Open AccessAutomatic Pilot Ship Route Planning Based on A RRT Guided Genetic Algorithm
Author(s) -
Ping Xie,
Wenhao Li
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1550/3/032085
Subject(s) - crossover , roulette , genetic algorithm , computer science , motion planning , chromosome , fitness function , population , robustness (evolution) , algorithm , fitness proportionate selection , path (computing) , evaluation function , mathematical optimization , genetic operator , population based incremental learning , artificial intelligence , mathematics , machine learning , biochemistry , chemistry , geometry , demography , sociology , robot , gene , programming language
The reasonable and optimized navigation for an automatic pilot ship is one of the key technologies in ship bridge system. In this paper, a genetic algorithm based path planning method is introduced for this kind of problem. In order to build efficient chromosome to improve the searching efficiency, before the planning procedure of the GA, a traditional but efficient fast searching method - RRT is utilized to give a clue to build the chromosomes. In this paper, at first, a searching area is constructed based on the result of RRT and secondly, a GA based planning algorithm is proposed for the ship to find a path from the start to a target. The fitness function and genetic operator are selected by roulette to ensure the robustness of genetic algorithm. The diversity of population is enhanced by two point crossover operators. Finally, the simulation results show the effectiveness of the proposed algorithm.