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。文中的实验结果表明了该方法的有效性 Aiming at the telepresence robotic system, there is a large communication delay in telepathing telerobotic system, resulting in system instability and poor operation performance. The model of slave manipulator and environment is established by using forward neural network. The neural network model is used to predict the mechanical force from the manipulator and control switch with the passive control algorithm to eliminate or reduce the influence of the communication delay on the system. The experimental results show the effectiveness of the method