检索结果-内蒙古大学图书馆

International Conference on Information Science and Technology (ICIST)

作者： Liangliang Cui Yongsheng Ou Junbo Xin Dawei Dai Xiang Gao School of Mechanical and Automotive Engineering sSouth China University of Technology Guangzhou China Guangdong Provincial Key Labortory of Robotics and Intelligent System Chinese Academy of Science Department of Mechanical and Automation Engineering Chinese University of Hongkong Hongkong China

Recently, learning based control is a popular topic on robotic applications. This paper presents a novel learning based intelligent control method which realizes the balance control of a statically unstable and dynamically stable robot - a two-wheeled self-balancing robot. The control strategy could be segmented into two levels: a learning based controller using Support Vector Regression approach as a high level and a traditional PD controller as a low level. Support Vector Regression is utilized to learn the mapping between robot's state data and corresponding actions from experiments by using the inclined angle and its angular speed as inputs and the wheels velocity of the robot needed to keep balance as outputs. And the low level PD controller makes sure the motors achieve the velocity value gained before. Experiments are taken to show that the control method is useful and efficient. Additionally, this paper presents a practice of learning based control.

关键词： Mobile robots Support vector machines Mathematical model Equations Accelerometers Mobile communication

来源：评论

学校读者我要写书评

暂无评论

Gene Therapy: Magnetic Helical Microswimmers Functionalized with Lipoplexes for Targeted Gene Delivery (Adv. Funct. Mater. 11/2015)

引用

Advanced Functional Materials 2015年第11期25卷

作者： Famin Qiu Satoshi Fujita Rami Mhanna Li Zhang Benjamin R. Simona Bradley J. Nelson Institute of Robotics and Intelligent System (IRIS) ETH Zurich Zurich CH‐8092 Switzerland Biomedical Research Institute AIST 1‐1‐1 Higashi Tsukuba Ibaraki 305‐8566 Japan Laboratory of Biosensors and Bioelectronics University and ETH Zurich Zurich CH‐8092 Switzerland Biomedical Engineering American University of Beirut Beirut 1107 2020 Lebanon Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong SAR China Chow Yuk Ho Technology Centre for Innovative Medicine The Chinese University of Hong Kong Hong Kong SAR China

来源：评论

学校读者我要写书评

暂无评论

A new bio-inspired unsupervised learning method

A new bio-inspired unsupervised learning method

引用

6th International Conference on Brain Inspired Cognitive systems, BICS 2013

作者： Weng, Kaijian Liang, Guoyuang Wu, Xinyu Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9783642387852

Unsupervised learning has been widely used in many areas such as pattern recognition. However, it is usually difficult to acquire accurate representation of pattern within a limited period of time. Unsupervised learning, in general, is likely to be more common in brain than supervised learning. In this paper, we propose a new neural network based unsupervised learning method and evaluate its applications on 1-D and 2-D pattern learning. Our approach is inspired by recent researches on the physiological process of neural connection and brain activity. A bipolar weight scheme based on biological neural connection mechanism is presented. Moreover, we have also noticed the synaptic plasticity of brain plays an important role in learning. A new brain-inspired short-term and long-term scheme is applied in our method to adjust weights during the learning process. Experimental results of learning over 1-D and 2-D patterns demonstrate the proposed method is effective and high-efficiency. © 2013 Springer-Verlag.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive visual servoing using common image features with unknown geometric parameters

Adaptive visual servoing using common image features with un...

引用

作者： Liu, Yun-Hui Wang, Hesheng Chen, Weidong Zhou, Dongxiang Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong Hong Kong Department of Automation Shanghai Jiao Tong University China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China State Key Laboratory of Robotics Technology and System Harbin Institute of Technology Harbin 150001 China Joint Center for Intelligent Sensing and Systems National University of Defense Technology China

This paper generalizes the concept of the depth-independent interaction matrix, developed for point and line features in our early work, to generalized image features. We derive the conditions under which the depth-independent interaction matrix can be linearly parameterized by the geometric parameters of the generalized image features, and propose an adaptive visual servo controller for robot manipulators using the generalized image features whose geometric parameters are unknown. To estimate the unknown parameters on-line, we propose new error functions that are linear to estimation errors of the parameters and an algorithm that minimizes the error functions using multiple images. The Lyapunov theory is used to prove asymptotic stability of the proposed controller based on the nonlinear dynamics of the manipulator. It is also shown that in addition to points and lines, other common image features like distances, angles, areas, and centroids all satisfy the conditions for the linear parameterization. Experiments have been conducted to validate the proposed control method. © 2013 Elsevier Ltd. All rights reserved.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Clothbot: Hardware improvement and auto-control

