关键词: 机械臂轨迹跟踪, 模型参考自适应控制, 熵聚类-径向基函数（EC-RBF）神经网络

Abstract: According to the problem that the tracking accuracy is not high enough in trajectory tracking control of robot manipulators, a model reference adaptive control scheme based on EC-RBF neural networks is adopted to achieve robot manipulator model identification and trajectory tracking control. This control scheme contains two RBF neural networks which are trained offline and online, using EC-RBF learning algorithm. The one is used to identify the robot manipulator’s model, and the other one is used to achieve its trajectory tracking control. Simulation result of 2-degree-of-freedom robot manipulator demonstrates that using this method for robot manipulator trajectory tracking control has high control accuracy, and the networks which gain high training speed because of the EC-RBF learning algorithm make the control process faster.

Key words: robot manipulator trajectory tracking, model reference adaptive control, Entropy Clustering-Radial Basis Function（EC-RBF） neural networks