基于神经网络的力觉临场感系统的预测控制  

Predictive control of force telepresence systems based on neural network

作　　者：陈启宏[1] 费树岷[1] 宋爱国[2] 

机构地区：[1]东南大学自动化研究所,江苏南京210096 [2]东南大学仪器科学与工程系,江苏南京210096

出　　处：《控制与决策》2003年第3期336-339,共4页Control and Decision

基　　金：国家高技术基金资助项目 ( 2 0 0 1AA42 3 140 )

摘　　要：针对力觉临场感系统传输通道中存在时变通讯时延 ,造成系统不稳定和操作性能降低的问题 ,利用前向神经网络建立主机械手、从机械手和环境的模型 ,并通过神经网络模型预测主机械手速度和从机械手受力 ,以消除或减少通讯时延对系统的影响。Time varying communication time delays in communication channels of a telepresence system usually cause instability and bad performance of the system. In order to eliminate or reduce the effect of time delays to a telepresence system,back propogation neural network is used to build the models of the master hand,slave hand and environment. The velocity of the master hand and the force of the slave hand are predicted through the neural network models.This method makes the system meet stability and achieve good performance. The experimental results show effectiveness of this method.

关 键 词：力觉临场感 时廷 神经网络 预测控制 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]