检索结果-内蒙古大学图书馆

International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)

作者： S.X. Yang M. Meng ART (Advanced Robotics & Teleoperation) Laboratory Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada

In this paper, a neural network architecture is proposed for sensory motor control of wing beat in a locust. The proposed neural network model is based on the neural anatomy and function of the neurons and sense organs involved in the flight control of wing beat in a locust. This model consists of a central pattern generator and a sensory motor network. Both the central nervous mechanisms and the sensory feedback are essential for the generation of the rhythmic output in the motoneuron. A larger input amplitude results in a higher frequency of the central pattern generator signal through a shorter down-strike duration. The feedback from sensory organs increase the wing beat frequency by generating an early, rapid increasing component and by modifying the late component of the elevator motoneuron activity. The model predictions are in qualitative agreement with the corresponding data.

关键词： Motor drives Neural networks Sense organs Frequency Anatomy Neurons Aerospace control Output feedback Neurofeedback Signal generators

来源：评论

学校读者我要写书评

暂无评论

Influence of shear, rotary inertia on the dynamic characteristics of flexible manipulators

Influence of shear, rotary inertia on the dynamic characteri...

引用

IEEE Pacific Rim Conference on Communications, computers and Signal Processing

作者： D. Wang M. Meng Y. Liu ART (Advanced Robotics & Teleoperation) Laboratory Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada

The influence of shear, rotary inertia on the dynamic characteristics of flexible manipulators is studied through frequency analysis. In terms of the various geometric effects, dynamic models of flexible manipulators are set up and characteristic equations are derived. By using the analysis, the influences of shear, rotary inertia, axial force on the flexible manipulator are given.

关键词： Manipulator dynamics Frequency Deformable models Equations Nonlinear dynamical systems Payloads Subspace constraints Robots Solid modeling Energy consumption

来源：评论

学校读者我要写书评

暂无评论

A neural network approach to real-time motion planning and control of robot manipulators

A neural network approach to real-time motion planning and c...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Xianyi Yang M. Meng Art Advanced Robotics & Teleoperation Laboratory Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada

Real-time motion planning and control of multi-joint robot manipulators are studied using neural networks. The proposed neural network approach consists of two modules: one for real-time collision-free motion planning, the other for real-time fine control of the robot manipulators. The motion planning module is a biologically inspired, parallel connected, topologically organised neural network, where each neuron is characterised by a shunting equation, whose state space is the robot configuration joint space. This module is capable of planning a real-time optimal path for robot manipulators through the dynamic activity landscape of the neural network. The motion control module involves of a feedforward neural network together with a traditional PD feedback loop. It is capable of achieving real-time fine motion control of robot manipulators under significant uncertainties and without any prior knowledge of the robot dynamics. This module can quickly compensate sudden changes in the robot dynamics. The real-time fine control of robot manipulators is achieved through the online learning of the neural network. Both the motion planning and motion control modules are computationally efficient, and their global stabilities are proved using Lyapunov stability theory.

关键词： Neural networks Motion control Motion planning Manipulator dynamics Orbital robotics Robot control Neurons Equations State-space methods Parallel robots

来源：评论

学校读者我要写书评

暂无评论

Real-time tracking control of robot manipulators with online learning based approach

Real-time tracking control of robot manipulators with online...

引用

Canadian Conference on electrical and computer engineering (CCECE)

作者： Xianyi Yang M. Meng ART (Advanced Robotics & Teleoperation) Laboratory Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada

An online learning based approach to real-time tracking control of robot manipulators is proposed. This controller involves a single-layered neural network together with a traditional PD feedback loop, which inherits advantages from both the neural networks and the PD controller. It is capable of achieving real-time fine tracking control of robot manipulators under significant uncertainties, without any prior knowledge of the robot dynamics, and without any off-line training procedures. In addition, it is capable of quickly compensating sudden changes of robot dynamics. The proposed controller is computationally simple. The global system stability and convergence are proved using Lyapunov stability analysis. A model variation is presented in the discussion. The effectiveness and the efficiency are demonstrated through simulation and comparison studies.

关键词： Robot control Neural networks Manipulator dynamics Feedback loop PD control Uncertainty Stability analysis Convergence Lyapunov method Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Real-time trajectory generation with clearance from obstacles

引用

IFAC Proceedings Volumes 1999年第2期32卷 5338-5343页

作者： Xianyi Yang Max Meng Advanced Robotics and Teleoperation (ART) Lab Department of Electrical and Computer Engineering University of Alberta Edmonton AB T6G 2G7 Canada

A neural network approach to real-time trajectory generation with clearance from obstacles in a nonstationary environment is proposed based on a biologically inspired model for a mobile robot. It is also extended to multi-joint robot manipulators. The strength of obstacle clearance is adjustable. The optimal trajectory is generated by implicitly minimising the robot travel distance while considering the obstacle clearance. The generated real-time “comfortable” path does not suffer from the “too close” or the “too far” problems. The stability is guaranteed by Lyapunov stability analysis. The effectiveness and the efficiency are demonstrated through simulation and comparison studies.

关键词： Real-time robot navigation obstacle avoidance global stability neural networks efficient algorithms

来源：评论

学校读者我要写书评

暂无评论

Influence of mode truncation and elongation deformation to a flexible manipulator

Influence of mode truncation and elongation deformation to a...

