Abstract: Objective The repeated online optimization method is applied in traditional model predictive control, which causes intense computation for underactuated ship path following predictive controller; in this paper, an efficient predictive controller of underactuated ship path following is presented based on the neurodynamic optimization system. Methods First, the line-of-sight (LOS) guidance principle is employed to ease the underactuated problem herein; for kinematic model uncertainty in traditional LOS guidance law, the robust LOS guidance law is presented based on the idea of sliding mode. Furthermore, the sideslip angle caused by the external disturbances would cause negative effects on path following, the robust adaptive LOS guidance method is presented herein to compensate the sideslip angle, which improves the robustness to model uncertainty and external disturbances. Second, in order to mitigate the input saturation problem, the model predictive control is adopted herein to transform ship path following problem into the quadratic optimization problem with input constraints. Finally, the neurodynamic optimization solver is presented based on the projection recurrent neural network herein to calculate the quadratic optimization problem with input constraints, improving the computational efficiency. Results In this paper, both simulations for straight line path following and curved line path following are conducted. The simulation results show that the presented efficient predictive controller can achieve arbitrary path following. Additionally, the comparative simulations are performed, revealing that the presented method exhibits advantage in computational efficiency compared to the Fmincon optimization solver (built-in solver in MATLAB). Conclusion The research results have practical value for improving the real-time performance of underactuated ship path following.