检索结果-内蒙古大学图书馆

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： T. Shibata T. Fukuda K. Tanie Bio-Roboucs Division Robotics Department Mechanical Engineering Laboratory Tsukuba Ibaraki Japan Department of Mechano-Informatics and Systems University of Nagoya Nagoya Japan

A new strategy for motion planning is proposed. The strategy applies a genetic algorithm (GA) to optimize the motion planning. To evaluate the planned motion, the strategy also applies fuzzy logic to a fitness function. The fitness function is referred to as Fuzzy Critic. The Fuzzy Critic evaluates plans as populations in the GA with respect to multiple factors. Depending on the goals of the tasks, human operators can easily determine inference rules in the Fuzzy Critic because of the fuzzy logic. The strategy determines a path for a mobile robot which moves from a starting point to a goal point, while avoiding obstacles in a work space and picking up loads on the way. Simulation illustrates the effectiveness of the proposed strategy.< >

关键词： Genetic algorithms Motion planning Intelligent robots Fuzzy logic Humans Orbital robotics Strategic planning Robot kinematics Neural networks Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Auto fuzzy tuning having minimum structure by using genetic algorithm and delta rule

Auto fuzzy tuning having minimum structure by using genetic ...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： T. Fukuda H. Ishigami T. Shibata F. Arai Department of Mechano-Informatics and Systems University of Nagoya Nagoya Japan Shin-Nagoya Thermal Power Station Cyubu Electric Power Company Inc. Nagoya Japan Bio-Robotics Division Robotics Department MITI Mechanical Engineering Laboratory Tsukuba Japan

An auto tuning algorithm of fuzzy inference for Fuzzy neural networks using the genetic algorithm and the delta rule is presented. Some auto-tuning methods are proposed to reduce time-consuming operations by human experts. This tuning method brings the minimal and optimal structure of the fuzzy model. Two types of the fuzzy model are prepared, whose membership functions on the antecedent part consist of triangular and Gaussian type, respectively. The effectiveness of the proposed methods compared with the former methods is shown by simulation. The proposed method has the potential to be applied to robotic motion control, sensing and recognition problems.< >

关键词： Genetic algorithms Humans Fuzzy systems Convergence Fuzzy neural networks Control systems Optimization methods Thermal engineering Power generation Mechanical engineering

来源：评论

学校读者我要写书评

暂无评论

Dynamic memory by recurrent neural network and its learning by genetic algorithm

Dynamic memory by recurrent neural network and its learning ...

引用

IEEE Conference on Decision and Control

作者： T. Fukuda T. Kohno T. Shibata Department of Mechano-Informatics and Systems University of Nagoya Nagoya Japan Dept. of Mechano-Inform. & Syst. Nagoya Univ. Japan Bio-Robotics Division Robotics Department Mechanical Engineering Laboratory M.I.T.I. Tsukuba Japan

Recurrent neural networks have dynamic characteristics and can express functions of time. The recurrent neural networks can be applied to memorize robotic motions, i.e. trajectory of a manipulator. For this purpose, it is necessary to determine appropriate interconnection weights of the network. Formerly, learning algorithms based on gradient search techniques have been shown. However, it is difficult for the recurrent neural network to learn such functions while using previous approaches because of much computing requirement and limitation of memory. This paper presents a new learning scheme for the recurrent neural networks by genetic algorithm (GA). The GA is applied to determine interconnection weights of the recurrent neural networks. The GA approach is compared with the backpropagation through time which is a famous learning algorithm for the recurrent neural networks. Simulations illustrate the performance of the proposed approach.< >

关键词： Recurrent neural networks Genetic algorithms Neural networks Multi-layer neural network Neurons Feedforward neural networks Cost function Feedforward systems Robots Mechanical engineering

来源：评论

学校读者我要写书评

暂无评论

Study on Model-Based Control of the Cable-Conduit Drive System

引用

Journal of robotics and Mechatronics 1993年第1期5卷 53-59页

作者： Sugano, Shigeki Matsumoto, Osamu Muto, Shin-Yo Department of Mechanical Engineering Waseda University 3-4-1 Ohkubo Shinjuku-ku Tokyo169 Japan Robotics Department of Mechanical Engineering Laboratory of MITI 1-2 Namiki Ibaraki Tsukuba305 Japan NIT Human Interface Laboratories Autonomous Robot Systems Laboratory 3-9-11 Midori-cho Musashino Tokyo180 Japan

