Neural-learning enhanced admittance control of a robot manipulator with input saturation

Abstract

In this paper, a sensorless admittance control scheme is developed for robot manipulators in the presence of input saturation by employing neural networks. To deal with system uncertainties, the radial basis function neural network (RBFNN) is integrated into control design. In order to deal with input saturation, a compensator is applied to handle this problem. To interact with the environment, admittance control is employed and external torque is estimated by using a generalized momentum based disturbance observer. Simulations are performed to verify the effectiveness of the proposed control scheme.