检索结果-内蒙古大学图书馆

Time-delay neural networks for control

IFAC Proceedings Volumes 1994年第14期27卷 967-972页

作者： M. Kaiser University of Karlsruhe Department of Computer Science Institute for Real-Time Computer Systems & Robotics Prof. Dr.-Ing. U. Rembold and Prof. Dr.-Ing. R. Dillmann D-76128 Karlsruhe Germany

This paper presents results regarding the Application of Time-Delay Neural Networks (TDNNs), up to now mainly used in speech recognition, for control tasks. A set of examples taken from a model-based robot controller is used to validate the suitability of the TDNN and to show its superiority to standard multilayer perceptrons. Afterwards, a new algorithm is presented that shows how the inherent capability of the TDNN to deal with time-variant signals can be employed to directly generate a TDNN from a PID control law. This synthesized neural controller is operational from the very beginning and can be tuned on-line using existing learning techniques. The advantages of this design procedure are shown for a simple control task.

关键词： Neural nets control system design control system synthesis adaptive control knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

APPLICATIONS OF FUZZY-LOGIC CONTROL IN AUTONOMOUS ROBOT systems

引用

INTERNATIONAL JOURNAL OF systems science 1993年第10期24卷 1885-1904页

作者： ZHANG, JW Institute for Real-Time Computer Systems and Robotics Department of Computer Science University of Karlsruhe Karlsruhe Germany

The development of autonomous robots involves the imitation of human decision-making abilities with the aid of diverse sensor information. Fuzzy logic, which is based on fuzzy modelling and approximate reasoning, can be applied in different levels of control tasks. We first present the research results of applying fuzzy logic control in the motion execution of mobile systems and sensor-guided fine-motion of a manipulator. To realize real-time 'reactive' control, suitable hardware which supports the acceleration of fuzzy inference should be developed. The design and development of a VME-bus compatible fuzzy co-processor is also described.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

ORIENTING POLYGONAL PARTS WITHOUT SENSORS

引用

ALGORITHMICA 1993年第2-4期10卷 201-225页

作者： GOLDBERG, KY 1. Institute for Robotics and Intelligent Systems Computer Science Department University of Southern California 90089-0273 Los Angeles CA USA

In manufacturing it is often necessary to orient parts prior to packing or assembly. We say that a planar part is polygonal if its convex hull is a polygon. We consider the following problem: given a list of n vertices describing a polygonal part whose initial orientation is unknown, find the shortest sequence of mechanical gripper actions that is guaranteed to orient the part up to symmetry in its convex hull. We show that such a sequence exists for any polygonal part by giving an O(n2 log n) algorithm for finding the sequence. Since the gripper actions do not require feedback, this result implies that any polygonal part can be oriented without sensors.

关键词： robotics PARTS FEEDING PLANNING GRASPING COMPLIANCE MOTION PLANNING WITH UNCERTAINTY COMPLIANT MOTION PLANNING

来源：评论

学校读者我要写书评

暂无评论

TASK DECOMPOSITION AND COMPETING expert-SYSTEM - ARTIFICIAL NEURAL-NET OBJECTS FOR RELIABLE AND REAL-TIME INFERENCE

TASK DECOMPOSITION AND COMPETING EXPERT-SYSTEM - ARTIFICIAL ...

引用

1993 IEEE INTERNATIONAL CONF ON NEURAL NETWORKS / 2ND INTERNATIONAL CONF ON FUZZY systems

作者： KHOSLA, R DILLON, T Expert and Intelligent Systems Laboratory Applied Computing Research Institute Department of Computer Science and Computer Engineering La Trobe University Bundoora 3083 VIC Australia

ISBN: (纸本)0780309995

The properties of Artificial Neural Networks(ANNs) like massive parallelism, generalization make them amenable for application in various diagnostic/time-critical problem domains including alarm processing in power systems. However, enormous size of power systems haB inhibited real time use of ANNs. In this paper, we apply an integrated model for real time alarm processing in a real world terminal power station. The integrated model is a combination of a generic neuro-expert system model, object model, and unix operating system process(UOSP) model. We show how the massive parallelism and fast execution features of ANNs help us to cope with real-time system constraints like data variability and fast response time. For further enhancing reliability we propose a practical use of competing ES-ANN objects. © 1993 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

