融合概率地图法的改进蚁群优化算法 无人水面船路径规划

打开文本图片集

中图分类号：U664.82；TP18 文献标志码：A

Abstract： In view of the shortcomings of the traditional ant colony optimization（ACO） algorithm，such as slow convergence speed and easy to fall into local optima，the traditional ACO algorithm is improved to make it suitable for the global path planning of unmanned surface vehicles （USVs） in complex and real maritime environments. The paths planned by the probabilistic roadmap method （PRM） are used as the basis for the initial pheromone distribution of ACO algorithm，improving the convergence speed of the algorithm；the heuristic function considering both path length and directionality is designed to avoid the traditional ACO algorithm falling into local optima; the turning angle heuristic function is added to reduce the turning points of the traditional ACO algorithm； the obstacle density heuristic function is introduced to improve the ability of the traditional ACO algorithm to perceive obstacles when planning paths; the cubic

B-spline curve is used to further optimize the planning paths and improve the smoothness of paths. Simulation results show that：the improved ACO algorithm has obvious advantages in the number of turning points and the number of iterations，and has good stability on diferent sizes of raster maps and in real maritime environmets. The proposed improved ACO algorithm is of great significance in the practical application of navigation.

Key words：unmanned surface vehicle （USV）； path planning；ant colony optimization （ACOalgorithm；probabilistic roadmap method；real maritime environmet

0 引言

随着自主化技术的发展，普通船舶也在向无人水面船（unmannedsurfaecvehicle，USV）方向发展。（剩余10534字）