作者: Long Cheng , Zeng-Guang Hou , Min Tan , W. J. Zhang
DOI: 10.1109/TSMCB.2012.2192270
关键词:
摘要: The trajectory tracking problem of a closed-chain five-bar robot is studied in this paper. Based on an error transformation function and the backstepping technique, approximation-based algorithm proposed, which can guarantee control performance robotic system both stable transient phases. In particular, overshoot, settling time, final be all adjusted by properly setting parameters function. radial basis neural network (RBFNN) used to compensate complicated nonlinear terms closed-loop dynamics system. approximation RBFNN only required bounded, simplifies initial “trail-and-error” configuration network. Illustrative examples are given verify theoretical analysis illustrate effectiveness proposed algorithm. Finally, it also shown that controller simplified smart mechanical design robot, demonstrates promise integrated philosophy.