A Novel Cooperative Hunting Algorithm for Inhomogeneous Multiple Autonomous Underwater Vehicles

Abstract

Cooperative hunting of multi-autonomous underwater vehicle (AUV) is an important research topic. Current studies concentrate on AUVs with the same speed abilities and mostly do not consider their speed differences. In fact, AUVs in a hunting group are often of different types and possess different maximum sailing speeds. For inhomogeneous multi-AUV, a novel time competition mechanism is proposed to construct an efficient dynamic hunting alliance. Hunting team with AUVs possessing higher speed abilities is more suitable for the vast underwater environment. In the pursuing stage, AUV needs to act fast enough to avoid the escape of evader. To achieve a quick and accurate pursuit, a combined path planning approach is presented, which combines a Glasius bio-inspired neural network model and a belief function. Simulation experiments demonstrate the feasibility and efficiency of the proposed algorithm in the cooperative hunting of inhomogeneous multi-AUV under dynamic underwater environment with intelligent evaders and multi-obstacle.