针对结构和参数均未知的机械手控制问题,提出了考虑驱动系统动态的机械手神经网络控制方法,采用稳定的径向基(Radial basis function,RBF)神经网络辨识机械手未知动态,而附加的鲁棒控制可以保证存在神经网络的建模误差和外部干扰时系统的稳定性和性能,并且该方法使机械手闭环系统一致最终有界.同时开发了基于半实物仿真技术的机械手控制系统,最后,将本文方法与经典的PD控制器和自适应控制器在同一机械手平台上进行了实验验证与分析,实验结果表明该方法具有良好的控制性能.
A neural network control scheme is proposed for the control of robotic manipulator including actuator dynamics in this paper. In the proposed control scheme, the radial basis function (RBF) network is adopted to approximate the nonlinear dynamics of the robotic manipulator. In addition, a robust control is used to eliminate the neural network modelling error and disturbance. Uniformly ultimate boundedness (UUB) stability of the closed-loop system can be guaranteed by Lyapunov theory. Finally, a hardware-in-the-loop simulation technique based control system is developed. Furthermore, the proposed control scheme is applied to the same robotic manipulator together with PD control and adaptive control. Experiment results confirm the validity of the proposed control scheme by comparing it with other control strategies.