基于航迹预测的无人机短时航迹偏离检测方法

doi:10.12305/j.issn.1001-506X.2024.08.17

摘要/Abstract

摘要：

保障无人机(unmanned aerial vehicle, UAV)飞行安全已经成为推动无人驾驶航空创新应用与规模发展的关键问题。针对UAV在低空结构化航路网络运行过程中由航迹偏离导致的安全隐患, 提出一种异常航迹检测方法(abnormal trajectory detection method, ATDM)。首先, 建立航迹数据预处理和重构模型, 构筑包含位置、速度、航向等多维属性的航迹数据。其次, 以具有多维属性的航迹数据为输入, 采用双向长短时记忆网络算法构建UAV短期航迹预测模型。最后, 基于历史航迹点和预测航迹点间的多维度局部异常因子, 将航迹偏离检测转化为航迹点密度分类问题, 建立UAV航迹偏离检测方法, 实现短时范围内航迹偏离状态的动态监测。结果表明, ATDM在短的预测时间范围内具有较好的精度优势和实时性。

关键词: 航迹异常检测, 航迹预测, 航迹偏离, 无人机

Abstract:

Safeguarding unmanned aerial vehicle (UAV) flight safety has become a key issue in promoting the innovative application and scale development of unmanned aviation. To solve the safety hazards caused by trajectory deviation during the operation of UAV in low-altitude structured airway networks, a abnormal trajectory detection method (ATDM) is proposed. Firstly, a trajectory data preprocessing and reconstruction model is established to construct the trajectory data containing multidimensional attributes such as position, velocity, heading and so on. Secondly, the UAV short-term trajectory prediction model is constructed by using the trajectory data with multi-dimensional attributes as input, and the bidirectional long and short-term memory network algorithm is used. Finally, based on the multidimensional local anomaly factor between historical and prediction trajectory points, the trajectory deviation detection is transformed into a density classification problem of the trajectory points, and the UAV trajectory deviation detection method is established to realize the dynamic monitoring of the trajectory deviation status in the short-time range. Results show that ATDM has better accuracy advantage and real-time performance in short prediction time range.

Key words: trajectory anomaly detection, trajectory prediction, trajectory deviation, unmanned aerial vehicle (UAV)

中图分类号:

钟罡, 周蒋颖, 杜森, 张洪海, 刘皞. 基于航迹预测的无人机短时航迹偏离检测方法[J]. 系统工程与电子技术, 2024, 46(8): 2696-2708.

Gang ZHONG, Jiangying ZHOU, Sen DU, Honghai ZHANG, Hao LIU. Short-time trajectory deviation detection method for UAV based on trajectory prediction[J]. Systems Engineering and Electronics, 2024, 46(8): 2696-2708.

