Fixed-Time Neuroadaptive Backstepping Tracking Control for Uncertain Nonlinear Systems With Predictor Based Learning

This work focuses on the issue of fixed-time tracking control for a class of nonlinear systems affected by unknown uncertainties and external disturbances. First, a fixed-time neuroadaptive approximator is proposed to estimate the lumped uncertainties in nonlinear systems. Unlike existing neural network based methods, the estimation solution presented here introduces an adaptive predictor based learning mechanism, which would improve the estimation performance by removing the effect of tracking errors on the estimation process. Then, based on the reconstructed information, a fixed-time command filtered backstepping controller is developed with a fixed-time compensation system. In the compensation system, a novel bounded function is skillfully utilized such that the order and complexity of the compensation system are effectively reduced. Moreover, it is demonstrated that the designed control scheme can drive the tracking error to a small set near zero in a fixed time. Finally, the validity of the proposed control scheme is illustrated by numerical simulations <italic>Note to Practitioners</italic>&#x2014;This paper is motivated by the tracking control problem for nonlinear systems such as robotic, spacecraft, and unmanned aerial vehicle system. Existing tracking control schemes often suffer from issues such as insufficient tracking speed, redundant design process and the explosion of complexity. A fixed time neuroadaptive backstepping control scheme is proposed in this paper to ensure convergence of the error within a fixed time. An adaptive predictor-based fixed-time neuroadaptive estimator is presented to enhance the speed and accuracy of uncertainty estimation. Furthermore, a novel fixed-time compensation system is presented, which effectively addresses the issue of complexity explosion while reducing coupling of the compensation system, making the controller more concise. The effectiveness of the proposed method is validated through a numerical simulation in an uncertain spacecraft pitch motion system. Future work will involve validation of the proposed method on a hardware-in-the-loop simulation system or experiment platform.