To address the challenge that unmanned surface vehicles (USVs) struggle to effectively balance tracking accuracy, control smoothness, and system energy efficiency under external disturbances, this paper proposes an anti-disturbance path tracking control method integrating quantum-inspired optimization (QIO) and dynamic game theory (GT). The proposed control method consists of a two-layer optimization architecture: the upper layer employs dynamic game theory to optimize the guidance process, modeling the optimization of the look-ahead distance ($Ld$) and switching radius ($R$) in the LOS guidance algorithm as a non-cooperative game, and achieves adaptive adjustment to path variations and environmental disturbances by solving for the Nash equilibrium. The lower layer, based on a quantum-inspired optimization algorithm, enhances the control process by employing quantum bit probability amplitude encoding for the PID parameter space and utilizing a quantum rotation gate mechanism for efficient global search, thereby achieving online self-tuning of PID parameters under environmental disturbances. Simulation results indicate that, under sea conditions with external disturbances, the proposed method achieves a superior balance among tracking accuracy, control smoothness, and system energy efficiency compared to the traditional fixed-parameter PID-LOS approach, enhancing the comprehensive anti-disturbance robustness of the USV.

Deep reinforcement learning (DRL) enables model-free adaptive control for marine dynamic positioning (DP) under changing disturbances. However, its application remains limited for vessels with strict mechanical constraints, such as the common stern-only dual-azimuth configuration. This paper applies DSAC-T (Distributional Soft Actor-Critic with Three Refinements), a distributional off-policy deep reinforcement learning algorithm, to DP of an 83 m offshore supply vessel under this stern-only configuration. DSAC-T is compared with proximal policy optimization (PPO) and soft actor–critic (SAC) using a shared reward and observation design and an equal simulation budget. All DRL controllers, together with a fixed-gain proportional–derivative (PD) baseline, are evaluated in simulations covering eight wind directions at two wind speeds, together with a calm-water case. DSAC-T achieves the lowest aggregate position-keeping error among the three learning-based methods with lower propulsor-command activity than PPO. We also find that a tighter Gaussian position tolerance in the reward function substantially reduces steady-state position error with a small increase in propulsor-command activity, identifying this tolerance as an influential design parameter for stern-only DP.