Precision Trajectory Tracking of Robot Manipulator Using a Discrete-Time Learning-Based Neural Network Control With Prescribed Performance

Robot manipulator control for accurate trajectory tracking with unknown system dynamics and time-varying external disturbances is a challenging issue. This article aimed to propose a novel discrete-time learning-based neural network control with prescribed performance (LNNCPP) to solve this issue. This control scheme consists of offline and online learning phases. In the offline learning phase, an adaptive neural network controller (ANNC) satisfying the persistent excitation condition can achieve accurate closed-loop learning of unknown system dynamics along recurrent trajectory during the tracking control. This offline learning focuses on the learning in dynamic environments requiring neither the evaluation of inverse dynamical model nor the time-consuming training. The learned knowledge can be stored as constant network weights. The online learning of the LNNCPP is developed based on the learned knowledge and the prescribed performance (PP) to counter the external disturbances and to guarantee the PP of tracking errors. The LNNCPP was compared with the ANNC, ANNC with PP and sliding model control by simulation and real-world experiment. Results showed that the LNNCPP had improved tracking accuracy, better transient performance and lower oscillations with the dynamic changes and external disturbances. This method may promote the tracking accuracy and stability for robotic manipulators towards unstructured environments.