引用

Canadian Conference on electrical and computer engineering (CCECE)

作者： Yan Liu M. Meng D. Wang ART (Advanced Robotics and Teleoperation) Laboratory Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada

Influences of the mode truncation and the longitudinal elongation on the dynamic response of a single link flexible robotic manipulator are studied. Firstly, the relationship between the mode truncation and the inertia matrix of the flexible manipulator dynamic equation is derived. The condition number of the inertia matrix is computed with respect to the number of mode shapes. The inertia matrix is becoming ill posed with the increasing of the mode number. Secondly, the dynamic model with longitudinal elongation is derived. The influence of the longitudinal elongation on the dynamic response, which is caused by the transversal deformation of the system, is analyzed.

关键词： Manipulator dynamics Robots Deformable models Frequency Payloads Equations Orbital robotics Angular velocity Subspace constraints Shape

来源：评论

学校读者我要写书评

暂无评论

Frequency analysis of a flexible robot manipulator

Frequency analysis of a flexible robot manipulator

引用

Canadian Conference on electrical and computer engineering (CCECE)

作者： D. Wang M. Meng ART (Advanced Robotics & Teleoperation) Laboratory Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada

In this paper, the effect of longitudinal elongation of a flexible robot manipulator is investigated using frequency analysis. The dynamic model of a flexible manipulator without longitudinal elongation is considered and the basic frequency of the flexible manipulator is computed. With the increasing length and weight of the manipulator, the basic frequency decreases. The instability of the dynamic response will occur when the angular velocity exceeds the basic frequency. In order to avoid the unstable dynamics, the longitudinal elongation that is caused by the flexible deformation is considered in the dynamic model. From the frequency analysis, with the increase of angular speed of the manipulator, the basic frequency will rise.

关键词： Frequency Robots Manipulator dynamics Angular velocity Deformable models Solid modeling Equations Resonance Propellers Nonlinear dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Real-time collision-free path planning of robot manipulators using neural network approaches

Real-time collision-free path planning of robot manipulators...

引用

IEEE International Symposium on Computational Intelligence in robotics and Automation (CIRA)

作者： S.X. Yang M. Meng School of Engineering University of Guelph Guelph ONT Canada ART (Advanced Robotics and Teleoperation) Laboratory Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada

In this paper, a novel neural network approach to real-time collision-free path planning of robot manipulators in a nonstationary environment is proposed, which is based on a biologically inspired neural network model for dynamic trajectory generation of a point mobile robot. The state space of the proposed neural network is the joint space of the robot manipulators, where the dynamics of each neuron are characterized by a shunting equation. The real-time robot path is planned through the dynamic neural activity landscape that represents the dynamic environment. The proposed model for robot path planning with safety consideration is capable of planning a real-time "comfortable" path without suffering from the "too close" nor "too far" problems. The model algorithm is computationally efficient. The computational complexity is linearly dependent on the neural network size. The effectiveness and efficiency are demonstrated through simulation studies.

关键词： Path planning Orbital robotics Manipulator dynamics Neural networks Mobile robots Computational modeling Biological system modeling Trajectory State-space methods Neurons

来源：评论

学校读者我要写书评

暂无评论

A novel sensing and control system of artificial eye-implant

引用

IFAC Proceedings Volumes 1999年第2期32卷 529-532页

作者： J. Gu M. Meng M.G. Faulkner A. Cook ART(Advanced Robotics and Telcoperation) Lab Department of Electrical and Computer Engineering University of Alberta Canada T6G 2G7 Department of Mechanical Engineering University of Alberta Canada T6G 2G7 Faculty of Rehabilitation Medicine University of Alberta Canada T6G 2G7

The aim of this paper is to let the anophthalmic patient has a natural movement of his artificial eye. The loss of an eye can be solved by the ocular implant. The artificial eye can be made like the real eye. But the problem is that it is static, and doesn't have the natural movement. Present study is to design a small automatic control system to let the. artificial eye has the same natural movement as the real eye. How to detect the eye movement is an important issue. The review of the eye movement detection methods is included in this paper. Main part of this paper deals with the experimental system and the further considerations.

关键词： automatic control detection natural movement

来源：评论

学校读者我要写书评

暂无评论

Dynamical trajectory generation with collision free using neural networks

Dynamical trajectory generation with collision free using ne...

引用

Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190)

作者： Xianyi Yang Max Meng ART (Advanced Robotics & Teleoperation) Lab Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada

ISBN: (纸本)0780344650

To dynamically generating trajectory with collision free is very important but difficult for the robots in a nonstationary environment. In this paper, the real-time trajectory generation and obstacle avoidance are studied using biologically motivated neural network approaches. The optimal trajectory is generated through the neural dynamics of a topologically organised neural network. Each neuron of the neural net is characterised by a shunting equation or an additive equation. This model is computationally efficient and its stability is guaranteed. These neural network approaches were applied for solving maze-type problems, dynamically tracking moving target, and avoiding varying obstacles. The model parameter sensitivity and model variations are discussed. Simulations are included to demonstrate the proposed approaches.

关键词： Neural networks Equations Biomembranes Neurons Biological system modeling Robot sensing systems Computational modeling State-space methods Subspace constraints Electronic mail

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：