图/表 25

图1

图2

图3

图4

图5

图6

图7

图8

表1

图9

表2

表3

图10

图11

图12

图13

图14

图15

图16

图17

表4

图18

图19

表5

图20

参考文献 34

1	MENOUAR H , GUVENC I , AKKAYA K , et al. UAV-enabled intelligent transportation systems for the smart city: applications and challenges[J]. IEEE Communications Magazine, 2017, 55 (3): 22- 28. doi: 10.1109/MCOM.2017.1600238CM
2	CHEN C M , YE Z , HU F , et al. Vehicle trajectory-clustering method based on road-network-sensitive features[J]. Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, 2021, 41 (1): 2357- 2375.
3	ZHU T L, XIE D F. Analysis of interdriver heterogeneity based on trajectory data with K-means clustering method[C]//Proc. of the International Conference on Sensor Network and Computer Engineering, 2016: 682-689.
4	JIN Y X , NIKITAS N , HU Q Y , et al. Maritime anomaly detection within coastal waters based on vessel trajectory clustering and naive Bayes classifier[J]. Journal of Navigation, 2017, 70 (3): 648- 670. doi: 10.1017/S0373463316000850
5	LIU S J , CHEN G , WEI L , et al. A novel compression approach for truck GPS trajectory data[J]. IET Intelligent Transport Systems, 2020, (5): 74- 83.
6	QI L , JI Y Y . Ship trajectory data compression algorithms for automatic identification system: comparison and analysis[J]. Journal of Water Resources and Ocean Science, 2020, 9 (2): 42- 47. doi: 10.11648/j.wros.20200902.11
7	GAO J B , CAI Z , YU W J , et al. Trajectory data compression algorithm based on ship navigation state and acceleration variation[J]. Journal of Marine Science and Engineering, 2023, 11 (1): 216. doi: 10.3390/jmse11010216
8	ZHONG G , ZHANG H H , ZHOU J Y , et al. Short-term 4D trajectory prediction for UAV based on spatio-temporal trajectory clustering[J]. IEEE Access, 2022, 10, 93362- 93380. doi: 10.1109/ACCESS.2022.3203428
9	WU X P , YANG H Y , HU C , et al. Long-term 4D trajectory prediction using generative adversarial networks[J]. Transportation Research Part C: Emerging Technologies, 2022, 136, 103554. doi: 10.1016/j.trc.2022.103554
10	LIN L , LI W Z , BI H K . Vehicle trajectory prediction using LSTMs with spatial-temporal attention mechanisms[J]. IEEE Intelligent Transportation Systems Magazine, 2021, 14 (2): 197- 208.
11	HUANG M , WASHINGTONY O , MACIAS J J E , et al. Accuracy evaluation of a new generic trajectory prediction model for unmanned aerial vehicles[J]. Aerospace Science and Technology, 2021, 119, 107160. doi: 10.1016/j.ast.2021.107160
12	ZHANG H H , YAN Y J , LI S , et al. UAV behavior-intention estimation method based on 4-D flight-trajectory prediction[J]. Sustainability, 2021, 13 (22): 12528. doi: 10.3390/su132212528
13	刘良旭, 乔少杰, 刘宾, 等. 基于R-Tree的高效异常轨迹检测算法[J]. 软件学报, 2009, 20 (9): 2426- 2435.
	LIU L X , QIAO S J , LIU B , et al. Efficient trajectory outlier detection algorithm based on R-Tree[J]. Journal of Software, 2009, 20 (9): 2426- 2435.
14	王志森, 张召悦, 冯朝辉, 等. 终端区飞行轨迹聚类分析及异常轨迹识别[J]. 科学技术与工程, 2022, 22 (9): 3807- 3814. doi: 10.3969/j.issn.1671-1815.2022.09.052
	WANG Z S , ZHANG Z Y , FENG Z H , et al. Cluster analysis and abnormal trajectories of flight trajectory in terminal area[J]. Science and Technology and Engineering, 2022, 22 (9): 3807- 3814. doi: 10.3969/j.issn.1671-1815.2022.09.052
15	吴建华, 吴琛, 刘文, 等. 船舶AIS轨迹异常的自动检测与修复算法[J]. 中国航海, 2017, 40 (1): 8-12, 101. doi: 10.3969/j.issn.1000-4653.2017.01.003
	WU J H , WU C , LIU W , et al. Automatic detection and restoration algorithm for trajectory anomalies of ship AIS[J]. Navigation of China, 2017, 40 (1): 8-12, 101. doi: 10.3969/j.issn.1000-4653.2017.01.003
16	姜佰辰, 关键, 周伟, 等. 海上交通的船舶异常行为挖掘识别分析[J]. 计算机仿真, 2017, 34 (6): 329- 334. doi: 10.3969/j.issn.1006-9348.2017.06.071
	JIANG B C , GUAN J , ZHOU W , et al. Vessel abnormal behaviors mining recognition analysis on maritime traffic[J]. Computer Simulation, 2017, 34 (6): 329- 334. doi: 10.3969/j.issn.1006-9348.2017.06.071
17	潘新龙, 王海鹏, 何友, 等. 基于多维航迹特征的异常行为检测方法[J]. 航空学报, 2017, 38 (4): 254- 263.
