二维环境模型由于平面表达局限，仅能呈现有限信息，导致路径规划效率低。为了解决上述问题，本文提出复杂开放水域下船舶避障路径自动规划研究。通过部署多类型传感器和多层面数据融合，构建三维环境模型，立体呈现水域地形与动态因素。基于该模型，利用摄像头采集图像，结合自适应直方图均衡化、改进Sobel算子及支持向量机（Support Vector Machine，SVM）模型，实现障碍物实时精准识别。通过改进蚁群算法并引入动态风险因素平滑初始路径，提高收敛速度，实现船舶避障路径自动规划。实验结果表明，本文提出的研究方法规划路径长度和迭代次数更优，提高了路径规划效率。
Due to the limitations of planar expression, two-dimensional environmental models can only present limited information, resulting in low efficiency in path planning. To address the aforementioned issues, a study is proposed on automatic planning of ship obstacle avoidance paths in complex open waters. By deploying multiple types of sensors and fusing data from multiple levels, a three-dimensional environment model is constructed to present the terrain and dynamic factors of the water area in a three-dimensional manner. Based on this model, using a camera to capture images, combined with adaptive histogram equalization, improved Sobel operator, and Support Vector Machine (SVM) model, real-time and accurate obstacle recognition is achieved. By improving the ant colony algorithm and introducing dynamic risk factors to smooth the initial path, the convergence speed is improved, and automatic planning of ship obstacle avoidance paths is achieved. The experimental results show that the proposed research method has better planning path length and iteration times, improving the efficiency of path planning.
2025,47(23): 56-60 收稿日期：2025-5-30
DOI：10.3404/j.issn.1672-7649.2025.23.008
分类号：U664
基金项目：国家自然科学基金资助项目（12345678）
作者简介：于海鹏(1985-),男,本科,讲师,研究方向为航海技术
参考文献：
[1] 龚立雄, 陈佳霖, 黄霄, 等. 基于改进Informed-RRT*算法的舰载机甲板平面路径规划[J]. 科学技术与工程, 2024, 24(17): 7429-7437.
[2] 孟凡齐, 孙潇潇, 朱金善, 等. 基于双向A*-APF算法的船舶路径规划研究[J]. 大连海洋大学学报, 2024, 39(3): 506-515.
[3] 张金奋, 王伦巍, 吴达, 等. 基于自适应步长快速搜索随机树算法的船舶避碰路径规划[J]. 中国航海, 2023, 46(4): 147-153+162.
[4] 孙茂伟, 范加利, 高富东, 等. 基于蚁群算法的舰载机甲板路径规划[J]. 火力与指挥控制, 2023, 48(7): 104-109+114.
[5] 田宇, 刘志全, 高妍南. 基于神经网络滑模的欠驱动船舶路径跟踪与避障协同控制[J]. 广东海洋大学学报, 2024, 44(5): 144-152.
[6] 颜明重, 李琛, 朱大奇. 基于生物启发神经网络的无人水面艇实时避障路径规划[J]. 上海海事大学学报, 2024, 45(3): 10-15+48.
[7] 庹玉龙, 康彩霞, 王莎莎, 等. 未知干扰下多船相邻交叉耦合同步编队避障控制[J]. 交通运输工程学报, 2023, 23(6): 314-326.
[8] 李光泽, 俞万能, 廖卫强, 等. 基于动态窗口法的近海水域船舶避障算法研究[J]. 中国舰船研究, 2024, 19(1): 230-237.
[9] 周治国, 邸顺帆. 基于Citespace的水面无人艇路径规划与避障算法研究[J]. 舰船科学技术, 2023, 45(16): 59-63.
[10] 杨琪森, 王慎执, 桑金楠, 等. 复杂开放水域下智能船舶路径规划与避障方法[J]. 计算机集成制造系统, 2022, 28(7): 2030-2040.
