The cooperative patrol control of multiple unmanned surface vehicles (Multi-USVs) in dynamic aquatic environments presents significant challenges in global coverage efficiency and system robustness. The study proposes a cooperative patrol control algorithm for multiple unmanned surface vehicles (Multi-USVs) based on a hybrid embedded task state information model and reward reshaping techniques, addressing global coverage challenges in dynamic aquatic environments. By integrating patrol, collaboration, and obstacle information graphs, the algorithm generates kinematically feasible control actions in real time and optimizes the exploration-cooperation trade-off through a dense reward structure. Simulation results demonstrate that the algorithm achieves 99.75% coverage in a 1 km × 1 km task area, reducing completion time by 23% and 74% compared to anti-flocking and partition scanning algorithms, respectively, while maintaining collision rates between agents (CRBAA) and obstacles (CRBAO) below 0.15% and 0.5%. Compared to DDPG, SAC, and PPO frameworks, the proposed training framework (TFMUSV) achieves 28% higher rewards with 40% smaller fluctuations in later training stages. This study provides an efficient and reliable solution for autonomous monitoring and search-rescue missions in complex aquatic environments.
In the dynamic marine environment, the high mobility of intrusion targets, complex interference, and insufficient multi-vessel coordination accuracy pose significant challenges to the cooperative interception mission of multiple unmanned surface vehicles (USVs). This paper proposes an adaptive dynamic prediction-based cooperative interception control algorithm and establishes a “mission planning—anti-interference control—phased coordination” system. Specifically, it ensures interception accuracy through threat-level-oriented target assignment and extended Kalman filter multi-step prediction, offsets environmental interference by separating the cooperative encirclement and anti-interference modules using an improved Two-stage architecture, and optimizes the movement of nodes to form a stable blockade through the “target navigation—cooperative encirclement” strategy. Simulation results show that in a 1000 m × 1000 m mission area, the node trajectory deviation is reduced by 40% and the heading angle fluctuation is decreased by 50, compared with the limit cycle encirclement algorithm, the average interception time is shortened by 15% and the average final distance between the intrusion target and the guarded target is increased by 20%, when the target attempts to escape, the relevant collision rates are all below 0.3%. The TFMUSV framework ensures the stable optimization of the algorithm and significantly improves the efficiency and reliability of multi-USV cooperative interception in complex scenarios. This paper provides a highly adaptable technical solution for practical tasks such as maritime security and anti-smuggling.