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

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.