检索结果-内蒙古大学图书馆

International Conference on Neural Networks

作者： S.G. Tzafestas P.A. Prokopiou C.S. Tzafestas Intelligent Robotics and Automation Laboratory Department of Computer Engineering National and Technical University of Athens Athens Greece Laboratoire de Robotique de Paris CNRS UPMC UVSQ Velizy France

In this paper the control problem of telemanipulators is considered under the condition that they are subject to modeling and other uncertainties of considerable levels. The design is based on the S. Lee and H.S. Lee teleoperator control scheme (1993, 1994), which is modified so as to be able to compensate the uncertainties, and is implemented using a partitioned multilayer perceptron neural network. Several subnetworks are used each one identifying a term of the manipulator's dynamic model. A new learning algorithm is proposed which distributes the learning error to each subnetwork and enables online training. Several simulation results are provided, which show the robustness ability by the partitioned neurocontroller, and compare it with the results obtained through sliding mode control.

关键词： Robust control Neural networks Uncertainty Teleoperators Multilayer perceptrons Multi-layer neural network Manipulator dynamics Partitioning algorithms Neurocontrollers Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Telemanipulator neurocontrol using multiple RBF networks

Telemanipulator neurocontrol using multiple RBF networks

引用

IEEE International Symposium on Intelligent Control (ISIC)

作者： S.G. Tzafestas P.A. Prokopiou C.S. Tzafestas Intelligent Robotics and Automation Laboratory Department of Electrical and Computer Engineering National and Technical University of Athens Athens Greece Laboratoire de Robotique de Paris CNRS UPMC UVSQ France

This paper addresses the control problem of masterslave systems which involve severe modeling errors and other high-level uncertainties, using neural networks. The solution approach is based on a recent teleoperator control scheme of S. Lee and H.S. Lee (1993, 1994), which is suitably enhanced such that to become capable of compensating the uncertainties. The class of radial-basis functions (RBF) neural networks are employed in a multipartitioned neural network architecture, and a special learning scheme is adopted which distributes the learning error to each subnetwork and allows online learning. The effectiveness of the present RBF neurocontroller was investigated through extensive simulation and compared to that of MLP (multilayer perceptron) neurocontroller and a robust sliding-mode controller representative.

关键词： Radial basis function networks Robot kinematics Error correction Neural networks Teleoperators Master-slave Uncertainty Delay effects robotics and automation Neurocontrollers

来源：评论

学校读者我要写书评

暂无评论

Fuzzy identifier based inverse dynamics control for a 3-DOF articulated manipulator

Fuzzy identifier based inverse dynamics control for a 3-DOF ...

引用

International Conference on Industrial Electronics, Control and Instrumentation

作者： K. Erbatur O. Kaynak I. Rudas Robotics and Automation Group TUBITAK Marmara Research Centre Kocaeli Turkey Faculty of Engineering National University of Singapore Singapore Department of Information Technology Banki Donat Polytechnic Budapest Hungary

A method using fuzzy logic and neural network structures for the identification and control of robot dynamics is presented in this paper. Fuzzy identifiers are employed to match the effects in the robot dynamics model. Fuzzy logic systems used are represented as three-layer feedforward neural networks. Fuzzy system parameters are adjusted via backpropagation. An on-line tuning algorithm is employed. Simulation results obtained with a three degrees of freedom articulated arm are given.

关键词： Manipulator dynamics Fuzzy control Fuzzy systems Neural networks Fuzzy logic Service robots Feedforward systems Feedforward neural networks Automatic control robotics and automation

来源：评论

学校读者我要写书评

暂无评论

The active kinematic histogram method for path planning of non-point, non-holonomically constrainted mobile robots

引用

Advanced robotics 1997年第4期12卷 373-395页

作者： Katevas, Nikos I. Tzafestas, Spyros G. Zenon SA - Industrial Automation Athens 15344 Kanari 5 Greece Intelligent Robotics and Automation Laboratory Department of Electrical and Computer Engineering National Technical University of Athens Athens 15773 Zografou Campus Greece

