《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (10): 3292-3299.DOI: 10.11772/j.issn.1001-9081.2021081387
所属专题: 前沿与综合应用
陈玉立1,2, 佟强1,2, 谌彤童3, 侯守璐1, 刘秀磊1,2
收稿日期:
2021-08-03
修回日期:
2021-11-12
接受日期:
2021-11-21
发布日期:
2022-01-07
出版日期:
2022-10-10
通讯作者:
佟强
作者简介:
第一联系人:陈玉立(1994—),男,河南周口人,硕士研究生,主要研究方向:机器学习、数据挖掘、时间序列预测基金资助:
Yuli CHEN1,2, Qiang TONG1,2, Tongtong CHEN3, Shoulu HOU1, Xiulei LIU1,2
Received:
2021-08-03
Revised:
2021-11-12
Accepted:
2021-11-21
Online:
2022-01-07
Published:
2022-10-10
Contact:
Qiang TONG
About author:
CHEN Yul, born in 1994, M. S. candidate. His research interests include machine learning, data mining, time series prediction.Supported by:
摘要:
针对单一长短时记忆(LSTM)网络在航迹预测上无法有效提取关键信息以及难以精准拟合数据分布等问题,提出基于注意力机制和生成对抗网络(GAN)的飞行器短期轨迹预测模型。首先,引入注意力机制对航迹赋予不同的权重,以提升航迹中重要特征的影响力;其次,基于LSTM提取航迹序列特征,并经汇聚层汇集时间步长内所有的飞行器特征;最后,利用GAN在对抗博弈下不断优化的特性来优化模型,从而提高模型的准确性。相较于社会生成对抗网络(SGAN),所提模型在处于爬升阶段的数据集上的平均位移误差(ADE)、最终位移误差(FDE)及最大位移误差(MDE)分别降低了20.0%、20.4%和18.3%。实验结果表明,所提模型能更精确地预测未来航迹。
中图分类号:
陈玉立, 佟强, 谌彤童, 侯守璐, 刘秀磊. 基于注意力机制和生成对抗网络的飞行器短期航迹预测模型[J]. 计算机应用, 2022, 42(10): 3292-3299.
Yuli CHEN, Qiang TONG, Tongtong CHEN, Shoulu HOU, Xiulei LIU. Short-term trajectory prediction model of aircraft based on attention mechanism and generative adversarial network[J]. Journal of Computer Applications, 2022, 42(10): 3292-3299.
发生时间 | 飞行器代码 | 纬度/(°) | 经度/(°) | 高度/m |
---|---|---|---|---|
1599440410 | 06a088 | 29.624 16 | -95.625 43 | 1 874.52 |
1599440420 | 06a088 | 29.631 89 | -95.612 77 | 1 866.90 |
1599440430 | 06a088 | 29.640 10 | -95.600 80 | 1 836.42 |
1599440440 | 06a088 | 29.648 34 | -95.590 29 | 1 783.08 |
1599440450 | 06a088 | 29.657 54 | -95.579 70 | 1 714.50 |
1599440460 | 06a088 | 29.665 69 | -95.570 64 | 1 638.30 |
表1 数据集样例
Tab. 1 Samples of datasets
发生时间 | 飞行器代码 | 纬度/(°) | 经度/(°) | 高度/m |
---|---|---|---|---|
1599440410 | 06a088 | 29.624 16 | -95.625 43 | 1 874.52 |
1599440420 | 06a088 | 29.631 89 | -95.612 77 | 1 866.90 |
1599440430 | 06a088 | 29.640 10 | -95.600 80 | 1 836.42 |
1599440440 | 06a088 | 29.648 34 | -95.590 29 | 1 783.08 |
1599440450 | 06a088 | 29.657 54 | -95.579 70 | 1 714.50 |
1599440460 | 06a088 | 29.665 69 | -95.570 64 | 1 638.30 |
模型 | ADE | FDE | MDE |
---|---|---|---|
BP | 0.022 075 | 0.021 804 | 0.085 027 |
LSTM | 0.082 516 | 0.087 059 | 0.487 775 |
GRU | 0.064 143 | 0.077 773 | 0.382 983 |
SGAN | 0.018 791 | 0.028 391 | 0.048 737 |
ATGAN | 0.014116 | 0.020845 | 0.038082 |
表2 不同模型在全阶段数据集上的预测误差
Tab. 2 Prediction errors of different models on dataset during all phases
模型 | ADE | FDE | MDE |
---|---|---|---|
BP | 0.022 075 | 0.021 804 | 0.085 027 |
LSTM | 0.082 516 | 0.087 059 | 0.487 775 |
GRU | 0.064 143 | 0.077 773 | 0.382 983 |
SGAN | 0.018 791 | 0.028 391 | 0.048 737 |
ATGAN | 0.014116 | 0.020845 | 0.038082 |
模型 | ADE | FDE | MDE |
---|---|---|---|
BP | 0.018 177 | 0.017 546 | 0.119 078 |
LSTM | 0.016 218 | 0.015 262 | 0.082 700 |
GRU | 0.012 724 | 0.011 947 | 0.065 207 |
SGAN | 0.008 729 | 0.014 992 | 0.047 028 |
ATGAN | 0.006984 | 0.011930 | 0.038422 |
表3 不同模型在处于爬升阶段数据集上的预测误差
Tab. 3 Prediction errors of different models on dataset during climb phase
模型 | ADE | FDE | MDE |
---|---|---|---|
BP | 0.018 177 | 0.017 546 | 0.119 078 |
LSTM | 0.016 218 | 0.015 262 | 0.082 700 |
