Iterative learning control of varying trajectories for robot manipulators
A new neural network iterative learning control is proposed for varying trajectories tracking of robotic manipulators with exogenous disturbance and uncertainties. To date, most of the available results in iterative learning control have been utilized in applications where robot manipulators are required to execute the same motion over and over again, with a certain periodicity. To overcome the varying trajectories and non-zero initial errors problems, the proposed control schemes learn the inverse structure of the system not concerning the error at each iteration employing the approximation of the neural network rather than learning the error in traditional iterative learning control algorithm. The convergence of the algorithm is proved using the Lyapunov-like function. The simulation results show that the neural network can approximate the robot manipulator better, and the tracking error is decreased and tends to a small value, which demonstrate the effects of the algorithm on the robot manipulator.
Iterative learning control Varying trajectories Robot manipulators Radial basis function network
Huifang Wang Shiqiang Zhu Songguo Liu
State Key Laboratory of Fluid Power Transmission and Control, Zhejiang University, Hangzhou, China
国际会议
杭州
英文
437-440
2009-04-08（万方平台首次上网日期，不代表论文的发表时间）