and analyzed. The generalization of the relative-position based mapping idea is also discussed. © 2004 IEEE.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

Global exponential stability of continuous-time interval neural networks

引用

Physical Review E 2002年第3期65卷 036133-036133页

作者： Sanqing Hu Jun Wang Department of Automation and Computer-Aided Engineering The Chinese University of Hong Kong Shatin New Territories Hong Kong

This paper addresses global robust stability of a class of continuous-time interval neural networks that contain time-invariant uncertain parameters with their values being unknown but bounded in given compact sets. We first introduce the concept of diagonally constrained interval neural networks and present a necessary and sufficient condition for global exponential stability of these interval neural networks irregardless of any bounds of nondiagonal uncertain parameters in connection weight matrices. Then we extend the robust stability result to general interval neural networks by giving a sufficient condition. Simulation results illustrate the characteristics of the main results.

关键词： .continuous-time neural network bounds matrices uncertain parameters constrained interval connection weight robust stability efficient condition compact sets interval neural Global exponential general interval

来源：评论

学校读者我要写书评

暂无评论

Synchronization and control of supermedia transmission via the internet

Synchronization and control of supermedia transmission via t...

引用

2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, ISIMP 2001

作者： Elhajj, Imad Hummert, Henning Xi, Ning Liu, Yun-Hui Li, Wen J. Department of Electrical and Computer Engineering 2120EB Michigan State University East Lansing MI 48824 United States Department of Automation and Computer-Aided Engineering Chinese University of Hong Kong ShatinN.T Hong Kong

ISBN: (纸本)9628576623

The growth of the Internet has been accompanied by an increase in its application. Many new Internet based applications have been introduced during the past decade. One of the most interesting of these is teleoperation, where the Internet is used as a bridge between operators and machines. The operator sends commands and receives visual and haptic feedback. Collectively, we refer to all those streams as supermedia. Teleoperation over the Internet comes with several problems: delay, lost packets and disconnection. All of these limitations may cause instability and desynchronization in teleoperation systems especially if those systems include haptic feedback. Most of the previous work in Internet based teleoperation rests on many limiting assumptions;for example, time delay is constant or has an upper bound, control is not in real-time. This paper presents a new real-time haptic feedback system that deals with these limitations and dificulties without any assumptions made regarding the time delay. The approach is based on Even Based Control, which has been implemented on a mobile robot and a mobile manipulator over the Internet.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

A MULTILAYER RECURRENT NEURAL NETWORK FOR REAL-TIME ROBUST POLE ASSIGNMENT IN SYNTHESIZING OUTPUT FEEDBACK CONTROL SYSTEMS

引用

IFAC Proceedings Volumes 2002年第1期35卷 271-276页

作者： Sanqing Hu Jun Wang Department of Automation and Computer-Aided Engineering The Chinese University of Hong Kong Shatin NT Hong Kong

Pole assignment is a basic design method for synthesis of feedback control systems. In this paper, a multilayer recurrent neural network is presented for robust pole assignment in synthesizing output feedback control systems. The proposed recurrent neural network is composed of three layers and is shown to be capable of synthesizing linear output feedback control systems via robust pole assignment in real time. Convergence of the neural network can be guaranteed. Moreover, with appropriate design parameters the neural network converges exponentially to an optimal solution to the robust pole assignment problem and the closed-loop control system based on the neural network is globally exponentially stable. These desired properties make it possible to apply the proposed recurrent neural network to slowly time-varying linear control systems. Simulation results are shown to demonstrate the effectiveness and advantages of the proposed neural network approach.

关键词： Recurrent neural network Output feedback control Robust pole assignment Self-tuning control

来源：评论

学校读者我要写书评

暂无评论

Supermedia enhanced e-service robots

Supermedia enhanced e-service robots

引用

IEEE International Conference on Robotics, Intelligent Systems and Signal Processing, RISSP 2003

作者： Elhajj, I. Xi, Ning Li, W.J. Liu, Yunhui Department of Computer Science and Engineering Oakland University RochesterMI48209 United States Department of Electrical and Computer Engineering Michigan State University East LansingMI48824 United States Department of Automation and Computer-Aided Engineering Chinese University of Hong Kong ShatinN.T. Hong Kong