GRU | 0.012 724 | 0.011 947 | 0.065 207 |
SGAN | 0.008 729 | 0.014 992 | 0.047 028 |
ATGAN | 0.006984 | 0.011930 | 0.038422 |
模型 | 训练时间/h | 预测时间/ms | 模型 | 训练时间/h | 预测时间/ms |
---|---|---|---|---|---|
BP | 1.03 | 0.02 | SGAN | 13.34 | 0.79 |
LSTM | 1.09 | 0.13 | ATGAN | 12.15 | 0.78 |
GRU | 1.10 | 0.08 |
表4 不同模型在全阶段数据集上的时间对比结果
Tab. 4 Time comparison results of different models on dataset during all phases
模型 | 训练时间/h | 预测时间/ms | 模型 | 训练时间/h | 预测时间/ms |
---|---|---|---|---|---|
BP | 1.03 | 0.02 | SGAN | 13.34 | 0.79 |
LSTM | 1.09 | 0.13 | ATGAN | 12.15 | 0.78 |
GRU | 1.10 | 0.08 |
1 | HAO S Q, CHENG S W, ZHANG Y P. A multi-aircraft conflict detection and resolution method for 4-dimensional trajectory-based operation[J]. Chinese Journal of Aeronautics, 2018, 31(7): 1579-1593. 10.1016/j.cja.2018.04.017 |
2 | SCHUSTER W. Trajectory prediction for future air traffic management — complex manoeuvres and taxiing[J]. The Aeronautical Journal, 2015, 119(1212): 121-143. 10.1017/s0001924000010307 |
3 | ZHANG J F, LIU J, HU R, et al. Online four dimensional trajectory prediction method based on aircraft intent updating[J]. Aerospace Science and Technology, 2018, 77: 774-787. 10.1016/j.ast.2018.03.037 |
4 | ZHOU Z J, CHEN J L, SHEN B B, et al. A trajectory prediction method based on aircraft motion model and grey theory[C]// Proceedings of the 2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference. Piscataway: IEEE, 2016: 1523-1527. 10.1109/imcec.2016.7867472 |
5 | KANESHIGE J, BENAVIDES J, SHARMA S, et al. Implementation of a trajectory prediction function for trajectory based operations[C]// Proceedings of the 2014 AIAA Atmospheric Flight Mechanics Conference. Reston, VA: AIAA, 2014: No.2198. 10.2514/6.2014-2198 |
6 | THIPPHAVONG D P, SCHULTZ C A, LEE A G, et al. Adaptive algorithm to improve trajectory prediction accuracy of climbing aircraft[J]. Journal of Guidance, Control, and Dynamics, 2013, 36(1): 15-24. 10.2514/1.58508 |
7 | 王涛波,黄宝军. 基于改进卡尔曼滤波的四维飞行航迹预测模型[J]. 计算机应用, 2014, 34(6): 1812-1815. 10.11772/j.issn.1001-9081.2014.06.1812 |
WANG T B, HUANG B J. 4D flight trajectory prediction model based on improved Kalman filter[J]. Journal of Computer Applications, 2014, 34(6): 1812-1815. 10.11772/j.issn.1001-9081.2014.06.1812 | |
8 | LYMPEROPOULOS I, LYGEROS J. Sequential Monte Carlo methods for multi-aircraft trajectory prediction in air traffic management[J]. International Journal of Adaptive Control and Signal Processing, 2010, 24(10): 830-849. 10.1002/acs.1174 |
9 | 谢丽,张军峰,隋东,等. 基于交互式多模型滤波算法的航迹预测[J]. 航空计算技术, 2012, 42(5): 68-70, 74. 10.3969/j.issn.1671-654X.2012.05.017 |
XIE L, ZHANG J F, SUI D, et al. Aircraft trajectory prediction based on interacting multiple model filtering algorithm[J]. Aeronautical Computing Technique, 2012, 42(5): 68-70, 74. 10.3969/j.issn.1671-654X.2012.05.017 | |
10 | WANG Z J, ZHANG X J, CAI K Q. An interacting multiple model based aircraft trajectory conformance prediction method[C]// Proceedings of the IEEE/AIAA 37th Digital Avionics Systems Conference. Piscataway: IEEE, 2018: 1-9. 10.1109/dasc.2018.8569251 |
11 | MAEDER U, MORARI M, BAUMGARTNER T I. Trajectory prediction for light aircraft[J]. Journal of Guidance, Control, and Dynamics, 2011, 34(4): 1112-1119. 10.2514/1.52124 |
