基于卡尔曼滤波算法展开的飞行目标轨迹预测

doi:10.12305/j.issn.1001-506X.2023.06.25

摘要/Abstract

摘要：

目标轨迹预测是保证目标航行安全、规划飞行航迹和搜寻空中目标等任务的关键技术，在军事和交通管制等方面具有重要意义。针对传统飞行目标轨迹预测方法模型较为简化且预测精度较低的问题，提出了基于卡尔曼滤波算法展开的深度神经网络模型, 用于飞行目标的轨迹预测任务。该模型通过长短时记忆(long short-term memory, LSTM)网络从目标的航迹数据中学习目标的运动状态，再利用卡尔曼滤波算法对LSTM预测的目标状态估计值进行动态修正，其有效结合了卡尔曼滤波算法和深度神经网络各自的优势。在仿真数据和真实数据上的实验验证了所提模型较其他网络模型对飞行目标轨迹预测的准确性和有效性优势。

关键词: 卡尔曼滤波, 轨迹预测, 长短时记忆网络, 算法展开

Abstract:

Target track prediction is a key technology to ensure the navigation safety of the target, to plan the flight path and to search the air target. It is of great significance in military and traffic control. Aiming at the problem that the traditional air target track prediction method model is relatively simplified and the prediction accuracy is low, a deep neural network based on the Kalman filter algorithm for the air target track prediction task is proposed. The model uses long short-term memory (LSTM) network to learn the target motion model from the track data of air targets, and then uses the Kalman filter algorithm to dynamically modify the estimated target state generated by LSTM, which effectively combines the advantages of the Kalman filter algorithm and deep neural network. Experiments on simulation data and real data verify the accuracy and effectiveness of the proposed model compared with other networks models for air target track prediction.

Key words: Kalman filter, track prediction, long short-term memory (LSTM) network, algorithm unfolding

中图分类号:

V212

戴礼灿, 刘欣, 张海瀛, 代翔, 王成刚. 基于卡尔曼滤波算法展开的飞行目标轨迹预测[J]. 系统工程与电子技术, 2023, 45(6): 1814-1820.

Lican DAI, Xin LIU, Haiying ZHANG, Xiang DAI, Chenggang WANG. Flight target track prediction based on Kalman filter algorithm unfolding[J]. Systems Engineering and Electronics, 2023, 45(6): 1814-1820.

