Research Of Ship Path Planning Algorithm

Marine transportation plays an extremely important role in the current trade between countries.The problem of ship path planning has been deeply affecting the development of marine transportation,and it has been developing towards the intelligent direction gradually.In recent years,with the introduction and wide application of various intelligent algorithms,the research of path planning has achieved good results,but it still exist some deficiencies.In this paper,through thorough research for the path planning problem,a simple model-based algorithm is presented to solve the problem of ship path planning,which aims at sailing distance,practical operability,safety,etc.Firstly,the Graham algorithm is used to establish a convex polygon model for the environment boundary and obstacles to simplify the environment model and improve the efficiency of the algorithm.According to the MAKLINK graph,the model of marine environment is established.Then the initial path is plotted on the established environment model by using the Dijkstra algorithm.Secondly,after completing path planning by use of linear decreasing inertia weight Particle Swarm Optimization,the route is smoothed by deleting redundant points to make it more practical and the ship can sail safely at a high speed.Aimed at the problem of getting into local extremum easily and poor accuracy deficiencies for linear decreasing inertia weight Particle Swarm Optimization,an improved method is proposed.By introducing chaos theory,the population is initialized by chaotic sequence to ensure the quality of the initial particles and the uniformity of distribution.The multi-population mechanism is established to balance the ability of global search and local search,which speeds up the convergence of the algorithm and improves its accuracy.Thirdly,the rolling window algorithm is applied to realize the path planning in the dynamic obstacle environment including typhoons.However,due to the possibility that plan path into local oscillation and the route is not a global minimum,an improved dynamic obstacle avoidance strategy is proposed,which combines global static route planning and local dynamic route planning.When the typhoon is detected in current rolling window,the dynamic route planning that is based on rolling windows refers to the path points that the global static route planning obtains.This algorithm can not only avoid effectively the threat area of typhoon,but also obtain the global shortest path,because the path points of global route planning are fully utilized,which follows the shortest path principle.Finally,based on Matlab GUI in the visual design module,route planning simulation system of the ship is established.Through the route planning simulation system,complete the modeling of marine environment,the initial path planning,global static path planning and simulation of dynamic obstacle avoidance.Through the simulation platform,the improved algorithm is compared with linear decreasing inertia weight Particle Swarm Optimization.The results of experiments show that the improved algorithm has better performance,especially in the complex environment,which can complete the global path planning quickly and get better result.