PERFORMANCE OF A PRIORITIZED ON-BOARD BASEBAND SWITCH FOR A MULTISERVICE MULTIBEAM SATELLITE

引用

INTERNATIONAL JOURNAL OF SATELLITE COMMUNICATIONS 1994年第3期12卷 283-297页

作者： BOHM, S ELHAKEEM, AK HACHICHA, M Department of Electrical and Computer Engineering Concordia University 1455 De Maisonneuve Blvd. West Montreal H3A 1M8 Canada Was born in Montreal Canada on 14 September 1966. He received the B. Eng. degree in electrical engineering from Concordia University Montreal Canada in 1989. He is at present completing the M.A.Sc. degree in electrical engineering at Concordia University. (S'75–S'79–M'79–SM'86) received the Ph.D. degree from Southern Methodist University Dallas TX in 1979. He spent the next two years working as a Visiting Professor in Egypt after which he moved to Ottawa Canada in 1982. He assumed teaching and research positions in Carleton and Manitoba Univerities and later moved to Concordia University Montreal Canada in 1983 where he is now a Professor in the Electrical and Computer Engineering Department. He has published numerous papers in IEEE and international journals in the areas of spread spectrum and networking. He is a well-known expert in these areas and serves as a consultant to many companies. His current research interests include wide-band metropolitan networks switching architectures and performance of on-board multibeam satellites acquisitionless CDMA networks code distribution and orthogonalization of CDMA signals responsive congestion control for ATM-based networks ARQ techniques and investigation of the novel SUGAR CDMA systems in fading channels. Dr. Elhakeem is a Senior Member of the Canadian Electrical Engineering Society and Armed Forces Association. He has chaired numerous technical sessions in IEEE Conferences was the Technical Program Chairman for IEEE Montech 1986 Montreal Canada. Dr. Elhakeem is the key guest editor of theIEEE Journal of Selected Areas in Communicationsfor the May June issues 1993 covering CDMA networks. Advanced Technology & Networks VISTAR Telecommunications Inc. Ottawa Ontario K1G 3J4 Canada An Associate Director of Advanced Technology & Networks Group VISTAR Telecommunications Inc. Ottawa Canada. He is also an Adjunct Pr

In this paper, we study the performance of a prioritized on-board baseband switch in conjunction with a multibeam satellite handling integrated services. The services considered for the analysis include voice, video, file transfer and interactive data. The prioritized switch uses both input and output buffering, switch speed-up as well as a two-phase head-of-line resolution algorithm, in order to reduce the buffer loss while maintaining acceptable user delays. The minimum required buffer capacity and switch speed-up for each service in a prioritized environment are found under uniform traffic conditions. It is shown that under uniform traffic conditions, only minimal buffering and switch speed-up are needed even for the lowest priority users. The performance dependence on the switch size is also substantially reduced with head of line resolution and buffering even in a prioritized environment.

关键词： SWITCH ON-BOARD BASEBAND MULTIBEAM PRIORITIZED HEAD-OF-LINE UNIFORM LOAD SPEED-UP

来源：评论

学校读者我要写书评

暂无评论

An asynchronous neural network model for the shortest path problem

An asynchronous neural network model for the shortest path p...

