一类带有监控器的自适应模糊神经网络机器人跟踪控制

A Adaptive Fuzzy-neural Control with Supervisor Controller for Robot Tracking Control

提出一种自适应模糊神经网络(FNN)监督控制方案。该方案在FNN控制器的基础上串联一个监督控制器,实现对系统的跟踪控制。监督控制器在FNN控制器不能维持系统稳定时发挥作用,从而确保了闭环系统的全局稳定性,且使系统具有良好的跟踪性能。并把此方案应用在机器人跟踪控制上。仿真结果表明了该控制方案的可行性。

An adaptive fuzzy-neural networks （FNN） controller with supervisory mode for a certain class of un- known nonlinear dynamical system is presented. A supervisory controller is appended into the FNN controller to jointly control the system. If the FNN controller cannot maintain the stability, the supervisory controller starts work- ing; on the other hand, if the FNN controller works well, the supervisory controller will be de-actived, which not only guarantees the global stability of the closed-loop system but also preserving the tracking performance. And this program is used in robot tracking control, Simulation results show the control scheme is easy to implement.