Paper Infomation
A Flight Trajectory Prediction Method Based on Internal Relationships between Attributes
Full Text(PDF, 511KB)
Author: Liwei Wu, Yuqi Fan
Abstract: The rapid development of the aviation industry urgently requires airspace traffic management, and flight trajectory prediction is a core component of airspace traffic management. Flight trajectory is a multidimensional time series with rich spatio-temporal characteristics, and existing flight trajectory prediction methods only target the trajectory point temporal relationships, but not the implicit interrelationships among the trajectory point attributes. In this paper, a graph convolutional network (AR-GCN) based on the intra-attribute relationships is proposed for solving the flight track prediction problem. First, the network extracts the temporal features of each attribute and fuses them with the original features of the attribute to obtain the enhanced attribute features, then extracts the implicit relationships between attributes as inter-attribute relationship features. Secondly, the enhanced attribute features are used as nodes and the inter-attribute relationship features are used as edges to construct the inter-attribute relationship graph. Finally, the graph convolutional network is used to aggregate the attribute features. Based on the full fusion of the above features, we achieved high accuracy prediction of the trajectory. In this paper, experiments are conducted on ADS-B historical track data. We compare our method with the classical method and the proposed method. Experimental results show that our method achieves significant improvement in prediction accuracy.
Keywords: Deep Learning, Graph Convolution Neural Network, Flight Trajectory Prediction
References:
[1] Slattery R, Zhao Y. Trajectory synthesis for air traffic automation[J]. Journal of guidance, control, and dynamics, 1997, 20(2): 232-238.
[2] Gui G, Zhou Z, Wang J, et al. Machine learning aided air traffic flow analysis based on aviation big data[J]. IEEE Transactions on Vehicular Technology, 2020, 69(5): 4817-4826.
[3] 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.
[4] Wang C, Guo J, Shen Z. Prediction of 4D trajectory based on basic flight models[J]. Journal of southwest jiaotong university, 2009, 44(2): 295-300.
[5] Zhang J F, Jiang H, Wu X G, et al. 4D trajectory prediction based on BADA and aircraft intent[J]. Journal of Southwest of Jiaotong University, 2014, 49(3): 553-558.
[6] Jing X, Cui J, He H, et al. Attitude estimation for UAV using extended Kalman filter[C]//2017 29th Chinese Control And Decision Conference (CCDC). IEEE, 2017: 3307-3312.
[7] Xie L, Zhang J, Sui D, et al. Aircraft trajectory prediction based on interacting multiple model filtering algorithm[J]. Aeronautical Computing Technique, 2012, 42(5): 68-71.
[8] Han P, Wang W, Shi Q, et al. A combined online-learning model with K-means clustering and GRU neural networks for trajectory prediction[J]. Ad Hoc Networks, 2021, 117: 102476.
[9] Jang J G, Choi D, Jung J, et al. Zoom-svd: Fast and memory efficient method for extracting key patterns in an arbitrary time range[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 2018: 1083-1092.
[10] Paszke A, Gross S, Massa F, et al. Pytorch: An imperative style, high-performance deep learning library[J]. Advances in neural information processing systems, 2019, 32.
[11] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[12] 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.
[13] Maeder U, Morari M, Baumgartner T I. Trajectory prediction for light aircraft[J]. Journal of Guidance, Control, and Dynamics, 2011, 34(4): 1112-1119.
[14] Ayhan S, Samet H. Aircraft trajectory prediction made easy with predictive analytics[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016: 21-30.
[15] Song L, Shengli W, Dingbao X. Radar track prediction method based on BP neural network[J]. The Journal of Engineering, 2019, 2019(21): 8051-8055.
[16] Chen Y, Sun J, Lin Y, et al. Hybrid N-Inception-LSTM-Based Aircraft Coordinate Prediction Method for Secure Air Traffic[J]. IEEE Transactions on Intelligent Transportation Systems, 2021.
[17] Z. Shi, M. Xu, Q. Pan, B. Yan, and H. Zhang, ‘‘LSTM-based flight trajectory prediction,’’ in Proc. Int. Joint Conf. Neural Netw. (IJCNN), Rio de Janeiro, Brazil, Jul. 2018, pp. 1–8.
[18] Ma L , Tian S . A Hybrid CNN-LSTM Model for Aircraft 4D Trajectory Prediction[J]. IEEE Access, 2020, PP(99):1-1.