Enhanced Grey Wolf Optimizer for Multi-USV Task Allocation in Maritime Environments

Task allocation ensures the efficient execution of tasks by multiple unmanned surface vehicles (multi-USVs) at sea. In order to enhance the efficiency of multi-USV task execution in maritime environments, this study proposes a novel task allocation strategy for multi-USVs based on an Enhanced Tent Grey Wolf Optimizer (ETGWO) integrated with path planning. Firstly, a distance correction factor is introduced to better simulate the distances between tasks in real maritime scenarios. Secondly, to improve the task allocation performance of the GWO, the tent chaos model is introduced to enhance the diversity of the initial population. Additionally, a population updating strategy is adopted, selecting multiple similar grey wolves and distancing them from weaker ones, thereby increasing the diversity of grey wolf individuals and expanding their hunting range. Subsequently, selective path planning is conducted to determine the routes. Finally, the performance of the proposed algorithm is evaluated using international benchmark functions and in a multi-USV task allocation environment. The results indicate that the proposed algorithm offers several advantages, including rapid convergence and broad applicability, enabling it to achieve effective task allocation schemes that are both reasonable and efficient.