力觉临场感遥操作机器人系统的预测无源控制  

Predictive and Passive Control of Force Reflecting Telepresence Teleoperation Robot Systems

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：《测控技术》2003年第5期57-59,62,共4页Measurement & Control Technology

基　　金：国家 8 63高技术资助项目 ( 863 -2 0 0 1AA42 3 2 40 )

摘　　要：针对力觉临场感遥操作机器人系统传输通道中存在大的通信时延 ,造成系统不稳定和操作性能降低 ,利用前向神经网络建立从机械手和环境的模型。通过神经网络模型预测从机械手受力 ,并结合无源控制算法进行控制切换 ,消除或减少通信时延对系统的影响。There are large communication time delays in communication channels of a force reflecting telepresence teleoperation robot system.This conduces to 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 model of slave hand and environment.Force of the slave hand is predicted by the neural network model.Controllers are switched between predictive control and passive control.This method makes the system meet stability and achieves good performance.The results of the experiment showed effectiveness of this method.

关 键 词：力觉临场感 遥操作 机器人系统 预测控制 无源控制 神经网络 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]