基于改进的FNNs移动机械臂输出反馈跟踪控制

针对包含电机动态模型的移动机械臂系统,提出一种鲁棒自适应输出反馈控制方法.将误差符号函数鲁棒积分反馈与神经网络前馈结构相结合用于控制器的设计,然后利用神经网络去逼近机器人和电机系统的不确定项,设计鲁棒项实时补偿网络误差.通过Lyapunov稳定性分析证明闭环系统所有信号半全局一致有界.最后仿真实验表明,控制方法对系统动态不确定性和外界干扰有很好的鲁棒性,可实现移动机械臂的输出反馈跟踪控制.

Output Feedback Tracking Control of Mobile Manipulators Based on Improved Fuzzy Neural Networks

A robust adaptive output feedback control method using fuzzy neural networks is proposed for mobile manipulators including dynamics model of motor.The neural networks are employed to approximate unknown model uncertainty terms of mobile manipulators and actuator model.In addition,a simple robust term is adopted to compensate the network error in real time.The Lyapunov stability analysis shows that all the signals in the closed-loop system are semi-global uniformly ultimately bounded.Finally,the simulation results show that the proposed control method has strong robustness against both dynamic uncertainties and external disturbances of the system,moreover,the tracking control for the output-feedback of mobile manipulators can be achieved.