12 | 汤新民,李腾,陈强超,等. 基于交互式多模型的短期4D航迹预测[J]. 武汉理工大学学报(交通科学与工程版), 2020, 44(1):39-45. 10.3963/j.issn.2095-3844.2020.01.008 |
TANG X M, LI T, CHEN Q C, et al. Short-term 4D trajectory prediction based on interactive multi-models[J]. Journal of Wuhan University of Technology (Transportation Science and Engineering), 2020, 44(1):39-45. 10.3963/j.issn.2095-3844.2020.01.008 | |
13 | DE LEEGE A M P, VAN PAASSEN M M, MULDER M. A machine learning approach to trajectory prediction[C]// Proceedings of the 2013 AIAA Guidance, Navigation, and Control Conference. Reston, VA: AIAA, 2013: No.4782. 10.2514/6.2013-4782 |
14 | TASTAMBEKOV K, PUECHMOREL S, DELAHAYE D, et al. Aircraft trajectory forecasting using local functional regression in Sobolev space[J]. Transportation Research Part C: Emerging Technologies, 2014, 39: 1-22. 10.1016/j.trc.2013.11.013 |
15 | 王涛波,黄宝军. 基于4D航迹的模糊聚类分析[J]. 交通信息与安全, 2013, 31(6):38-42. 10.3963/j.issn.1674-4861.2013.06.008 |
WANG T B, HUANG B J. Fuzzy cluster analysis of 4D trajectory based on ADS-B[J]. Journal of Transport Information and Safety, 2013, 31(6): 38-42. 10.3963/j.issn.1674-4861.2013.06.008 | |
16 | GEORGIOU H, PELEKIS N, SIDERIDIS S, et al. Semantic-aware aircraft trajectory prediction using flight plans[J]. International Journal of Data Science and Analytics, 2020, 9(2): 215-228. 10.1007/s41060-019-00182-4 |
17 | 马兰,高永胜. 基于ADS-B数据挖掘的4D航迹预测方法[J]. 中国民航大学学报, 2019, 37(4):1-4. 10.3969/j.issn.1674-5590.2019.04.001 |
MA L, GAO Y S. Four-dimensional trajectory prediction method based on ADS-B data mining[J]. Journal of Civil Aviation University of China, 2019, 37(4): 1-4. 10.3969/j.issn.1674-5590.2019.04.001 | |
18 | 钱夔,周颖,杨柳静,等. 基于BP神经网络的空中目标航迹预测模型[J]. 指挥信息系统与技术, 2017, 8(3): 54-58. 10.15908/j.cnki.cist.2017.03.010 |
QIAN K, ZHOU Y, YANG L J, et al. Aircraft target track prediction model based on BP neural network[J]. Command Information System and Technology, 2017, 8(3): 54-58. 10.15908/j.cnki.cist.2017.03.010 | |
19 | WU Z J, TIAN S, MA L. A 4D trajectory prediction model based on the BP neural network[J]. Journal of Intelligent Systems, 2020, 29(1): 1545-1557. 10.1515/jisys-2019-0077 |
20 | NAESSENS H, PHILIP T, PIATEK M, et al. Predicting flight routes with a deep neural network in the operational air traffic flow and capacity management system[EB/OL]. (2017-12-17) [2021-05-25].. |
21 | SHI Z Y, XU M, PAN Q, et al. LSTM-based flight trajectory prediction[C]// Proceedings of the 2018 International Joint Conference on Neural Networks. Piscataway: IEEE, 2018: 1-8. 10.1109/ijcnn.2018.8489734 |
22 | PANG Y T, XU N, LIU Y M. Aircraft trajectory prediction using LSTM neural network with embedded convolutional layer[C]// Proceedings of the 11th Annual Conference of the Prognostics and Health Management Society. [S.l.]: PHM Society, 2019: No.849. 10.36001/phmconf.2019.v11i1.849 |
23 | HAN P, YUE J C, FANG C, et al. Short-term 4D trajectory prediction based on LSTM neural network[C]// Proceedings of the SPIE 11427, 2nd Target Recognition and Artificial Intelligence Summit Forum International Society for Optics and Photonics. Bellingham, WA: SPIE, 2020: No.114270M. 10.1117/12.2550425 |
24 | 张宏鹏,黄长强,轩永波,等. 用门控循环单元实时预测空战飞行轨迹[J]. 系统工程与电子技术, 2020, 42(11): 2546-2552. 10.3969/j.issn.1001-506X.2020.11.17 |
