基于人工智能技术的复杂环境船舶自动导航系统

Design of ship automatic navigation system in complex environment based on artificial intelligence technology

作者单位:

1. 四川师范大学 计算机科学学院，四川 成都 610066;2. 四川城市职业学院信息技术学院，四川 成都 6101011. School of Computer Science and Technology, Sichuan Normal University, Chengdu 610066, China;2. School of Information Technology, Urban Vocational College of Sichuan, Chengdu 610101, China

人工智能技术;复杂环境;船舶自动导航;电子海图;航线规划;障碍物artificial intelligence technology; complex environment; ship automatic navigation; electronic chart; route planning; obstruction

为保证船舶安全平稳航行并顺利完成既定出海任务，设计基于人工智能技术的复杂环境船舶自动导航系统。该系统利用信息接收模块获取当前船舶海上位置信息和海域地图信息，使用无线通信模块将所得信息传送到电子海图管理模块，该模块依据接收到的信息，通过海图数据加载和纸质海图转换单元生成电子海图，在此基础上，航线设计与航路监视模块运用基于人工智能技术的复杂环境船舶航线规划方法，得出障碍物多布的复杂环境下的船舶航行最优路径，实现复杂环境船舶自动导航。实验结果表明：该系统能准确检测出船舶航行海域内的全部障碍物，规划的复杂环境船舶航线总航程较短，且对于静态和动态碍航物均具有较强的避障能力，自动导航效果优势显著。In order to ensure the safe and smooth navigation of ships and successfully complete the established sea mission, a ship automatic navigation system in complex environment based on artificial intelligence technology is designed. The system uses the information receiving module to obtain the current ship's sea position information and sea area map information, and uses the wireless communication module to transmit the obtained information to the electronic chart management module. According to the received information, the module generates the electronic chart through the chart data loading and paper chart conversion unit. On this basis, the route design and route monitoring module uses the ship route planning method in complex environment based on artificial intelligence technology. The optimal navigation path of ship in complex environment with many obstacles is obtained to realize the automatic navigation of ship in complex environment. The experimental results show that the system can accurately detect all the obstacles in the sea area. The total range of the ship route in the complex environment planned by the system is short, and it has strong obstacle avoidance ability for static and dynamic obstacles, and the advantage of automatic navigation effect is remarkable.

参考文献：

[1] 陈志超, 薛圻蒙, 罗凯, 等. 基于改进LOS导航算法的智能船舶自动靠泊控制研究[J]. 中国航海, 2021, 44: 126–133

[2] 肖长诗, 陈芊芊, 文元桥, 等. 基于LoRa的封闭水域船舶自动识别系统设计[J]. 船海工程, 2019, 48(1): 158–162+167

[3] 杨浩琪, 姚红革, 王诚, 等. 复杂场景下遥感船舶的检测与分割定位[J]. 计算机辅助设计与图形学学报, 2020, 32(3): 472–485

[4] 张闯, 郭晨, 张大恒. 船舶组合导航自适应迭代粒子滤波方法及应用[J]. 系统工程与电子技术, 2019, 41(4): 884–889

[5] 厉文涛, 聂晓明, 周健. 基于二维激光多普勒测速仪建立新组合导航系统的方法[J]. 中国激光, 2020, 47(3): 269–274

[6] 陈光武, 程鉴皓, 杨菊花, 等. 基于改进神经网络增强自适应UKF的组合导航系统[J]. 电子与信息学报, 2019, 41(7): 1766–1773

[7] 毛虎, 吴德伟, 卢虎. 对GPS接收机多音干扰参数优化设置及效能分析[J]. 系统工程与电子技术, 2019, 41(8): 1699–1704

[8] 李江卫, 马立烨, 吴仁攀, 等. 基于低成本单频u-blox接收机的GPS/BDS定向性能分析[J]. 大地测量与地球动力学, 2019, 39(3): 279–284

[9] 陈长林, 周成虎, 杨管妍, 等. 电子海图开放式图示表达模型及其构建方法[J]. 武汉大学学报:信息科学版, 2020, 45(3): 325–330

[10] 祝亢, 黄珍, 王绪明. 基于深度强化学习的智能船舶航迹跟踪控制[J]. 中国舰船研究, 2021, 16(1): 105–113