Underwater multi-AUV path planning method based on improved sparrow search algorithm

Abstract

The invention discloses an underwater multi-robot (AUV) path planning method based on an improved sparrow search algorithm, and the method comprises the steps: firstly, constructing a marine environment two-dimensional map through a grid method; then, performing task allocation on the multiple AUVs by using a particle swarm algorithm; secondly, due to the fact that the ocean environment is complex and the AUV is most affected by ocean currents when sailing underwater, in order to make full use of the ocean currents, combining fitness functions of a speed synthesis method and a sparrow search algorithm, and the algorithm comprehensively estimating the fitness value of each sparrow according to ocean current information and the current positions of the sparrows; after the algorithm is iterated continuously, a solution with an optimal adaptive value is found, and completing finally path planning. According to the invention, the dynamic safe obstacle avoidance of a plurality of AUVs is realized, and the collision-free optimal path of each AUV is quickly planned while the optimal task target is quickly allocated to each AUV.

Description

technical field [0001] The invention relates to a path planning method of an autonomous underwater vehicle (Autonomous Underwater Vehicle, AUV), in particular to an underwater multi-AUV path planning method based on an improved sparrow search algorithm. Background technique [0002] As the main tool for humans to explore the ocean, AUV can safely avoid obstacles when interacting with the external environment underwater. Planning a reasonable path is crucial to ensure the safety of underwater robots. At present, the multi-AUV system is more efficient and widely used than a single AUV. Scholars at home and abroad have done a lot of research on a single AUV system, but the research on multiple AUV systems is still a challenge. [0003] At present, the path planning of underwater robots is widely used in two-dimensional environment research, such as the typical A* algorithm, ant colony algorithm (Ant Colony Algorithm, ACO), artificial potential field method (Artificial Potentia...

AI Technical Summary

Problems solved by technology

Scholars at home and abroad have done a lot of research on a single AUV system, but the research on multiple AUV systems is still a challenge

[0003] At present, the path planning of underwater robots is widely used in two-dimensional environment research, such as the typical A* algorithm, ant colony algorithm (Ant Colony Algorithm, ACO), artificial potential field method (Artificial Potential Field Method, APF), etc., but all They have their own defects, such as the A* algorithm is slow in processing large-scale maps, the convergence speed of the ant colony algorithm is slow in the early stage, the artificial potential field method is easy to fall into local optimum, and it is not suitable for multi-AUV path planning

Images