基于递归模糊神经网络的移动机器人滑模控制

针对非完整移动机器人轨迹跟踪控制问题,提出了一种Backstepping运动学控制器与自适应动态递归模糊神经滑模控制器相结合的控制结构。采用遗传算法对运动学控制器的参数进行了优化选取,有效地抑制了因初始位姿过大而引起的初始速度及输出力矩过大的问题;采用动态递归模糊神经网络(Adaptive dynamic recurrent fuzzy neural network,AD-RFNN)对动态非线性不确定部分进行在线估计,使不确定性估计误差大大减小;通过与自适应鲁棒控制器结合应用,不但解决了移动机器人的参数与非参数不确定性问题,同时也消除了在滑模控制中的输入抖振现象;基于Lyapunov方法的设计过程,保证了控制系统的稳定与收敛;仿真结果表明了该方法的有效性。

Sliding mode control of mobile robots based on recurrent fuzzy-neural network

A control structure is proposed for trajectory tracking control of nonholonomic mobile robots.It integrates the backstepping kinematic controller and a sliding mode controller with Adaptive Dynamic Recurrent Fuzzy Neural Network(ADRFNN).The genetic algorithm is used to optimize the parameters of kinematic controller that effectively suppresses the excessive initial speed and output torque caused by large initial error of posture.The ADRFNN is developed to achieve on-line estimation of the part of dynamic nonlinear uncertain,which greatly reduces estimation errors of uncertainties.By combing ADRFNN with the adaptive robust controller,this method can not only solve the problem of parameters and non-parameter uncertainties of mobile robots,but also eliminate input chattering of the sliding mode control.The stability and convergence of the control system are proved by Lyapunov theory.Simulation results demonstrate the effectiveness of the proposed method.