Learning-Guided Cooperative Evolution for Multi-AUV Task Allocation in Dynamic Flow Fields

Objectives Aiming at the problems of strong environmental uncertainty, dynamic variation of task adaptation relationships, and difficulty in balancing search and convergence in cooperative task allocation for multiple autonomous underwater vehicles (AUV) under dynamic flow-field environments, a cooperative task allocation method for multi-AUV systems in complex dynamic flow-field conditions is studied. Methods A dual-feedback-driven learning-guided cooperative evolutionary framework is proposed. A probabilistic long short-term memory (LSTM) network is employed to predict the probability distribution of navigation time correction factors under flow-field effects, and a risk-aware cost function is constructed accordingly. A graph neural network (GNN) integrating flow-field features is designed to learn the structural adaptation relationships between tasks and AUVs, thereby providing structural guidance for task allocation. Furthermore, a reinforcement learning meta-controller based on proximal policy optimization (PPO) is introduced to dynamically regulate evolutionary operator parameters, enabling adaptive control of the search process. Results Simulation experiments are conducted in dynamic flow-field environments. The results show that the proposed method reduces the total system energy consumption by 53% and decreases the dynamic flow-field risk penalty by 74% compared with the classical non-dominated sorting genetic algorithm. Meanwhile, the proposed method outperforms comparative algorithms in terms of task completion efficiency, safety robustness, and feasible solution ratio.Conclusions The proposed method realizes the collaborative effect of flow-field uncertainty perception on task allocation structure generation and evolutionary search regulation. It can provide technical support for multi-AUV swarm operations in complex marine environments.