路径规划是无人船自主导航的核心问题。由于无人船当前位置以及目标位置的确定受到障碍物影响，最佳航行路径的获取难度较大。为此，提出基于混合蚁群算法的无人船航行路径自主规划方法。采用栅格法构建无人船工作环境模型，由上至下、由左至右的对栅格完成编号处理，划分安全区域与障碍物区域。构建无人船航行路径自主规划数学模型，设定地形与威胁、航程上限以及路径平滑度等约束条件。针对蚁群算法初始搜索效率差等问题，将其与粒子群算法相结合，提出混合蚁群算法。利用该算法求解无人船航行路径自主规划数学模型。实验结果显示，研究方法具有较高的路径规划准确性，路径长度、平均能耗及路径规划时间指标均较优。
Path planning is the core problem of unmanned ship autonomous navigation. Because the current position and target position of unmanned ship are affected by obstacles, it is difficult to obtain the best navigation path. Therefore, an autonomous path planning method for unmanned ships based on hybrid ant colony algorithm is proposed. The working environment model of unmanned ship is constructed by grid method. The grid is numbered from top to bottom and from left to right, and the safe area and the obstacle area are divided. The mathematical model of autonomous navigation path planning of unmanned ship is constructed, and the constraint conditions such as terrain and threat, range upper limit and path smoothness are set. Aiming at the problem of poor initial search efficiency of ant colony algorithm, a hybrid ant colony algorithm is proposed by combining it with particle swarm optimization algorithm. This algorithm is used to solve the mathematical model of autonomous navigation path planning for unmanned ships. The experimental results show that the proposed method has higher path planning accuracy, and the indexes of path length, average energy consumption and path planning time are better.
2023,45(22): 93-96 收稿日期：2023-7-11
DOI：10.3404/j.issn.1672-7649.2023.22.017
分类号：TP391
作者简介：陈宇文(1995-),男,硕士,助理工程师,研究方向为路径优化
参考文献：
[1] 马小轩, 吴韵哲, 吴浩峻, 等. 基于改进人工势场法的水下自主航行器路径规划[J]. 船舶工程, 2021, 43(9): 89-93+100.
MA Xiaoxuan, WU Yunzhe, WU Haojun, et al. Path planning of autonomous underwater vehicle based on improved artificial potential field method[J]. Ship Engineering, 2021, 43(9): 89-93+100.
[2] 滕建平, 梁霄, 陶浩, 等. 无人水下航行器全局路径规划及有限时间跟踪控制[J]. 上海海事大学学报, 2022, 43(1): 1-7.
TENG Jianping, LIANG Xiao, TAO Hao, et al. Global path planning and finite-time tracking control of unmanned underwater vehicles[J]. Journal of Shanghai Maritime University, 2022, 43(1): 1-7.
[3] 王立鹏, 张智, 马山, 等. 考虑船舶操纵性约束的改进遗传算法航线规划[J]. 哈尔滨工程大学学报, 2021, 42(7): 1056-1062.
WANG Lipeng, ZHANG Zhi, MA Shan, et al. Improved genetic algorithm-based ship route planning considering ship maneuverability constraints[J]. Journal of Harbin Engineering University, 2021, 42(7): 1056-1062.
[4] 刘智萍, 周清华, 彭吉琼, 等. 基于免疫遗传优化的实时交通路径诱导方法[J]. 计算机仿真, 2022, 39(2): 98-101+418.
LIU Zhiping, ZHOU Qinghua, PENG Jiqiong, et al. Real-time traffic path induction method based on immune genetic optimization[J]. Computer Simulation, 2022, 39(2): 98-101+418.
[5] 胡致远, 王征, 杨洋, 等. 基于人工鱼群-蚁群算法的UUV三维全局路径规划[J]. 兵工学报, 2022, 43(7): 1676-1684.
HU Zhiyuan, WANG Zheng, YANG Yang, et al. Three-dimensional global path planning for UUV based on artificial fish swarm and ant colony algorithm[J]. Acta Armamentarii, 2022, 43(7): 1676-1684.
[6] 曹建秋, 徐鹏, 张广言. 基于贪心策略下混合蚁群算法的无人机航迹规划[J]. 重庆交通大学学报(自然科学版), 2021, 40(9): 9-16+23.
CAO Jianqiu, XU Peng, ZHANG Guangyan. Path Planning of UAV basedon hybrid ant colony algorithm under greedy strategy[J]. Journal of Chongqing Jiaotong University(Natural Sciences), 2021, 40(9): 9-16+23.
[7] 张岳星, 王轶群, 李硕, 等. 基于海图和改进粒子群优化算法的AUV全局路径规划[J]. 机器人, 2020, 42(1): 120-128.
ZHANG Yuexing, WANG Yiqun, LI Shuo, et al. Global path planning for AUV based on charts and the improved particle swarm optimization algorithm[J]. Robot, 2020, 42(1): 120-128.
[8] 荆学东, 杜黎童, 郭泰, 等. 基于混合参数蚁群算法的移动机器人路径规划[J]. 机床与液压, 2022, 50(9): 41-47.
JING Xuedong, DU Litong, GUO Tai, et al. Mobile robot path planning based on mixed parameter ant colony algorithm[J]. Machine Tool & Hydraulics, 2022, 50(9): 41-47.