ZHANG H P, HUANG C Q, XUAN Y B, et al. Real-time prediction of air combat flight trajectory using GRU[J]. Systems Engineering and Electronics, 2020, 42(11): 2546-2552. 10.3969/j.issn.1001-506X.2020.11.17 | |
25 | BAKLACIOGLU T, CAVCAR M. Aero-propulsive modelling for climb and descent trajectory prediction of transport aircraft using genetic algorithms[J]. The Aeronautical Journal, 2014, 118(1199): 65-79. 10.1017/s0001924000008939 |
26 | ZHANG Z X, YANG R N, FANG Y H. LSTM network based on antlion optimization and its application in flight trajectory prediction[C]// Proceedings of the 2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference. Piscataway: IEEE, 2018: 1658-1662. 10.1109/imcec.2018.8469476 |
27 | QIAO S J, SHEN D Y, WANG X T, et al. A self-adaptive parameter selection trajectory prediction approach via hidden Markov models[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(1): 284-296. 10.1109/tits.2014.2331758 |
28 | 石庆研,岳聚财,韩萍,等. 基于LSTM-ARIMA模型的短期航班飞行轨迹预测[J]. 信号处理, 2019, 35(12): 2000-2009. |
SHI Q Y, YUE J C, HAN P, et al. Short-term flight trajectory prediction based on LSTM-ARIMA model[J]. Journal of Signal Processing, 2019, 35(12): 2000-2009. | |
29 | MA L, TIAN S. A hybrid CNN-LSTM model for aircraft 4D trajectory prediction[J]. IEEE Access, 2020, 8: 134668-134680. 10.1109/access.2020.3010963 |
30 | XU Z F, ZENG W L, CHU X, et al. Multi-aircraft trajectory collaborative prediction based on social long short-term memory network[J]. Aerospace, 2021, 8(4): No.115. 10.3390/aerospace8040115 |
31 | ZENG W L, QUAN Z B, ZHAO Z Y, et al. A deep learning approach for aircraft trajectory prediction in terminal airspace[J]. IEEE Access, 2020, 8: 151250-151266. 10.1109/access.2020.3016289 |
32 | MNIH V, HEESS N, GRAVES A, et al. Recurrent models of visual attention[C]// Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2014: 2204-2212. |
33 | FERNANDO T, DENMAN S, SRIDHARAN S, et al. Soft + Hardwired attention: an LSTM framework for human trajectory prediction and abnormal event detection[J]. Neural Networks, 2018, 108: 466-478. 10.1016/j.neunet.2018.09.002 |
34 | GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144. 10.1145/3422622 |
35 | GUPTA A, JOHNSON J, LI F F, et al. Social GAN: socially acceptable trajectories with generative adversarial networks[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 2255-2264. 10.1109/cvpr.2018.00240 |
36 | SCHÄFER M, STROHMEIER M, LENDERS V, et al. Bringing up OpenSky: a large-scale ADS-B sensor network for research[C]// Proceedings of the 13th International Symposium on Information Processing in Sensor Networks. Piscataway: IEEE, 2014: 83-94. 10.1109/ipsn.2014.6846743 |
37 | LIN Y, LI Q, GUO D Y, et al. Tensor completion-based trajectory imputation approach in air traffic control[J]. Aerospace Science and Technology, 2021, 114: No.106754. 10.1016/j.ast.2021.106754 |
38 | 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(11A):126-131. 10.11896/j.issn.1002-137X.2018.11A.022 |
QUAN B, YANG B C, HU K Q, et al. Prediction model of ship trajectory based on LSTM[J]. Computer Science, 2018, 45(11A):126-131. 10.11896/j.issn.1002-137X.2018.11A.022 | |
