Adaptive Neural Network-Based Fixed-Time Control for Trajectory Tracking of Robotic Systems

This brief investigates the problem of fixed-time trajectory tracking control of uncertain robotic systems. Firstly, an adaptive radial basis function neural network is designed to estimate the model uncertainties and viscous frictions in robotic systems. Secondly, a segmented terminal sliding mode control (TSMC) variable is adopted to alleviate the singularity problem. To improve the tracking performance, a new second-order fixed-time reaching law is designed. Then, in order to make the tracking errors converge to a small neighborhood of the origin in a fixed-time independent of the initial state, a novel fixed-time non-singular TSMC based on the adaptive neural network is proposed. Finally, the experimental results demonstrate the effectiveness and advantage of the proposed control method.

Automated summary

This paper investigates the problem of fixed-time trajectory tracking control of uncertain robotic systems. An adaptive radial basis function neural network is designed to estimate the model uncertainties and viscous frictions in robotic systems. A segmented terminal sliding mode control variable is adopted to alleviate the singularity problem. A new second-order fixed-time reaching law is designed to improve the tracking performance. A novel fixed-time non-singular TSMC based on the adaptive neural network is proposed to make the tracking errors converge to a small neighborhood of the origin in a fixed-time independent of the initial state. The experimental results demonstrate the effectiveness and advantage of the proposed control method.