基于改进遗传算法的无人水下航行器路径规划

针对无人水下航行器（Autonomous Underwater Vehicle，AUV）运动约束多，传统遗传算法的路径寻优效率低、收敛速度慢等问题，提出了一种改进遗传算法的 AUV 路径规划方法。该算法选用栅格法构建环境，使用路径长度、平滑度和危险区域作为评价函数。改进遗传算法种群初始化过程，引入周围点栅格提高收敛速度，同时结合灾变思想避免群体陷入局部最优解。该算法根据 AUV 最大转角的约束条件，设计了 AUV 平滑过程和删除过程，避免了 AUV 航行出现急停急转。仿真及湖上试验结果表明：改进遗传算法相比传统遗传算法，路径长度减少 11.4%，收敛速度加快 20.0%，且收敛路径满足 AUV 航行约束要求。

Path Planning for Unmanned Underwater Vehicles Based on Improved Genetic Algorithm

Aiming at the problems of unmanned underwater vehicles（AUVs）with many motion constraints as well as the low efficiency of path optimization and slow convergence speed of traditional genetic algorithm，an improved genetic algorithm path planning method for AUVs is proposed. The algorithm selects grid method to construct the environment，and uses path length，smoothness and dangerous area as evaluation function. The population initialization process of genetic algorithm is improved，the convergence speed is raised by introducing the grid of surrounding points，and the idea of catastrophe is combined to avoid the population falling into the local optimal solution. AUV smoothing process and deletion process are designed according to the constraints of AUV maximum turning angle to avoid sharp stop and turn of AUV navigation. The simulation and lake test results show that compared with the traditional genetic algorithm，the improved genetic algorithm reduces the path length by 11.4%，improves the convergence speed by 20.0%，and the convergence path meets the constraints of AUV navigation.