	PAN X L , WANG H P , HE Y , et al. Anomalous behavior detection method based on multi-dimensional trajectory characteristics[J]. Acta Aeronautica et Astronautica Sinica, 2017, 38 (4): 254- 263.
18	ZHAO K W , XIE X L , ZHANG X J . Maritime anomaly detection based on a support vector machine[J]. Soft Computing, 2022, 26 (21): 11553- 11566. doi: 10.1007/s00500-022-07409-w
19	刘朋. 基于监视数据的机动区航空器异常行为检测[D]. 天津: 中国民航大学, 2018.
	LIU P. Abnormal behavior detection for aircraft in maneuvering area based on surveillance data[D]. Tianjin: Civil Aviation University of China, 2018.
20	LUO P , WANG B H , LI T Y , et al. ADS-B anomaly data detection model based on VAE-SVDD[J]. Computers & Security, 2021, 104, 102213.
21	JI Y F , WANG L W , WU W L , et al. A method for LSTM-based trajectory modeling and abnormal trajectory detection[J]. IEEE Access, 2020, 8, 104063- 104073. doi: 10.1109/ACCESS.2020.2997967
22	NING S G , SUN J Z , LIU C , et al. Applications of deep learning in big data analytics for aircraft complex system anomaly detection[J]. Journal of Risk and Reliability, 2021, 235 (5): 923- 940.
23	CAO Y P , CAO J W , ZHOU Z G , et al. Aircraft track anomaly detection based on MOD-Bi-LSTM[J]. Electronics, 2021, 10 (9): 1007. doi: 10.3390/electronics10091007
24	XIAO K , ZHAO J Y , HE Y H , et al. Abnormal behavior detection scheme of UAV using recurrent neural networks[J]. IEEE Access, 2019, 7, 110293- 110305. doi: 10.1109/ACCESS.2019.2934188
25	LEI P R . A framework for anomaly detection in maritime tra-jectory behavior[J]. Knowledge & Information Systems, 2016, 47, 189- 214.
26	WANG Y K , LIU J X , LIU R W , et al. Data-driven methods for detection of abnormal ship behavior: progress and trends[J]. Ocean Engineering, 2023, 271 (1): 113673.
27	LIU H D , LIU Y , LI B , et al. Ship abnormal behavior detection method based on optimized GRU network[J]. Journal of Marine Science and Engineering, 2022, 110 (2): 249- 259.
28	GUO S Q , MOU J M , CHEN L Y , et al. An anomaly detection method for AIS trajectory based on kinematic interpolation[J]. Journal of Marine Science and Engineering, 2021, 2 (6): 609.
29	WANG X L , WANG Q . An abnormal traffic detection method using GCN-Bi-LSTM-attention in the internet of vehicles environment[J]. EURASIP Journal on Wireless Communications and Network, 2023, 2023, 70. doi: 10.1186/s13638-023-02274-z
30	YU W . Research on feature extraction of vehicle abnormal driving behaviour based on 5G internet of vehicles[J]. International Journal of Vehicle Design, 2021, 86 (1/4): 124- 142.
31	LI C N , FENG G W , JIA Y R . RETAD: vehicle trajectory anomaly detection based on reconstruction error[J]. International Journal of Data Warehousing and Mining, 2023, 19 (2): 316460.
32	ZHAO X J , SU J H , CAI J H , et al. Vehicle anomalous trajectory detection algorithm based on road network partition[J]. Applied Intelligence, 2021, 52 (8): 8820- 8838.
33	HUANG S E , FENG Y , LIU H X . A data-drivenmethod for falsified vehicle trajectory identification by anomaly detection[J]. Transportation Research Part C: Emerging Technologies, 2021, 128 (6): 103196.
34	CORRADO S J , PURANIKN T G , FISCHER O P , et al. A clustering-based quantitative analysis of the interdependent relationship between spatial and energy anomalies in ADS-B trajectory data[J]. Transportation Research Part C: Emerging Technologies, 2021, 131, 103331. doi: 10.1016/j.trc.2021.103331

名称	参数
深度学习框架	Tensorflow2.2.0
激活函数	Sigmoid/Tanh
损失函数	MSE
优化器	Adam
网络层数	256/128/5
训练轮次	50

特征	航迹点
时间	5/9/2022 15:39:36
编号	2
经度/(°)	118.781 848 31
纬度/(°)	31.941 673 23
高度/m	27.423
速度/(m/s)	0.09
航向/(°)	15

真实\预测	正常航迹	异常航迹
正常航迹	TP	FN
异常航迹	FP	TN

参数	k取值
参数	3	5	7	9
精度	0.895	0.902	0.888	0.885
召回率	0.991	0.992	0.996	1
F1得分	0.941	0.945	0.939	0.938

参数	模型
参数	LSTM	SVM	iForest	ATDM
精度	0.892	0.872	0.901	0.902
召回率	0.871	0.843	0.884	0.992
F1得分	0.881	0.857	0.892	0.945
是否需要标注	是	是	否	否