基于快速学习型神经网络的机器人运动学模型辨识及运动控制  

A Kinematic Model Identification and Motion Control of Manipulator Based on the Artificial Neural Network of a Kind of High Speed Learning Algorithm

作　　者：叶军[1] 

机构地区：[1]绍兴文理学院机电系,浙江绍兴312000

出　　处：《计算机仿真》2002年第5期62-63,70,共3页Computer Simulation

基　　金：浙江省自然科学基金资助项目 ( 5 0 0 0 30 )

摘　　要：该文提出一种快速学习型神经网络 ,它不仅符合生物神经网络的基本特征 ,而且算法简单 ,学习收敛速度快 ,有线性、非线性系统辨识精度高等优异特点。因此 ,此类神经网络非常适合于机器人运动学模型辨识及运动控制。仿真结果表明 ,基于快速学习型神经网络进行机械手运动学模型辨识及运动控制是合适的。This paper presents an artificial neural network model based on a kind of high speed learning algorithm. It not only fits the basic characteristic of the biological neural network but also has a simple algorithm, a high speed learning process, and an excellent characteristic of high accuracy in the linear and nonlinear system identification. Therefore, the neural network is very suitable for the kinematic model identification and motion control of manipulator. The simulation results show that the kinematic model identification and motion control of manipulator is suitable on the base of the artificial neural network of a kind of high speed learning algorithm.

关 键 词：快速学习型神经网络 机器人 运动学模型 辨识 运动控制 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置] TP183[自动化与计算机技术—控制科学与工程]