航行预测是无人艇关键技术之一。航行问题复杂度较高，传统的预测算法无法满足当前需求。为此，提出一种基于注意力机制-长短期记忆（Attention-Long Short Term Memory，Attention-LSTM）的多维船舶航行预测算法，结合船舶自动识别系统（Automatic Identification Systerm，AIS），采用注意力机制突出对船舶航行起关键作用的输入特征，实现对船舶未来时刻经度、纬度、航向、航速的预测。以成山角海域真实数据为例，进行仿真对比实验，结果表明所提方法具有更好的精确性和鲁棒性。
One of the key technologies of unmanned warships is the prediction of ship navigation. Because the problem of ship navigation has high complexity, the traditional prediction algorithm can not meet the needs of solving this kind of problem. For this reason, a ship navigation prediction algorithm based on Attention-LSTM neural network is proposed. In this prediction algorithm, the input features which play a key role in ship navigation are highlighted by combining AIS and the attention mechanism, so as to predict the longitude, latitude, heading, speed and other factors of the ship in the future. Taking the real data of Chengshanjiao sea area as an example, the simulation experiment is carried out, and according to the results, it can be found that the proposed algorithm has better accuracy and robustness.
2019,41(12): 177-180 收稿日期：2019-09-30
DOI：10.3404/j.issn.1672-7649.2019.12.034
分类号：U675.9
基金项目：山东省交通运输科技计划资助项目（2018B70）；山东交通学院研究生科技创新基金资助项目（2019YK013）
作者简介：徐国庆(1996 -),男,硕士研究生,研究方向为水上交通安全管理
参考文献：
[1] 徐铁, 蔡奉君, 胡勤友, 等. 基于卡尔曼滤波算法船舶AIS轨迹估计研究[J]. 现代电子技术, 2014, 37(05): 97–100+104
[2] 赵帅兵, 唐诚, 梁山, 等. 基于改进卡尔曼滤波的控制河段船舶航迹预测[J]. 计算机应用, 2012, 32(11): 3247–3250
[3] 王艳锋. 基于SVM的桥区水域失控船舶航迹对比分析[D]. 武汉理工大学, 2010.
[4] 刘锡铃, 阮群生, 龚子强. 船舶航行GPS定位轨迹的新预测模型[J]. 江南大学学报(自然科学版), 2014, 13(06): 686–692
[5] TONG Xiaopeng, MAO Zhe, CHEN Xu, et al.Vessel trajectory prediction in curving channel of inland river[C].//2015 International Conference on Transportation Information and Safety: 3rd International Conference on Transportation Information and Safety (ICTIS 2015), July 25-28, 2015, Wuhan, China. 2015: 706-714.
[6] 徐婷婷, 柳晓鸣, 杨鑫. 基于BP神经网络的船舶航迹实时预测[J]. 大连海事大学学报, 2012, 38(1): 9–11
[7] 甄荣, 金永兴, 胡勤友, 等. 基于AIS信息和BP神经网络的船舶航行行为预测[J]. 中国航海, 2017, 40(2): 6–10
[8] 权波, 杨博辰, 胡可奇, 等. 基于LSTM的船舶航迹预测模型[J]. 计算机科学, 2018, 45(S2): 126–131
[9] 杨博辰. 基于AIS的船舶轨迹分析的研究与应用[D].电子科技大学, 2018.
[10] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[M]//Supervised Sequence Labelling with Recurrent Neural Networks. Springer Berlin Heidelberg, 1997: 1735-1780.
[11] 司念文, 王衡军, 李伟, 等. 基于注意力长短时记忆网络的中文词性标注模型[J]. 计算机科学, 2018, 45(04): 66–70+82
[12] LIU Hao, ZENG Guangping, ZHANG Qingchuan, et al. Part-of-speech and postion attention mechanism based BLSTM for question answering system[P]. Other Conferences, 2018.
[13] 张昭昭, 乔俊飞, 余文. 多层自适应模块化神经网络结构设计[J]. 计算机学报, 2017, 40(12): 2827–2838
[14] JAFARIAN Ahmad, NIA Safa Measoomy, GOLMANKHANEH Alireza Khalili, et al. On artificial neural networks approach with new cost functions[J]. Applied Mathematics and Computation, 2018: 339