引用

IEEE International Conference on Neural Networks, ICNN 1993

作者： Zhao, Songhe Dillon, T.S. Expert and Intelligent Systems Laboratory Applied Computing Research Institute Department of Computer Science and Computer Engineering La Trobe University BundooraVIC3083 Australia Northern Jiao-tong University Beijing China

ISBN: (纸本)0780309995

Researchers have shown that the neural network models can be used to find solutions for many optimization problems. Most of these models are energy based models and there is no guarantee the network converges to a global optimal solution. In this paper, we propose a new neural shortest path network model which no special convergence procedure needs to be performed. The network can work in purely an asynchronous mode and guarantees to reach the global optimal solution. © 1993 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

A fuzzy control approach for executing subgoal guided motion of a mobile robot in a partially-known environment

A fuzzy control approach for executing subgoal guided motion...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： J. Zhang P. Bohner Institute for Real-Time Computer Systems and Robotics Department of Computer Science University of Karlsruhe Germany

A fuzzy control approach is proposed for controlling a mobile robot by effectively using the static knowledge of a partially-known environment and the dynamic sensor data. To describe the global structure of the static environment, a tangent-graph is first constructed and a sequence of subgoals is generated for guiding the global path direction. During the execution of these subgoals, a motion executor using the concept of fuzzy control evaluates the sensor data and the robot current status, and adjusts the moving speed and direction of the robot.< >

关键词： Fuzzy control Mobile robots Robot sensing systems Path planning Control systems Humans Motion control Robot control Roads Robot motion

来源：评论

学校读者我要写书评

暂无评论

The Control Architecture of the Mobile System Priamos

引用

IFAC Proceedings Volumes 1993年第1期26卷 391-396页

作者： R. Dillmann J. Kreuziger F. Wallner University of Karlsruhe Department of Computer Science Institute for Real-Time Computer Control Systems & Robotics P.O. Box 6980. 7500 Karlsruhhe 1 Germany

In this paper the control architecture of the mobile robot system PRIAMOS is presented. It consists of four layers which integrate reactive and reflexive components in such a way that the robot can combine fast reaction to unexpected obstacles with predictive behaviour to known components in the environnement. A solution for the problem bow to combine control layers which process information on different levels of abstraction and of increasing complexity is discussed. The reflexive part of the control architecture and the modification concerning the motion controller of the mobile robot which was necessary to apply the idea of reflexive navigation is described in more details. The architecture presented allows to execute motion tasks in partially unknown or changing environment in an efficient manner. Especially the time critical reflexive level is computationally less expensive than previous approaches

关键词： Intelligent machines navigation hierarchically intelligent control architecture obstacle avoidance robots sensors

来源：评论

学校读者我要写书评

暂无评论

Grasp recognition strategies from empirical models

Grasp recognition strategies from empirical models

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： D. Kang K.Y. Goldberg Institute for Robotics and Intelligent Systems Computer Science Department University of Southern California Los Angeles CA USA

A method for recognizing a part from a set of known parts using a parallel-jaw gripper and a simple sensor that measures the distance between the jaws is described. The authors consider how empirical measurements of part behavior can be used to generate efficient recognition strategies. These strategies are compared to random strategies using physical experiments. It is found that the former cut error rates and recognition times by approximately 50%.< >

关键词： Grippers Shape Noise measurement Intelligent robots Intelligent sensors Sensor systems Virtual manufacturing Strategic planning Solid modeling Manufacturing automation

来源：评论

学校读者我要写书评

暂无评论

Task decomposition and competing expert system-artificial neural net objects for reliable and real time inference

Task decomposition and competing expert system-artificial ne...

引用

International Conference on Neural Networks

作者： R. Khosla T.S. Dillon Expert and Intelligent Systems Laboratory Applied Computing Research Institute and Department of Computer Science and Computer Engineering La Trobe University Bundoora VIC Australia

An integrated model for real time alarm processing in a real world terminal power station is applied. The integrated model is a combination of a generic neuro-expert system model, object model, and UNIX operating system process (UOSP) model. It is shown how the massive parallelism and fast execution features of ANNs help to cope with real-time system constraints like data variability and fast response time. For further enhancing reliability, a practical use of competing expert system-artificial neural networks (ES-ANN) objects is proposed.< >

关键词： Neural networks Power system modeling Electronic switching systems Real time systems Artificial neural networks computer network reliability Power system reliability computer networks Concurrent computing Power engineering computing

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：