The cable-conduit system, one of the remote drive system, is advantageous for integrating multiple-degrees of freedom. However, from the perspective of accurate motion control, a difference is caused between the actuator motion and the joint motion because a considerable friction between the cable and the conduit which varies according to the change in cable route. Therefore, the behaviors of cable must be clarified in order to realize highly accurate motion control. The objective of this study is to clarify the relationship between the actuator motion and the joint motion and to establish the motion control technique of the cable-conduit system. The present paper discusses the model-based control of the cable system. First, we modelled the cable-conduit system using the bend angles and the number of roots and crests of cable. Next, for precisely expressing the behaviors during start-up, we formulated the relationship between the actuator torque and the joint motion in consideration of the static friction and the kinetic friction. In addition, we verified the effectiveness of this formula through an experiment. As a result of the verification experiment, the motion computed from the formula strictly coincided with the actual behavior, thus displaying the effectiveness of the model. © 1993 the authors.

关键词： Cables

来源：评论

学校读者我要写书评

暂无评论

Heuristic learning by genetic algorithm for recurrent neural network

Heuristic learning by genetic algorithm for recurrent neural...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： T. Fukuda T. Kohno T. Shibata Department of Mechano-Infomatics and Systems University of Nagoya Nagoya Aichi Japan Nagoya Daigaku Nagoya Aichi JP Dept. of Mechano-Inf. & Syst. Nagoya Univ. Japan Bio-Robotics Division Robotics Department Mechanical Engineering Laboratory Ministry of International Trade and Industry Tsukuba Ibaraki Japan

Recurrent neural networks have dynamic characteristics and express functions of time. Recurrent neural networks can memorize robotic motions, i.e., trajectories of manipulators For this purpose, it is necessary to determine appropriate interconnection weights of the network. A new learning scheme for the recurrent neural networks by genetic algorithm (GA) is presented. The GA is applied to determine interconnection weights of the recurrent neural networks. The proposed approach is compared with backpropagation through time for recurrent neural networks. Simulation illustrates the performance of the proposed approach.< >

关键词： Genetic algorithms Recurrent neural networks Neural networks Multi-layer neural network Neurons Cost function Electronic mail Feedforward neural networks Robot motion Manipulators

来源：评论

学校读者我要写书评

暂无评论

SENSITIVITY OF FRONT-FACE WELD GEOMETRY IN REPRESENTING THE FULL PENETRATION

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF engineering MANUFACTURE 1992年第3期206卷 191-197页

作者： ZHANG, YM KOVACEVIC, R WU, L National Laboratory for Welding Harbin Institute of Technology Harbin People's Republic of China Center for Robotics and Manufacturing Systems and Department of Mechanical Engineering University of Kentucky USA

The measurement of weld penetration using a front-face sensor has been an important issue in welding automation. The fundamental problem is to find a measurable front-face parameter that can adequately represent the weld penetration. In this paper, both the front-face average weld depression depth (a novel weld geometrical parameter) and the weld width are selected as possible representations of full penetration in GTA welding. Two types of sensitivities of front-face weld geometry, with respect to variations in welding conditions and with respect to control variables, are proposed as criteria for determination of promising parameters. Sensitivity calculation of experimental data shows that the front-face weld width is not promising while the average front-face weld depression depth is. This conclusion is also confirmed by a specific experiment and statistic models.

关键词： Welds

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT DISTANCE COMPUTATION USING BEST ELLIPSOID FIT

EFFICIENT DISTANCE COMPUTATION USING BEST ELLIPSOID FIT

引用

1992 IEEE INTERNATIONAL SYMP ON INTELLIGENT CONTROL

作者： RIMON, E BOYD, SP Robotics Laboratory Stanford University Department of Computer Science United States Information Systems Laboratory Stanford University Department of Electrical Engineering United States

