基于改进蚁群算法的水下自主航行机器人路径规划  

AUV path planning based on improved ant colony algorithm

作　　者：刘雨青[1] 向军 曹守启[1] LIU Yu-qing;XIANG Jun;CAO Shou-qi(College of Engineering,Shanghai Ocean University,Shanghai 201306,China)

机构地区：[1]上海海洋大学工程学院,上海201306

出　　处：《计算机工程与科学》2022年第3期536-544,共9页Computer Engineering & Science

基　　金：国家重点研发计划(2019YFD0900803)。

摘　　要：为解决水下机器人AUV自主航行问题,在水底环境状态已知的条件下,利用一种改进的蚁群算法研究AUV在复杂水底环境下的路径规划问题。首先基于栅格法建立水下三维环境模型,在该模型中每只蚂蚁采用分层前进与栅格平面法相结合的搜索模式搜索路径。根据水下自主机器人的速度和在水底的受力情况,来确定水下机器人能耗模型和路径规划的数学模型。在传统蚁群算法的基础上,基于Dijkstra算法改进初始信息素分配,考虑到水下水流的作用,不同的路径点消耗的能量有所差异,因此构造新的启发函数来消除这种影响。通过基于线性回归的信息素更新方式来优化算法的收敛速度及求解质量。最后在使用改进的蚁群算法规划出来的路径基础上,采用贝塞尔曲线改善路径的平滑性,以便于AUV跟踪该路径。实验结果表明,改进的蚁群算法具有较强的全局搜索能力,收敛速度明显加快,规划出的路径明显优于传统蚁群算法和遗传算法的,适合水下机器人的路径规划。In order to solve the autonomous navigation problem of AUV,an improved ant colony optimization algorithm is used to study the path planning problem of AUV in complex underwater environment.Firstly,an underwater three-dimensional environment model is established based on the grid method.In this model,each ant uses the combination of layered forward and grid plane method to search the path.The energy consumption model and path planning mathematical model of AUV are determined by the speed of AUV and the force on the bottom.Based on the traditional ant colony algorithm,Dijkstra algorithm is used to improve the initial pheromone allocation.Considering the effect of underwater flow,the energy consumption of different path points is different,so a new heuristic function is constructed to eliminate the influence.The convergence speed and solution quality of the algorithm are optimized by pheromone replacement based on linear regression.Finally,based on the path planned by the improved ant colony algorithm,Bessel curve is used to improve the smoothness of the path,so as to facilitate AUV to track the path.The experimental results show that the improved ant colony algorithm has strong global search ability,the convergence speed is significantly faster,and the path planning is obviously better than the traditional ant colony algorithm and genetic algorithm,which is suitable for the path planning of underwater vehicles.

关 键 词：AUV路径规划 水下机器人 蚁群算法 信息素 水下环境建模 DIJKSTRA算法 线性回归模型 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置] TP182[自动化与计算机技术—控制科学与工程]