FROM: A Fish Recognition-Inspired Optimization Method for Multi-Agent Decision-Making Problems with a Fluid Environment.

Underwater multi-agent systems face critical hydrodynamic constraints that significantly degrade the performance of conventional constraint optimization algorithms in dynamic fluid environments. To meet the needs of underwater multi-agent applications, a fish recognition-inspired optimization method (FROM) is proposed in this paper. The proposed method introduces the characteristics of fish recognition. There are two major improvements in the proposed method: the neighbor topology improvement based on vision recognition and the learning strategies improvement based on hydrodynamic recognition. The computational complexity of the proposed algorithm was analyzed, and it was found to be acceptable. The statistical analysis of the experimental results shows that the FROM algorithm performs better than other algorithms in terms of minimum, maximum, standard deviation, mean, and median values calculated from objective functions. With solid experiment results, we conclude that the proposed FROM algorithm is a better solution to solve multi-agent decision-making problems with fluid environment constraints.