ISBN: (纸本)0780305469

Knowledge of the distance between a robot and its surrounding environment is vital for any robotic system. The robot must obtain this information rapidly in order to plan and react in real-time. Our technique first surrounds the robot links and the obstacles by optimal ellipsoids, and then computes the clearance of the links from the obstacles with a generalized distance function. This approach offers an attractive alternative to the widely used technique of computing the distance via polyhedral representation of the robot and the obstacles. In particular, our approach offers a drastic reduction in the complexity of the data structures: each polyhedron, typically represented by a list of its features and their adjacency graph;is replaced by a minimum-volume ellipsoid represented by its center and a symmetric matrix whose dimension is either two or three (the workspace dimension). Moreover, while the computation time of the distance between polyhedra is often a function of their geometrical complexity, computation time in the ellipsoidal case is essentially constant;and becomes even more rapid when it is computed repeatedly along the robot's trajectory. Our method consists of the following two algorithms: The first computes the optimal ellipsoid surrounding a convex polyhedron. The second is an analytic formula for the free margin about one ellipsoid with respect to another, that is computed as a standard eigenvalue problem. An efficient incremental version of the latter algorithm is then proposed. This system has been implemented and preliminary simulation results are provided throughout the paper. © 1992 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

A transputer based laser scanning system

A transputer based laser scanning system

引用

1992 Singapore International Conference on Intelligent Control and Instrumentation

作者： Tewkesbury, G. Harrison, D.J. Sanders, D.A. Billingsley, J. Hollis, J.E.L. Automation and Robotics Research Laboratory School of Systems Engineering Portsmouth Polytechnic Anglesea Road PortsmouthPO1 3DJ United Kingdom

ISBN: (纸本)0780306325

This paper presents a transputer-based laser scanner. This is to be integrated into an existing transputer-based manufacturing environment to allow rapid construction of 3-D models. The approach allows Z-gradient information to be obtained from a 2-D image by illuminating areas of interest with a form of structured light. An active scanning system is described. Simple algorithms are applied to the raw image data to extract concise information. This foveal analysis greatly reduces the data to be processed, allowing a simple and fast method for analysis. The system primarily consists of a video camera which obliquely views a scene being scanned by a laser. The principle, the procedure, and methods of scanning are described. An overview of the principles of foveal analysis, the prototype experimental system and initial results are presented. © 1992 by IEEE Singapore Section.

关键词： Transputers

来源：评论

学校读者我要写书评

暂无评论

Lateral control of an autonomous road vehicle in a simulated highway environment using adaptive resonance neural networks

Lateral control of an autonomous road vehicle in a simulated...

引用

1992 Intelligent Vehicles Symposium, IVS 1992

作者： Lubin, J.M. Gilbert, S. Huber, E.C. Kornhauser, A.L. Human Information Processing Group Robotics and Expert Systems Laboratory Department of Civil Engineering and Operations Research Princeton University PrincetonNJ08544 United States

ISBN: (纸本)078030747X

Lateral control of a simulated vehicle in a simulated highway driving environment is explored. Three modules are used: A driving simulator, a visual preprocessor, and a neural network. Once trained, the networks control the trajectory of the vehicle by accessing a steering decision for implementation at each timestep in response to a visual encoding of an image generated at the previous timestep. The paper presents the development of the three system modules, the creation of training sets, and computational results. Neural network performances are gauged by a number of procedures. Excellent results are achieved for straight roads and curved roads under a variety of initial conditions on the vehicle. © 1992 IEEE.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

The segmented bus: A dynamically segmentable interprocessor communication network for intelligent mobile robot systems

The segmented bus: A dynamically segmentable interprocessor ...

引用

1992 IEEE/RSJ International Conference on Intelligent Robots and systems, IROS 1992

作者： Aras, C.M. Luo, Ren C. Reeves, D.S. Robotics and Intelligent Systems Laboratory Department of Electrical and Computer Engineering United States Department of Computer Science North Carolina State University RaleighNC27695 United States

ISBN: (纸本)0780307372

We propose a new interprocessor communication network, named the Segmented Bus, for multiprocessor message passing computer architectures executing groups of processes with localized communication patterns and time varying computational demands. The control of autonomous robots includes such process sets, making this architecture suitable for the intelligent robot control problem and other control systems with localized and changing message communication patterns. The Segmented Bus also allows dynamic segmentation of the interprocessor communication network for dynamic reconfiguration based on task communication locality. Virtual cut-Through and preemptive circuit switched data transfers are used for inter-segment data transfers on the Segmented Bus. Hardware and protocols for implementing these two techniques are discussed. The performance of the Segmented Bus using the two data transfer techniques is evaluated with simulation and the results are compared to the single bus and the multiple bus in terms of the performance, expandability and the complexity of hardware. © 1992 Institute of Electrical and Electronics Engineers Inc. All rights reserved.

关键词： Data transfer

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：