基于HJI理论的移动机器人神经网络自适应控制

Neural Network Adaptive Control of Mobile Robot Based on HJI Theory

考虑一类动力学模型不确定的移动机器人在受外界不确定扰动情况下的轨迹跟踪控制问题。首先,基于反步法设计了运动学控制器。其次,采用径向基函数RBF(Radical Basis Function)神经网络对移动机器人动力学模型不确定项和外部干扰进行逼近,并设计自适应率对RBF神经网络的权值进行在线调整。在此基础上,基于HJI(Hamilton-JacobiInequality)理论设计了一种前馈控制和反馈控制相结合的动力学控制方法。利用Lyapunov理论证明了运动学系统的稳定性,利用HJI不等式证明了动力学系统的稳定性。最后通过仿真验证了上述方法的有效性,在上述方法下的移动机器人具有良好的跟踪性能。

This article considers the trajectory tracking control problem of a class of mobile robots with uncertain dynamics model under the condition of uncertain external disturbances.First,the kinematics controller was designed based on the backstepping method.Secondly,the radial basis function(RBF)neural network was used to compensate the uncertain items and external interference of the dynamic model of the mobile robot,and the adaptive rate was designed to adjust the weights of the RBF neural network online.On this basis,a dynamic control method combining feedforward control and feedback control was designed based on the Hamilton-Jacobi Inequality(HJI)theory.The Lyapunov theory was used to prove the stability of the kinematic system,and the HJI inequality was used to prove the stability of the dynamic system.Finally,the effectiveness of the method was verified through simulation,and the mobile robot under this method has good tracking performance.