基于改进蚁群优化算法的AUV三维路径规划  

Three-dimensional path planning of AUV based on improved ant colony optimization algorithm

作　　者：蒲兴成[1,2] 冼文杰 聂壮 PU Xingcheng;XIAN Wenjie;NIE Zhuang(School of Computer Science and Technology,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;School of Mathematics and Computer Science,Tongling University,Tongling 244061,China)

机构地区：[1]重庆邮电大学计算机科学与技术学院,重庆400065 [2]铜陵学院数学与计算机学院,安徽铜陵244061

出　　处：《智能系统学报》2024年第3期627-634,共8页CAAI Transactions on Intelligent Systems

基　　金：国家自然科学基金项目(61876200);安徽省质量工程项目(2022cxtd162);安徽省自然科学基金项目(2008085MG227);铜陵学院人才引进项目(R23010);安徽省重点研究与开发计划项目(202004a05020010);重庆市教委项目(KJZD-M202001901);重庆市科委项目(cstc2020jcyj-msxmX0895).

摘　　要：针对蚁群算法在三维路径规划时收敛速度慢且难以收敛至最优的缺点,提出一种新的改进蚁群算法,并将其应用于自主式水下机器人(autonomous underwater vehicle,AUV)三维路径规划。与现有算法相比,改进算法优点主要体现在3个方面:首先,引进伪随机状态转移概率提升算法全局搜索能力;其次,将距离和轨迹限定因子引入启发式函数,距离因子保证搜索不断趋近目标点,在轨迹限定因子约束下,轨迹累计转角更小,以此提升收敛速度和精度;最后,通过扩大信息素增量差距并逐步提高信息素衰减系数,进一步提高路径规划效率。实验结果表明,改进蚁群算法能够获得累计转角更小路径,且路径长度更小,收敛速度更快。A new and improved ant colony algorithm is proposed and applied to AUV in 3D path planning.This method addresses the disadvantages of slow convergence and difficulty in achieving the optimum of conventional ant colony algorithms in 3D path planning.Compared with existing algorithms,the improved algorithm mainly has three advantages.First,the pseudorandom state transition probability is introduced to improve the global search ability of the algorithm.Second,the distance and trajectory limitations are considered in the heuristic function,using the distance factor to ensure the search continues to approach the target point.Under the constraint of trajectory limitation,the cumulative rotation angle of the trajectory is small,thereby increasing the convergence speed and accuracy.Finally,the path planning efficiency can be further improved by expanding the incremental gap of pheromones and gradually increasing the attenuation coefficient of pheromones.Test results show that,by using the improved ant colony algorithm,a reduced path of the accumulative turning angle can be obtained,the path length decreases,and the convergence speed accelerates.

关 键 词：路径规划 改进蚁群算法 启发函数 信息素更新 收敛速度 三维路径规划 自主水下机器人 转移概率 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]