The paper presents a novel path planning method for non-point, non-holonomically constrainted mobile robots. The proposed method, named the Active Kinematic Histogram (AKH) method, is a potential field path-planning method based on the Vector Field Histogram (VFH) method introducedby J. Borenstein and Y. Koren. The method relies on one-dimensional environment representations named AKHs, derived from the available information on the obstacle space and the robot itself. The AKHs provide the information abstraction required for fast, collision-free and kinematically feasiblepath planning for non-point, non-holonomically constrainted mobile robots. The method constructs two AKH structures incorporating the information stored in occupancy grid environment representations as well as the exact robot's size, shape and kinematic features. The method applies simpleand fast procedures, e.g. histogram shifting, in order to determine kinematic feasibility and the result of the robot's steering limits. Being a potential field method, the AKH method uses adaptive thresholding procedures to reduce the inherited drawback of the local minima traps ***, the method proposes specific updating and coding procedures for the environmental information and introduces the Ageing function to insert time parameterization in the path-planning results. Also, the so-called bicycle kinematic model is presented in order to describe the kinematicfamily of mobile robots suitable for applying the AKH method. The method integrates a velocity control procedure which is also based on information provided by the active kinematic histograms. The method produced smooth, collision-free paths in a variety of experimental configurations. Simulationand experimental results are presented. © VSP and robotics Society of Japan 1997.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hamilton-Jacobi-Bellman optimal design of functional link neural network controller for robot manipulators

Hamilton-Jacobi-Bellman optimal design of functional link ne...

引用

IEEE Conference on Decision and Control

作者： Y.H. Kim F.L. Lewis D.M. Dawson Automation and Robotics-Research Institute University of Texas Arlington South Fort Worth TX USA Center for Advanced Manufacturing Department of Electrical and Computer Engineering Clemson University Clemson SC USA

The paper is concerned with the application of quadratic optimization for motion control to feedback control of robotic systems using neural networks. Explicit solutions to the Hamilton-Jacobi-Bellman (HJB) equation for optimal control of robotic systems are found by solving an algebraic Riccati equation. It is shown how neural networks can cope with nonlinearities through optimization with no preliminary off-line learning phase required. The adaptive learning algorithm is derived from Lyapunov stability analysis, so that both system tracking stability and error convergence can be guaranteed in the closed-loop system. The filtered tracking error or critic gain and the Lyapunov function for the nonlinear analysis are derived from the user input in terms of a specified quadratic performance index. Simulation results on a two-link robot manipulator show the satisfactory performance of the proposed control schemes even in the presence of large modeling uncertainties and external disturbances.

关键词： Robots Riccati equations Neural networks Nonlinear equations Lyapunov method Performance analysis Motion control Feedback control Optimal control Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Hybrid closed loop systems: a nonlinear control perspective

Hybrid closed loop systems: a nonlinear control perspective

引用

IEEE Conference on Decision and Control

作者： N.H. McClamroch C. Rui I. Kolmanobsky M. Reyhanoglu Department of AeroSpace Engineering University of Michigan Ann Arbor MI USA University of Michigan Ann Arbor MI US Automation Robotics Technology Texas State Technical College Sweetwater TX USA

A survey of hybrid closed loop control problems that arise from the use of hybrid controllers to control smooth nonlinear systems is presented. This is a special class of hybrid closed loop systems, but they are of substantial interest in identifying the value of hybrid control as a generalization of classical control approaches for nonlinear systems.

关键词： Closed loop systems Nonlinear control systems Control systems Nonlinear systems Automatic control Adaptive control robotics and automation Books Educational institutions Feedback

来源：评论

学校读者我要写书评

暂无评论

Growing region technique in the detection of autonomous structures within X-ray radiographs

Growing region technique in the detection of autonomous stru...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： S.N. Raptis S.G. Tzafestas S. Pavlopoulos D. Koutsouris S. Kollias Intelligent Robotics and Automation Laboratory National and Technical University of Athens Athens Greece Biomedical Engineering Laboratory National and Technical University of Athens Athens Greece Department of Electrical & Computer Engineering National and Technical University of Athens Athens Greece

