移动机器人自适应神经滑模轨迹跟踪控制

Adaptive Neural Sliding Mode Trajectory Tracking Control for Mobile Robots

针对质心和几何中心不重合情况下轮式移动机器人的轨迹跟踪问题,提出了一种鲁棒项系数自调整的自适应神经滑模轨迹跟踪控制策略。首先选择适当的Lyapunov函数设计运动学控制器,其次基于反演方法和积分滑模控制思想设计出自适应神经滑模动力学控制器。利用自适应径向基神经网络（RBF）分别调节控制律的等效控制部分和切换增益,有效地消除了系统不确定参数和未知扰动的影响,并运用Lyapunov方法证明了系统的稳定性和渐进收敛。仿真结果验证了该控制策略的有效性和正确性。

According to the trajectory tracking problem of wheeled mobile robots, a robust adaptive neural network sliding mode tracking control strategy is proposed. Firstly, select the appropriate Lyapunov function to design the kinematic controller. Secondly, based on the inversion method and integral sliding mode control, the adaptive neural sliding mode controller is designed. After that, the adaptive radial basis function neural network is used to adjust the control law of the equivalent control and the switching gain, which can eliminate the effects of uncertain parameters and unknown disturbances effectively, and the Lyapunov method is used to prove the stability and asymptotic convergence of the system. The simulation results verify the effectiveness and correctness of the proposed control strategy.