摘要
提出一种针对机器人跟踪控制的神经网络自适应滑模控制策略。该控制方案将神经网络的非线性映射能力与滑模变结构和自适应控制相结合。对于机器人中不确定项,通过RBF网络分别进行自适应补偿,并通过滑模变结构控制器和自适应控制器消除逼近误差。同时基于Lyapunov理论保证机器手轨迹跟踪误差渐进收敛于零。仿真结果表明了该方法的优越性和有效性。
A neural network-based adaptive sliding mode control, which is designed to ensure trajectory tracking by the uncertainty robot manipulator. This control algorithm integrates the nonlinear mapping of neural network and adaptive and sliding mode control. To the uncertainty of robot manipulators, neural network is used to respectively adaptively learn and compensate the unknown system, and approach error is eliminated by used variable structure and adaptive controller. And based on Lyapunov, this new controller can guarantee the asymptotic convergence of the tracking error to zero. The simulation results show the effectiveness of the presented methods.
出处
《微型机与应用》
2012年第9期60-62,65,共4页
Microcomputer & Its Applications
关键词
不确定机器人
神经网络
自适应控制
uncertainty robot manipulators
neural network
adaptive control