Nodule identification is a major issue in chest radiography and cancer prevention and detection. The recognition of cancer nodule characteristics in chest radiographs is a key point to the detection procedure. The method described here is based on the extraction of the major geometrical as well as luminance characteristics that make nodule recognizable and easy to detect. The purpose of the proposed method is to detect within a given block of chest X-ray image any homogeneous and autonomous mass that might means the existence of a nodule or some structure within it. The idea of pixels of interest is introduced which makes the growing a finite steps procedure. The growing of the region around a given point is realized gradually in a finite number of iterations at each one of which a set of criteria is evaluated. These criteria are established in a prior training procedure.

关键词： X-ray detection X-ray detectors X-ray imaging Diagnostic radiography Pixel Laboratories Biomedical engineering Cancer detection Character recognition Shape

来源：评论

学校读者我要写书评

暂无评论

Nonsmooth stabilization of an underactuated unstable two degrees of freedom mechanical system

Nonsmooth stabilization of an underactuated unstable two deg...

引用

IEEE Conference on Decision and Control

作者： C. Rui M. Reyhanoglu I. Kolmanovsky S. Cho N.H. McClamroch Department of AeroSpace Engineering University of Michigan Ann Arbor MI USA Automation/Robotics Technology Texas State Technical College Sweetwater TX USA Ford Motor Company Limited Dearborn MI USA

This paper studies a specific mechanical example that is representative of a class of underactuated, weakly coupled, unstable mechanical systems that are exceptionally difficult to stabilize. In particular, systems in this class are not stabilizable using static smooth feedback but are stabilizable using nonsmooth feedback. Although similar purely theoretical developments have been previously presented, we emphasize the physical basis and physical implications of the theoretical conclusions in the context of a specific example. The development in this paper is limited to a specific physical example, but the approach is applicable to a wide class of underactuated, weakly coupled, unstable mechanical systems.

关键词： Mechanical systems Springs Feedback Force control Weight control Couplings Control systems Equations robotics and automation Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Neural Fault Detection and Accommodation for Interconnected Power Systems

引用

IFAC Proceedings Volumes 1997年第18期30卷 943-947页

作者： Spyros Tzafestas Yiannis Anthopoulos Efthimios Kyriannakis Intelligent Robotics and Automation Laboratory Department of Electrical and Computer Engineering National Technical University of Athens Zographou 15773 Athens Greece. Tel: +30-1-7722489 +30-1-772-1527 Fax: +30-1-7722490 +30-1-7722459

Due to increasing safety and reliability demands fault detection and accommodation is a key issue in the design of industrial control systems. This paper presents a neural network based method for fault detection and accommodation, appropriate for interconnected power systems. The simulation results show that the method is very promising.

关键词： fault detection neural networks interconnected systems

来源：评论

学校读者我要写书评

暂无评论

Analysis of deadlocks and circular waits using a matrix model for discrete event systems

Analysis of deadlocks and circular waits using a matrix mode...

引用

IEEE Conference on Decision and Control

作者： F.L. Lewis S. Bogdan A. Gurel O. Pastravanu Automation and Robotics Research Institute University of Texas Arlington Worth TX USA Faculty of Electrical Engineering and Computer University of Zagreb Zagreb Croatia Department Automatic Control and Ind. Inf Polytechnic Institute Iasi Romania

A new matrix rule-based model of discrete-part discrete event systems is given that, together with the well-known Petri net marking transition equation, yields a complete matrix-based dynamical description of these systems. In this application to deadlock analysis, the exact relations between circular blockings and deadlocks are given for a large class of reentrant flow lines. Explicit matrix equations are given for online dynamic deadlock analysis in terms of circular blockings, and certain 'critical siphons' and 'critical subsystems'. This allows efficient dispatching with deadlock avoidance using a generalized kanban scheme. For the class of flow lines considered, the existence of matrix formulae shows that deadlock analysis is not NP-complete, but of polynomial complexity.

关键词： System recovery Discrete event systems Equations Dispatching robotics and automation Petri nets Manufacturing Bills of materials Assembly Lifting equipment

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：