Intelligent control for robotic manipulator with adaptive learning rate and variable prescribed performance boundaries

Abstract

The purpose of this study is to enhance the transient performance and mitigate the possible boundary-crossing issue during the design of a neural network-based intelligent prescribed performance control for robotic manipulators that suffer from input saturation. Initially, an auxiliary system is created utilizing the saturation signal, which is then used to modify the prescribed performance boundaries when saturation takes place. This ensures that the tracking errors adhere to the performance constraints even if the available control effort is limited. To further enhance the transient performance of the closed-loop system, a composite learning-based online identification scheme employing a Gaussian function to adaptively adjust the learning rate is utilized instead of a fixed-learning-rate weight updating law to train the neural network. This approach facilitates the reduction of the undesired weight oscillations at the beginning of the control process when the neural network is not sufficiently trained. Lastly, the stability of the closed-loop system is demonstrated by applying the Lyapunov approach, and simulation results support the effectiveness of the identification and control schemes proposed in this study.