Robotic Arm Trajectory Tracking Control Based on An RBF Neural Network Adaptive Control Algorithm

Abstract

This work investigates and contrasts two approaches for trajectory tracking control strategies for robotic operating systems: model-free adaptive algorithm and radial basis function (RBF) neural network adaptive algorithm. The tracking for high precision systems is then finished using a computational torque control approach in conjunction with a compensating controller designed based on this algorithm. The model-free adaptive control technique just employs these I/O data to construct the controller and only needs to know the input and output data of the controlled system. It is not required to know the specific model information of the controlled system. Last but not least, the experimental trajectory tracking results show that the RBF neural network can better track the trajectory of the manipulator with a relatively small tracking error.