图/表 12

图1

图2

图3

图4

图5

表1

表2

图6

表3

图7

图8

表4

参考文献 27

28	BENGIO Y , SIMARD P , FRASCONI P . Learning long-term dependencies with gradient descent is difficult[J]. IEEE Trans.on Neural Networks, 1994, 5 (2): 157- 166.
29	GREFF K , SRIVASTAVA R K , KOUTNIK J , et al. LSTM: a search space odyssey[J]. IEEE Trans.on Neural Networks and Learning Systems, 2016, 28 (10): 2222- 2232.
30	SHERSTINSKY A . Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network[J]. Physica D: Nonlinear Phenomena, 2020, 404, 132306.
31	GLOROT X, BENGIO Y. Understanding the difficulty of training deep feedforward neural networks[C]//Proc. of the 13th International Conference on Artificial Intelligence and Statistics, 2010.
32	KINGMA D P, BA J. Adam: a method for stochastic optimization[EB/OL]. [2022-01-07]. https://arxiv.org/abs/1412.6980.
1	ZENG W L , CHU X , XU Z F , et al. Aircraft 4D trajectory prediction in civil aviation: a review[J]. Aerospace, 2022, 9 (2): 91- 109. doi: 10.3390/aerospace9020091
2	LIU R W , LIANG M H , NIE J T , et al. Deep learning-powered vessel trajectory prediction for improving smart traffic services in maritime Internet of Things[J]. IEEE Trans.on Network Science and Engineering, 2022, 9 (5): 3080- 3094. doi: 10.1109/TNSE.2022.3140529
3	LEON F , GAVRILESCU M . A review of tracking and trajectory prediction methods for autonomous driving[J]. Mathematics, 2021, 9 (6): 660- 696. doi: 10.3390/math9060660
4	LYMPEROPOULOS I, LYGEROS J, LECCHINI A. Model based aircraft trajectory prediction during takeoff[C]//Proc. of the AIAA Guidance, Navigation, and Control Conference and Exhibit, 2006.
5	GALLO E. Quasi static atmospheric model for aircraft trajectory prediction and flight simulation[EB/OL]. [2022-01-07]. https://arxi.org/abs/2101.10744.
6	JIANG S Y , LUO X , HE L . Research on method of trajectory prediction in aircraft flight based on aircraft performance and historical track data[J]. Mathematical Problems in Engineering, 2021, 2021, 6688213.
7	SCHULTZ C, THIPPHAVONG D, ERZBERGER H. Adaptive trajectory prediction algorithm for climbing flights[C]//Proc. of the AIAA Guidance, Navigation, and Control Conference, 2012.
8	SCHUSTER W , PORRETTA M , OCHIENG W . High-accuracy four-dimensional trajectory prediction for civil aircraft[J]. The Aeronautical Journal, 2012, 116 (1175): 45- 66. doi: 10.1017/S0001924000006618
9	BENAVIDES J V, KANESHIGE J, SHARMA S, et al. Implementation of a trajectory prediction function for trajectory based operations[C]//Proc. of the AIAA Atmospheric Flight Mechanics Conference, 2014.
10	LIU W , LIANG X , ZHENG M . Dynamic model informed human motion prediction based on unscented kalman filter[J]. IEEE/ASME Trans.on Mechatronics, 2022, 27 (6): 5287- 5295. doi: 10.1109/TMECH.2022.3173167
11	JULIER S J, UHLMANN J K. New extension of the Kalman filter to nonlinear systems[C]//Proc. of the Signal Processing, Sensor Fusion, and Target Recognition VI. International Society for Optics and Photonics, 1997.
12	GUO G , ZHAO S J . 3D multi-object tracking with adaptive cubature Kalman filter for autonomous driving[J]. IEEE Trans.on Intelligent Vehicles, 2023, 8 (1): 512- 519. doi: 10.1109/TIV.2022.3158419
13	QIAO S J , HAN N , ZHU X W , et al. A dynamic trajectory prediction algorithm based on Kalman filter[J]. Acta Electonica Sinica, 2018, 46 (2): 418- 423.
14	CHOI H C , DENG C , HWANG I . Hybrid machine learning and estimation-based flight trajectory prediction in terminal airspace[J]. IEEE Access, 2021, 9, 151186- 151197. doi: 10.1109/ACCESS.2021.3126117
15	HASHEMI S M , BOTEZ R M , GRIGORIE T L . New reliabi-lity studies of data-driven aircraft trajectory prediction[J]. Aerospace, 2020, 7 (10): 145- 152. doi: 10.3390/aerospace7100145
16	SCHIMPF N, KNOBLOCK E J, WANG Z, et al. Flight tra-jectory prediction based on hybrid-recurrent networks[C]// Proc. of the IEEE Cognitive Communications for Aerospace Applications Workshop, 2021.
17	PANG Y T, LIU Y M. Conditional generative adversarial networks (CGAN) for aircraft trajectory prediction considering weather effects[C]//Proc. of the AIAA Scitech Forum, 2020.
18	DALMAU R , PRATS X , VERHOEVEN R , et al. Comparison of various guidance strategies to achieve time constraints in optimal descents[J]. Journal of Guidance, Control, and Dynamics, 2019, 42 (7): 1612- 1621. doi: 10.2514/1.G004019
19	吕波, 王超. 改进的扩展卡尔曼滤波在航空器4D航迹预测算法中的应用[J]. 计算机应用, 2021, 41 (S1): 277- 282.
	LYU B , WANG C . Application of improved extended Kalman filter in 4D flight path prediction algorithm of aircraft[J]. Journal of Computer Applications, 2021, 41 (S1): 277- 282.
20	陈明强, 傅嘉赟. 基于无迹卡尔曼滤波的飞行航迹预测方法研究[J]. 计算机仿真, 2021, 38 (6): 27- 30. doi: 10.3969/j.issn.1006-9348.2021.06.006
	CHEN M Q , FU J Y . Research on flight path prediction method based on untraced Kalman filter[J]. Computer Simulation, 2021, 38 (6): 27- 30. doi: 10.3969/j.issn.1006-9348.2021.06.006
21	ZHANG X W, YU W Z. Research on the application of Kalman filter algorithm in aircraft trajectory analysis[C]//Proc. of the IEEE 7th International Conference on Intelligent Computing and Signal Processing, 2022.
22	RALAIVOLA L, D'ALCHE-BUC F. Time series filtering, smoothing and learning using the kernel Kalman filter[C]// Proc. of the IEEE International Joint Conference on Neural Networks, 2005.
23	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.
	QIAN K , ZHOU Y , YANG L J , et al. Air target track prediction model based on BP neural network[J]. Command Information System and Technology, 2017, 8 (3): 54- 58.
24	吴一凡, 冉晓旻. CNN神经网络在航迹预测中的应用[J]. 电子设计工程, 2019, 27 (12): 13- 20. doi: 10.3969/j.issn.1674-6236.2019.12.003
	WU Y F , RAN X M . Application of CNN neural network in track prediction[J]. Electronic Design Engineering, 2019, 27 (12): 13- 20. doi: 10.3969/j.issn.1674-6236.2019.12.003
25	GRAVES A, MOHAMED A, HINTON G. Speech recognition with deep recurrent neural networks[C]//Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2013.
26	HOCHREITER S , SCHMIDHUBER J . Long short-term memory[J]. Neural Computation, 1997, 9 (8): 1735- 1780. doi: 10.1162/neco.1997.9.8.1735
27	HOCHREITER S . Recurrent neural net learning and vanishing gradient[J]. International Journal of Uncertainity, Fuzziness and Knowledge-Based Systems, 1998, 6 (2): 107- 116. doi: 10.1142/S0218488598000094

