遥控作业器是实现未知或危险环境中作业的有力手段．由于遥控机械手大多工作在不确定的环境中，操作者难以预先知道环境目标的动力学特性，在机械手和环境发生力的交互过程中，需要考虑机械手和环境碰撞时的强非线性对控制回路的影响，因此对机械手和环境碰撞的实时感知和识别是非常重要的．本文利用接近觉传感器测量机械手顶端与环境物体的距离，提出了基于主动时延神经网络的遥控作业器的感知和控制方法．仿真实验表明了该方法的有效性和对接近觉传感器量程的要求 Remote Operators are powerful tools for working in unknown or hazardous environments. Because remote manipulators mostly work in uncertain environment, it is difficult for operators to know the dynamic characteristics of environmental targets in advance. During the interaction between manipulator and environment, it is necessary to consider the strong nonlinearity of manipulator and environment in the control loop Impact, so real-time perception and recognition of the robot and the environment collision is very important. In this paper, the proximity sensor is used to measure the distance between the top of the manipulator and the environment object, and the sensing and control method of the remote manipulator based on the active-delay neural network is proposed. Simulation experiments show the effectiveness of the method and the requirements of proximity sensor range