The Internet, also known as e-world, has added a new dimension to many of the traditional concepts in industrial applications and everyday life. Many words encountered nowadays are prefixed by the letter "e" to reflect their close relation to the electronic world. Therefore, it was not surprising when researchers and businesses started developing "e-services", which are simply services provided via the Internet. The use of robots has dramatically expanded the potential of e-services. Now individuals with particular expertise can perform highly accurate and fairly complicated tasks remotely via the Internet. This increase in the human reachability is faced with several obstacles. Reliable and efficient robot facilitated services via the Internet face several challenges. These range from human-computer interfacing and overcoming random time delay to task synchronization and human-robot interaction. These limitations intensify when supermedia is being fed back and rendered in real-time. Supermedia are the term used to describe the collection of all the feedback streams;such as, haptic, video, audio, temperature and others. This paper provides new theoretical and experimental results on supermedia enhanced e-services. The main characteristics of such systems are Internet based real-time closed loop control with supermedia rendered in their original form. © 2003 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Nonlinear 1

引用

丛书名： Advances in Industrial Control

1000年

作者： Murad Abu-Khalaf Frank L. Lewis Jie Huang

ISBN: (数字)9781846283505

ISBN: (纸本)9781846283499;9781849965842

The series Advances in Industrial Control aims to report and encourage technology transfer in control engineering. The rapid development of control technology has an impact on all areas of the control discipline. New theory, new controllers, actuators, sensors, new industrial processes, computer methods, new applications, new philosophies , new challenges. Much of this development work resides in industrial reports, feasibility study papers and the reports of advanced collaborative projects. The series offers an opportunity for researchers to present an extended exposition of such new work in all aspects of industrial control for wider and rapid dissemination. Almost all physical systems are nonlinear and the success of linear control techniques depends on the extent of the nonlinear system behaviour and the careful attention given to switching linear controllers through the range of nonlinear system operations. In many industrial and process-control applications, good engineering practice, linear control systems and classical PID control can give satisfactory performance because the process nonlinearity is mild and the control system performance specification is not particularly demanding; however, there are other industrial system applications where the requirement for high-performance control can only be achieved if nonlinear control design techniques are used. Thus, in some industrial and technological domains there is a strong justification for more applications of nonlinear methods. One prevailing difficulty with nonlinear control methods is that they are not so easily understood nor are they easy to reduce to formulaic algorithms for routine application.

关键词： Control and Systems Theory Electrical engineering Automotive engineering Industrial and Production engineering Artificial Intelligence Industrial Chemistry/Chemical engineering

来源：评论

学校读者我要写书评

暂无评论

Spiral Path Planning for 2D Regions

Spiral Path Planning for 2D Regions

引用

2005国际机械工程与力学会议

作者： Zhiyang YAO Department of Automation and Computer-Aided Engineering Chinese University of Hong Kong

In robot planning problems, the complete coverage path planning refers to the problem of determining a path that a robot must take in order to pass over each point in an environment and avoid obstacles. Applications include de- mining, sweeping, cleaning, vacuuming, inspection robots. For this kind of problem, not only the complete coverage should be performed, but an efficient path is highly desired. Usually, a robot can move much faster if there is no sharp turns. Thus, finding a path that has the least number of sharp turns is preferred. This type of path is also desirable in milling operations, especially in high speed milling operations. Spiral curve is a special curve which can have no sharp turn, and the stepover between adjacent segments can also be controlled to a predefined value. However, traditional approaches to finding such a path either work for very simple convex regions, or, for irregular shapes, many overlap linkage paths have to be used. Thus, although spiral curves are promising, there is still not a good algorithm in generating a path which 1) covers the entire region, 2) has least number of turns, 3) uses an controllable stepover value. In this paper, we will introduce a novel approach which covers a 2D region in a very efficient manner. In particular, 1) it covers the 2D region using a set of modified spiral curves based on the geometry of the 2D region, 2) these curves are linked in a proper manner, 3) step-over values can be predefined and maintained. This proposed spiral path planning algorithm can be used in controlling robot movements as well as in generating efficient milling cutter paths in which the cutter engagement value is controlled within a predefined value.

关键词： Path Planning, Complete Coverage, Spiral Curve

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：