This note tackles the problem of path‐following control for underactuated ships with actuators uncertainties and unknown environmental disturbances. A novel dynamical virtual ship (DVS) guidance principle is initially developed to deal with the assumption that “the reference path could be generated by a virtual ship”, which is normal but not workable in the current literature. In addition, a practical robust control scheme is proposed using feedforward approximation, dynamic surface control, and robust neural damping techniques. In the algorithm, the strong couplings among state variables, underactuated characteristic and the actuators uncertainties are considered to guarantee semiglobal uniform ultimate boundedness of the closed‐loop system. The outstanding advantages are that the control law has a concise form and is easy to implement in practice.The control inputs of interest are two actuator‐steerable variables: the main engine speed and the rudder angle. Although the uncertainties are compensated by NNs, no adaptive parameters are derived for merits of the robust neural damping technique. Finally, the experiment has demonstrated the effectiveness of the proposed scheme, comparing with the LOS self‐tuning fuzzy control.