Dynamic path planning of a three-dimensional underwater AUV based on an adaptive genetic algorithm

Abstract

Aiming at the problems of low global path quality and poor dynamic obstacle avoidance performance in underwater three-dimensional AUV autonomous path planning, an AUV global path planning method based on an adaptive genetic algorithm (AGA) is proposed in this paper. First, the traditional genetic algorithm are optimized to reduce the time of global path generation and improve the quality of global path generation. The path optimization strategy based on the collision detection mechanism is used to optimize the global path. Then, a local obstacle avoidance strategy based on the vector artificial potential field method (VAPF) is proposed. The space vector method is used to improve the calculation method of the resultant force direction to improve the calculation efficiency of the algorithm. Finally, the key path point is used as the local target point, and local obstacle avoidance is carried out under the guidance of the vector artificial potential field method. The simulation results show that the adaptive genetic algorithm can generate effective and high-quality global paths in a three-dimensional underwater environment. The new obstacle avoidance strategy can make AUVs effectively avoid all kinds of obstacles and reduce the obstacle avoidance cost of AUVs.