Clothbot: Hardware improvement and auto-control

引用

IEEE International Conference on robotics and Biomimetics

作者： Pengfei Liu Yuanyuan Liu Duan Zheng Jianquan Sun Wei Feng Xinyu Wu Guangdong Provincial Key Laboratory of Robotics and Intelligent System Chinese Academy of Sciences China Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong SAR China

ISBN: (纸本)9781479927456

Clothbot is a new kind of climbing robot with novel structure that enables it to move on human cloth. Earlier version of Clothbot can only climb on cloth with manual control because there is complex deformation on human cloth and thus Clothbot can't keep itself stable. In this paper, we propose some new hardware improvements to enhance the stability of Clothbot on human cloth, then adopt a remote control system that enables Clothbot climbing automatically. To ensure that proper amount of cloth is gripped between two wheels, we add a shield in the front to prevent Clothbot from suck superfluous cloth and adjust its pose to prevent it from slipping off. A balance tail in the end makes Clothbot free from side tumbling. Based on these hardware improvement, Clothbot can move steadily on human body and auto control strategy becomes applicable. The whole climbing process is divide into discrete steps and A* is repeatedly called to compute path at the beginning of each step. Experiments have been conduct to test the effect of hardware change and it shows that Clothbot can automatically climb on human body.

关键词： Wheels Turning Neck Stability analysis Robots Hardware Gravity

来源：评论

学校读者我要写书评

暂无评论

A novel local path planning method considering both robot posture and path smoothness

A novel local path planning method considering both robot po...

引用

IEEE International Conference on robotics and Biomimetics

作者： Xiang Gao Yongsheng Ou Yiqun Fu Zhao Li Dawei Dai Liangliang Cui Yimin Zhou Weidong Guo The School of Mechanical Engineering & Automation Beihang University Beijing China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong SAR China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Chinese Academy of Science

Path planning is a core problem of the mobile robot navigation technology. However, few path plan methods that have been proposed consider the path smoothness and the robot attitude in the path. In this paper, a novel path planning method is proposed which considers three optimizing targets, including the path length, the path smoothness and the distance between the path and the obstacles. Firstly, a localization method which the path planning method relies on is explained. Secondly, a path planning model considering the path smoothness and the robot posture is discussed in detail. Thirdly, a solution based on particle swarm optimization (PSO) algorithm is discussed. Fourthly, simulation results are shown and analyzed. At last, conclusion and future work are provided.

关键词： Robot kinematics Path planning Sonar Planning Cameras Robot vision systems

来源：评论

学校读者我要写书评

暂无评论

A robotic holder of transcranial doppler probe for CBFV auto-searching

A robotic holder of transcranial doppler probe for CBFV auto...

引用

International Conference on Information and automation (ICIA)

作者： Quanli Qiu Xiaoping Yang Jia Liu Pandeng Zhang Xinyu Wu Guangdong Provincial Key Laboratory of Robotics and Intelligent System Chinese Academy of Sciences Shenzhen Guangdong China Key Lab of Advanced Manufacturing Technology Harbin Institute of Technology China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong SAR China

ISBN: (纸本)9781479913329

The operational difficulty of Transcranial Doppler (TCD) limits its use in normal clinical settings. We therefore present a robotic arm consists of five degrees of freedom which are achieved by four motors and one extra flexible spring, to assure appropriate pressure on temporal window. With proper control strategies, the robotic arm can move the TCD probe to automatically search temporal window positions. In this paper, we have developed the first full-automatic ambulatory TCD system, evaluated its reliability and efficiency after many experiments. In view of the validation of the instrument in successful experiments, this probe holder is likely to have great impact on future TCD examination.

关键词： Probes DC motors Robots Equations Mathematical model Force Arteries

来源：评论

学校读者我要写书评

暂无评论

HOUSEHOLD SERVICE ROBOT WITH CELLPHONE INTERFACE

引用

International Journal of Information Acquisition 2013年第2期9卷

作者： LONG HAN XINYU WU YONGSHENG OU YEN-LUN CHEN CHUNJIE CHEN YANGSHENG XU Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong

In this paper, an efficient and low-cost cellphone-commandable mobile manipulation system is described. Aiming at house and elderly caring, this system can be easily commanded through common cellphone network to efficiently grasp objects in household environment, utilizing several low-cost off-the-shelf devices. Unlike the visual servo technology using high quality vision system with high cost, the household-service robot may not afford to such high quality vision servo system, and thus it is essential to use some of low-cost device. However, it is extremely challenging to have the said vision for precise localization, as well as motion control. To tackle this challenge, we developed a realtime vision system with which a reliable grasping algorithm combining machine vision, robotic kinematics and motor control technology is presented. After the target is captured by the arm camera, the arm camera keeps tracking the target while the arm keeps stretching until the end effector reaches the target. However, if the target is not captured by the arm camera, the arm will take a move to help the arm camera capture the target under the guidance of the head camera. This algorithm is implemented on two robot systems: the one with a fixed base and another with a mobile base. The results demonstrated the feasibility and efficiency of the algorithm and system we developed, and the study shown in this paper is of significance in developing a service robot in modern household environment.

