Radial Basis Function Neural Network Adaptive Control of Flexible-Joint Space Robot

Abstract

Because of their unique properties and good performance, some elastic components, such as the harmonic reducers and the torque sensors, are widely used in the joints of the space robots and manipulators, in order to obtain high reduction ratio. However these elastic components bring joint flexibility into the system at the same time, which makes its stability control more complex. Based on this, this paper discussed radial basis function neural network adaptive control and elastic vibration suppression for flexible-joint space robots, it worked under the unknown parameter. Firstly, mathematical models which been suit for design of control system are established by using a joint flexibility compensation controller, the model composed of the slow-subsystem robot dynamics model and and the fast-subsystem dynamics model is deduced by the second type of Lagrange method. Then, for the dynamic model of the fast-subsystem dynamics model, the torque differential feedback control algorithm is adopted to the premise that the ultimate doundedness of system, for the slow-subsystem robot dynamics model, the radial basis function neural network adaptive control algorithm is designed to to track the desired trajectory in joint space. The whole control system is superposed by the slow-subsystem and the fast-subsystem control algorithm. The system simulation comparison test proves the effectiveness of said algorithm.