Autonomous dynamic formation for maritime target tracking using multi-agent reinforcement learning

Hua Wang, Jiaxin Li, Hao Tao, Junnan Liu, Chaochao Li, Ke Wang, Mingliang Xu

Abstract: In various maritime missions such as escort and roundup, dynamic formation target tracking plays a crucial role. Most existing dynamic formation methods require user intervention before formation changes, resulting in poor flexibility and low automation. And they do not consider variations in the abilities of individual members. To address the above issue, we propose an autonomous dynamic formation planning method based on multi-agent reinforcement learning, integrating formation configuration into the strategy. This method can automatically adjust the formation based on the current state of the formation, providing greater flexibility and adaptability. Simultaneously, a staged reward function is devised for the training process to guide agents in progressively learning dynamic formation tasks. Finally, we validate the effectiveness and generalization of our proposed method through various experiments.