针对水下机器人在运用于蚁群计算求解路线规划问题时的收束速度过慢，较易进入局部最优求解，以及搜索速度的低下等现象，提出一种可以应用于水下机器人中的混合蚁群计算方法。首先，使用栅格法构建问题中的环境模式，并在此基础上采用A*算法更新初始信息素浓度，在信息素初期，也可以起到指导作用；其次，通过对蚁群计算的像素更新方法和节点转移概率方法中的启发方法加以改进，来提高算法的精确程度；最后，通过对PYTHON仿真试验证明，该方法的收敛速度和目标搜索寻优时间都得以提高。
In view of the phenomenon that traditional robots are used in ant colony computing to solve route planning problems, such as too slow beam closing speed, easy to enter local optimal solution, and low search speed, A new method is provided for hybrid ant colony computing in traditional robots. First, the grid method is used to construct the environment model in the problem, and on this basis, algorithm A is used to update the initial pheromone concentration in the initial stage, pheromone can also play a guiding role. Secondly, it can improve the pixel update method of ant colony calculation and the heuristic method of node transfer probability method to improve the accuracy of the algorithm. Finally, PYTHON simulation experiment proves that the convergence speed and target search optimization time of this method can improve the path planning method of the algorithm.
2025,47(9): 96-101 收稿日期：2024-5-17
DOI：10.3404/j.issn.1672-7649.2025.09.017
分类号：TP242
作者简介：张代雨（1988-），男，副教授，研究方向为水下航行器多学科设计优化
参考文献：
[1] GASPARETTO A, BOSCARIOL P, LANZUTTI A, et al. Path planning and trajectory planning algorithms: a general overview[J]. Motion and Operation Planning of Robotic Systems: Background and Practical Approaches, 2015: 3-27.
[2] JOHNSON D B. A note on dijkstra's shortest path algorithm[J]. Journal of the ACM (JACM), 1973, 20(3): 385-388.
[3] BERTSIMAS D, TSITSIKLIS J. Simulated annealing[J]. Statistical Science, 1993, 8(1): 10-15.
[4] KENNEDY J, EBERHART R. Particle swarm optimization[C]//Proceedings of ICNN'95-international Conference On Neural Networks. IEEE, 1995.
[5] 周怀芳, 张华, 霍建文, 等. 基于混合蚁群算法的核应急车辆疏散路径规划[J]. 辐射研究与辐射工艺学报, 2023, 41(6): 67-80.
[6] 李三平, 袁龙强, 吴立国, 等. 基于改进融合蚁群算法的移动机器人路径规划[J]. 机械设计, 2023, 40(10): 76-84.
[7] 毛寿祺, 杨平, 高迪驹, 等. 基于细菌觅食-改进蚁群优算法的水面无人船路径规划[J]. 控制工程, 2024, 31(4): 608-616.
[8] 符运来, 王魏, 刘妙男, 等. 基于改进P-RRT*算法的无人船路径规划 [J/OL]. 控制工程, 1-8
[9] 封声飞, 雷琦, 吴文烈, 等. 自适应蚁群算法的移动机器人路径规划[J]. 计算机工程与应用, 2019, 55(17): 35-43.
[10] KHALED A , FARID K. Mobile robot path planning using an improved ant colonyoptimization. International Journal of Advanced Robotic Systems, 2018, 15(3), 172988141877467.
[11] COLORNIA, DORIGOM, MANIEZZOV, etal. Distributed optimization by antcolonies[C]//Proceedings of European Conference on Artificial Life, Paris: Elsevier Publishing, 1991.
[12] 万晓凤, 胡伟, 方武义, 等. 基于改进蚁群算法的机器人路径规划研究[J]. 计算机工程与应用, 2014, 50(18): 63-66.
[13] 叶小勇, 雷勇, 侯海军. 蚁群算法在全局最优路径寻优中的应用[J]. 系统仿真学报, 2007(24): 5643-5647.
