Discrete-Time Circadian Rhythms Neural Network for Perturbed Redundant Robot Manipulators Tracking Problem With Periodic Noises
Zhijun Zhang, Siyuan Chen, Junjie Liang
Abstract
Via the Euler forward-difference rule, an Euler-type discrete-time circadian rhythms neural network model (E-DTCRNN) is proposed, developed, and investigated for motion planning of the redundant robot manipulator affected by periodic noises. In this article, an Euler-type discrete-time zeroing neural network model (E-DTZNN) is presented as comparison. The E-DTCRNN model is 0-stable, consistent, and convergent. In addition, through a hybrid torque and velocity optimization scheme synthesized by the proposed E-DTCRNN and the traditional E-DTZNN, a tracking trajectory is designed and applied to the motion planning of the redundant robot manipulator. Finally, groups of simulations and physical experiments verify the efficacy and noise suppression ability of the proposed E-DTCRNN model for motion planning of the manipulator.