基于RBF神经网络的多关节机器人固定时间滑模控制

针对具有典型非线性特性的多关节机器人轨迹跟踪控制问题,提出一种基于径向基函数(RBF)神经网络的固定时间滑模控制方法.首先,基于凯恩方法建立包括系统模型不确定性以及外部干扰在内的多关节机器人动力学模型;然后,根据机器人动力学模型设计一种固定时间收敛的滑模控制器, RBF神经网络用来逼近系统模型中的不确定性项,并利用Lyapunov理论证明该系统跟踪误差能在固定时间内收敛;最后,对特定型号的多关节机器人虚拟样机进行仿真分析,结果表明:与基于RBF神经网络的有限时间滑模控制器相比,所提出控制器具有良好的跟踪性能且能保证系统状态在固定时间内收敛.

Fixed-time sliding mode control of multi-joint robot based on RBF neural network

A fixed-time sliding mode control method based on the radial basis function(RBF) neural network is proposed for trajectory tracking control of multi-joint robots with typical nonlinear characteristics. Firstly, the dynamic model of multi-joint robots including system model uncertainty and external disturbance is established based on the Kane method. A sliding mode controller with fixed-time convergence is designed according to the dynamic model of the robot, the RBF neural network is used to approximate the uncertainties in the system model. The Lyapunov theory is used to prove that the tracking error of the system can converge in a fixed-time. Finally, a virtual prototype of a certain type of multi-joint robot is simulated and analyzed. Compared with the finite-time sliding mode controller based on the RBF neural network, the proposed controller has good tracking performance and can ensure that the system state converges in a fixed-time.