硬件环境	处理器	Intel(R) Core(TM) i7-9750H CPU @ 2.60GHz
	显卡	NVIDIA GTX 1660Ti, 6 GB
	内存	16 GB
软件环境	操作系统	Windows 10(64bit)
	编程语言	Python 3.6
	编程框架	Pytorch 1.1
	集成开发环境	PyCharm 2020.2.1 (Community Edition)

仿真数据	参数方程	参数描述
1	$ \left\{\begin{array}{l} x=t \cos t \\ y=t \sin t \\ z=t \end{array}\right.$	0≤t≤8π, 时间点数量为200
2	$ \left\{\begin{array}{l} x=\sin t \\ y=\cos t \\ z=\cos (4 t) \end{array}\right.$	0≤t≤6π, 时间点数量为300
3	$ \left\{\begin{array}{l} x=\sin t \\ y=\cos t \\ z=\cos (2 t) \end{array}\right.$	0≤t≤6π, 时间点数量为300

模型	RNN	LSTM	KFU-LSTM
仿真数据1	0.078 16	0.047 24	0.011 06
仿真数据2	0.035 44	0.014 15	0.008 65
仿真数据3	0.040 10	0.011 42	0.008 34
真实数据	0.061 62	0.055 79	0.004 39

[1]	何益康, 张文瀚, 王振华, 何闻. 用于卫星应急恢复的太阳电池阵转角估计方法[J]. 系统工程与电子技术, 2023, 45(3): 797-805.
[2]	宋波涛, 许广亮. 基于LSTM与1DCNN的导弹轨迹预测方法[J]. 系统工程与电子技术, 2023, 45(2): 504-512.
[3]	李明杰, 周池军, 雷虎民, 邵雷, 骆长鑫. 基于控制参数估计的再入滑翔目标智能轨迹预测算法[J]. 系统工程与电子技术, 2023, 45(1): 221-233.
[4]	穆静, 严东升, 蔡远利, 王长元. 基于Masreliez-Martin的鲁棒分数阶容积卡尔曼滤波算法及应用[J]. 系统工程与电子技术, 2023, 45(1): 234-240.
[5]	徐庚, 何永旭, 张勇刚. 基于罗德里格斯参数的惯性系传递对准算法[J]. 系统工程与电子技术, 2022, 44(9): 2903-2913.
[6]	史浩然, 卢发兴, 祁江鑫, 杨光. 基于辅助信标的无人机协同目标跟踪[J]. 系统工程与电子技术, 2022, 44(7): 2302-2310.
[7]	翟光, 王妍欣, 孙一勇. 基于低轨星网的多目标协同跟踪滤波技术[J]. 系统工程与电子技术, 2022, 44(6): 1957-1967.
[8]	吉瑞萍, 张程祎, 梁彦, 王跃东. 基于LSTM的弹道导弹主动段轨迹预报[J]. 系统工程与电子技术, 2022, 44(6): 1968-1976.
[9]	董一平, 刘宁, 苏中, 王靖骁, 白宏阳. 基于AEKF的高速自旋飞行体组合导航方法[J]. 系统工程与电子技术, 2022, 44(6): 1977-1983.
[10]	李文华, 汪立新, 沈强, 李灿, 吴宗收. 基于鲁棒EKF的MEMS-INS/GNSS/VO组合导航方法[J]. 系统工程与电子技术, 2022, 44(6): 1994-2000.
[11]	侯召国, 王华伟, 周良, 付强. 基于改进深度残差网络的旋转机械故障诊断[J]. 系统工程与电子技术, 2022, 44(6): 2051-2059.
[12]	孙世岩, 张钢, 梁伟阁, 佘博, 田福庆. 基于时间序列数据扩增和BLSTM的滚动轴承剩余寿命预测方法[J]. 系统工程与电子技术, 2022, 44(3): 1060-1068.
[13]	王琪, 廖志忠, 燕飞. 基于概率数据关联的雷达导引头抗速度拖引干扰算法[J]. 系统工程与电子技术, 2022, 44(2): 448-454.
[14]	刘艺, 周晓雄, 程广俊. 高动态跳频载波跟踪技术[J]. 系统工程与电子技术, 2022, 44(2): 677-683.
[15]	孙照强, 王志贵, 孟飞, 李陆雨, 于中, 陈燕. 基于EKF及弹道方程的弹道目标跟踪滤波器设计[J]. 系统工程与电子技术, 2022, 44(10): 3207-3212.