39 | YANG T, NAN Z X, ZHANG H, et al. Traffic agent trajectory prediction using social convolution and attention mechanism[C]// Proceedings of the 2020 IEEE Intelligent Vehicles Symposium. Piscataway: IEEE, 2020: 278-283. 10.1109/iv47402.2020.9304645 |
40 | BOTTOU L. Large-scale machine learning with stochastic gradient descent[C]// Proceedings of the COMPSTAT’2010: 19th International Conference on Computational Statistics. Berlin: Physica-Verlag HD, 2010: 177-186. 10.1007/978-3-7908-2604-3_16 |
41 | ZHOU J, WANG H D, WEI J L, et al. Adaptive moment estimation for polynomial nonlinear equalizer in PAM8-based optical interconnects[J]. Optics Express, 2019, 27(22): 32210-32216. 10.1364/oe.27.032210 |
42 | DE OLIVEIRA L S, GRUETZMACHER S B, TEIXEIRA J P. COVID-19 time series prediction[J]. Procedia Computer Science, 2021, 181:973-980. 10.1016/j.procs.2021.01.254 |
43 | PATACCHIOLA M, CANGELOSI A. Head pose estimation in the wild using convolutional neural networks and adaptive gradient methods[J]. Pattern Recognition, 2017, 71:132-143. 10.1016/j.patcog.2017.06.009 |
44 | MADSEN P T. Marine mammals and noise: problems with root mean square sound pressure levels for transients[J]. The Journal of the Acoustical Society of America, 2005, 117(6): 3952-3957. 10.1121/1.1921508 |
45 | YU H, JIN R, YANG S. On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization[C]// Proceedings of the 36th International Conference on Machine Learning. New York: JMLR.org, 2019: 7184-7193. |
[1] | 秦璟, 秦志光, 李发礼, 彭悦恒. 基于概率稀疏自注意力神经网络的重性抑郁疾患诊断[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2970-2974. |
[2] | 李力铤, 华蓓, 贺若舟, 徐况. 基于解耦注意力机制的多变量时序预测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2732-2738. |
[3] | 赵志强, 马培红, 黑新宏. 基于双重注意力机制的人群计数方法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2886-2892. |
[4] | 薛凯鹏, 徐涛, 廖春节. 融合自监督和多层交叉注意力的多模态情感分析网络[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2387-2392. |
[5] | 汪雨晴, 朱广丽, 段文杰, 李书羽, 周若彤. 基于交互注意力机制的心理咨询文本情感分类模型[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2393-2399. |
[6] | 高鹏淇, 黄鹤鸣, 樊永红. 融合坐标与多头注意力机制的交互语音情感识别[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2400-2406. |
[7] | 李钟华, 白云起, 王雪津, 黄雷雷, 林初俊, 廖诗宇. 基于图像增强的低照度人脸检测[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2588-2594. |
[8] | 莫尚斌, 王文君, 董凌, 高盛祥, 余正涛. 基于多路信息聚合协同解码的单通道语音增强[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2611-2617. |
[9] | 刘丽, 侯海金, 王安红, 张涛. 基于多尺度注意力的生成式信息隐藏算法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2102-2109. |
[10] | 徐松, 张文博, 王一帆. 基于时空信息的轻量视频显著性目标检测网络[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2192-2199. |
[11] | 李大海, 王忠华, 王振东. 结合空间域和频域信息的双分支低光照图像增强网络[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2175-2182. |
[12] | 魏文亮, 王阳萍, 岳彪, 王安政, 张哲. 基于光照权重分配和注意力的红外与可见光图像融合深度学习模型[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2183-2191. |
[13] | 熊武, 曹从军, 宋雪芳, 邵云龙, 王旭升. 基于多尺度混合域注意力机制的笔迹鉴别方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2225-2232. |
[14] | 李欢欢, 黄添强, 丁雪梅, 罗海峰, 黄丽清. 基于多尺度时空图卷积网络的交通出行需求预测[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2065-2072. |
[15] | 毛典辉, 李学博, 刘峻岭, 张登辉, 颜文婧. 基于并行异构图和序列注意力机制的中文实体关系抽取模型[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2018-2025. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||