关键词： Service robotics robot interface mobile manipulation grasping

来源：评论

学校读者我要写书评

暂无评论

Study of intercept action algorithm based on the radius regulation on a fixed point in robot soccer

引用

Harbin Gongye Daxue Xuebao/Journal of Harbin Institute of Technology 2010年第SUPPL. 2期42卷 141-144页

作者： Luo, Yuan Song, Zhuo-Xi Li, Min Shu, Fan Ou, Xing-Chao Intelligent System and Robotics Institute Chongqing University of Posts and Telecommunications Chongqing 400065 China Automation Department College of Mobile Telecommunications Chongqing University of Posts and Telecom Chongqing 400065 China School of Automation Chongqing University of Posts and Telecommunications Chongqing 400065 China

The efficiency of the interception plays a crucial role in the process and the result of the soccer match in the FIRA World Cup. Nowadays, there exist some algorithms on how to grip the rolling ball. However, among them some weak points are clear. For example, the player would waste more time to search the goal, but sometimes it can not capture the ball in time. To solve these questions, we have been studying the match and get a new control method of soccer robot, which can predict the time and the exact place of the ball by regulating the radius of the circle. And after using this algorithm, the crucial players, such as the striker, act accurately and flexibly and can intercept the ball high-efficiency. The simulation experiment proves that this algorithm has satisfying effect on intercepting.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

A Study On Iterative Learning Control With Adjustment Of Learning Interval For Monotone Convergence In The Sense Of Sup-Norm

引用

Asian Journal of Control 2008年第1期4卷

作者： Kwang-Hyun Park Zeungnam Bien Division of EE Department of EECS Korea Advanced Institute of Science and Technology 373–1 Kusong-dong Yusong-gu Taejon 305–701 Korea. Zeungname Bien:received the B.S. degree in electronics engineering from Seoul National University Seoul Korea in 1969 and the M.S. and Ph.D. degrees in electrical engineering from the University of Iowa Iowa City Iowa U.S.A. in 1972 and 1975 respectively. During 1976–1977 academic years he taught as assistant professor at the Department of Electrical Engineering University of Iowa. Then Dr. Bien joined Korea Advanced Institute of Science and Technology summer 1977 and is now Professor of Control Engineering at the Department of Electrical Engineering and Computer Science KAIST. Dr. Bien was the president of the Korea Fuzzy Logic and Intelligent Systems Society during 1990–1995 and also the general chair of IFSA World Congress 1993 and for FUZZ-IEEE99 respectively. He is currently co-Editor-in-Chief for International Journal of Fuzzy Systems (IJFS) Associate Editor for IEEE Transactions on Fuzzy Systems and a regional editor for the International Journal of Intelligent Automation and Soft Computing. He has been serving as Vice President for IFSA since 1997 and is now Chief Chairman of Institute of Electronics Engineers of Korea and Director of Humanfriendly Welfare Robot System Research Center. His current research interests include intelligent control methods with emphasis on fuzzy logic systems service robotics and rehabilitation engineering and large-scale industrial control systems. Kwang-Hyun Park:received the B.S. M.S. and Ph.D. degrees in electrical engineering and computer science from KAIST Korea in 1994 19997 and 2001 respectively. He is now a researcher at Human-friendly Welfare Robot System Research Center. His research interests include learning control machine learning human-friendly interfaces and service robotics.

It has been found that some huge overshoot in the sense of sup-norm may be observed when typical iterative learning control (ILC) algorithms are applied to LTI systems, even though monotone convergence in the sense of λ-norm is guaranteed. In this paper, a new ILC algorithm with adjustment of learning interval is proposed to resolve such an undesirable phenomenon, and it is shown that the output error can be monotonically converged to zero in the sense of sup-norm when the proposed ILC algorithm is applied. A numerical example is given to show the effectiveness of the proposed algorithm.

关键词： Iterative learning control monotone convergence learning interval sup-norm

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：