Method for Planning Collision Avoidance Paths of Maritime Ships Based on DDPG Algorithm
In order to improve the ability of collision avoidance path planning in the case of multiple ships encountering each other,this study proposes a collision avoidance path planning method for maritime vessels based on the DDPG(deep deterministic policy gradient)algorithm.Using grid method to establish a static global environment for ship navigation routes,and using artificial bee colony algorithm to design static initial paths.Calculate the risk level of collision between maritime vessels and other vessels in the event of multiple vessel encounters.Using the degree of danger as the input parameter of the DDPG algorithm,the planning results of collision avoidance paths for maritime vessels are output through training and learning.The experiment shows that after the planning of the method proposed in this paper,the maritime ships safely avoided the other three ships,did not encounter collision accidents,and safely reached the target point,proving the effectiveness of the method proposed in this paper.After applying the method in this article,the collision risk of maritime vessels is lower,indicating that the route planned by this method has stronger collision avoidance performance and improves the safety of maritime vessel navigation.
NETL
NSTL
万方数据
