An algorithm for trajectory prediction of flight plan based on relative motion between positions

  • Yi Lin
  • Jian-wei Zhang
  • Hong LiuEmail author


Traditional methods for plan path prediction have low accuracy and stability. In this paper, we propose a novel approach for plan path prediction based on relative motion between positions (RMBP) by mining historical flight trajectories. A probability statistical model is introduced to model the stochastic factors during the whole flight process. The model object is the sequence of velocity vectors in the three-dimensional Earth space. First, we model the moving trend of aircraft including the speed (constant, acceleration, or deceleration), yaw (left, right, or straight), and pitch (climb, descent, or cruise) using a hidden Markov model (HMM) under the restrictions of aircraft performance parameters. Then, several Gaussian mixture models (GMMs) are used to describe the conditional distribution of each moving trend. Once the models are built, machine learning algorithms are applied to obtain the optimal parameters of the model from the historical training data. After completing the learning process, the velocity vector sequence of the flight is predicted by the proposed model under the Bayesian framework, so that we can use kinematic equations, depending on the moving patterns, to calculate the flight position at every radar acquisition cycle. To obtain higher prediction accuracy, a uniform interpolation method is used to correct the predicted position each second. Finally, a plan trajectory is concatenated by the predicted discrete points. Results of simulations with collected data demonstrate that this approach not only fulfils the goals of traditional methods, such as the prediction of fly-over time and altitude of waypoints along the planned route, but also can be used to plan a complete path for an aircraft with high accuracy. Experiments are conducted to demonstrate the superiority of this approach to some existing methods.

Key words

Velocity vector Hidden Markov model Gaussian mixture model Machine learning Plan path prediction Relative motion between positions (RMBP) 

CLC number



Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Alligier R, Gianazza D, Durand N, 2015. Machine learning and mass estimation method for ground–based aircraft climb prediction. IEEE Trans Intell Transp Syst, 16(6): 3138–3149. Google Scholar
  2. Ayhan S, Samet H, 2016. Aircraft trajectory prediction made easy with predictive analytics. ACM SIGKDD Int Conf on Knowledge Discovery & Data Mining, p.21–30.Google Scholar
  3. Barrios C, Motai Y, 2011. Improving estimation of vehicle’s trajectory using the latest global positioning system with Kalman filtering. IEEE Trans Instrum Meas, 60(12): 3747–3755. CrossRefGoogle Scholar
  4. Chen ZJ, 2010. Theory and Method of Airspace Management. Science Press, Beijing, China, p.217–227 (in Chinese).Google Scholar
  5. Ding ZM, Yang B, Güting RH, et al., 2015. Network–matched trajectory–based moving–object database: models and applications. IEEE Trans Intell Transp Syst, 16(4): 1918–1928. CrossRefGoogle Scholar
  6. Gardi A, Sabatini R, Ramasamy S, et al., 2013. 4–Dimensional trajectory negotiation and validation system for the next generation air traffic management. AIAA Guidance, Navigation, and Control Conf, p.1–15.CrossRefGoogle Scholar
  7. Hamed MG, Gianazza D, Serrurier M, et al., 2013. Statistical prediction of aircraft trajectory: regression methods vs point–mass model. 10th USA/Europe Air Traffic Management Research and Development Seminar, p.1–11.Google Scholar
  8. Jeung HY, Shen HT, Zhou XF, 2007. Mining trajectory patterns using hidden Markov models. Int Conf on Data Warehousing and Knowledge Discovery, p.470–480.Google Scholar
  9. Li Z, Li SH, Wu XL, 2015. General aircraft 4D flight trajectory prediction method based on data fusion. Int Conf on Machine Learning and Cybernetics, p.309–315.Google Scholar
  10. Lymperopoulos I, Lygeros J, 2010. Sequential Monte Carlo methods for multi–aircraft trajectory prediction in air traffic management. Int J Adapt Contr Signal Process, 24(10):830–849. MathSciNetCrossRefzbMATHGoogle Scholar
  11. Mahler PSR, 2011. Statistical Multisource–Multitarget Information Fusion. National Defense Industry Press, Beijing, China, p.27–37 (in Chinese).zbMATHGoogle Scholar
  12. Morzy M, 2007. Mining frequent trajectories of moving objects for location prediction. Proc 5th Int Conf on Machine Learning and Data Mining in Pattern Recognition, p.667–680.CrossRefGoogle Scholar
  13. Naseri A, Neogi N, Rantanen E, 2007. Stockastic hybrid models with applications to air traffic management. AIAA Guidance, Navigation, and Control Conf and Exhibit, p.370–379.Google Scholar
  14. Prento T, Thom A, Blunck H, et al., 2015. Making sense of trajectory data in indoor spaces. IEEE Int Conf on Mobile Data Management, p.9424–9436.Google Scholar
  15. Qiao MY, Bian W, Xu RYD, et al., 2015. Diversified hidden Markov models for sequential labeling. IEEE Trans Knowl Data Eng, 27(11):2947–2960. CrossRefGoogle Scholar
  16. Qiao SJ, Jin K, Han N, et al., 2015a. Trajectory prediction algorithm based on Gaussian mixture model. J Softw, 26(5):1048–1063.MathSciNetGoogle Scholar
  17. Qiao SJ, Shen DY, Wang XT, et al., 2015b. A self–adaptive parameter selection trajectory prediction approach via hidden Markov models. IEEE Trans Intell Transp Syst, 16(1):284–296. CrossRefGoogle Scholar
  18. Shanmuganathan SK, 2014. A HMM–Based Prediction Model for Spatio–Temporal Trajectories. MS Thesis, the University of Texas at Arlington, Dallas, USA.Google Scholar
  19. Song LL, 2012. A 4–D trajectory prediction method based on set of historical trajectory. Comput Technol Dev, 12:11–14.Google Scholar
  20. Tang KS, Zhu SF, Xu YQ, et al., 2016. Modeling drivers’ dynamic decision–making behavior during the phase transition period: an analytical approach based on hidden Markov model theory. IEEE Trans Intell Transp Syst, 17(1):206–214. CrossRefGoogle Scholar
  21. Tang XM, Chen P, Zhang Y, 2015a. 4D trajectory estimation based on nominal flight profile extraction and airway meteorological forecast revision. Aerosp Sci Technol, 45:387–397. CrossRefGoogle Scholar
  22. Tang XM, Gu JW, Shen ZY, et al., 2015b. A flight profile clustering method combining TWED with K–means algorithm for 4D trajectory prediction. Integrated Communication, Navigation, and Surveillance Conf, p.1–9.Google Scholar
  23. Tang XM, Zhou L, Shen ZY, et al., 2015c. 4D trajectory prediction of aircraft taxiing based on fitting velocity profile. 15th COTA Int Conf of Transportation Professionals, p.1–12.Google Scholar
  24. Wandelt S, Sun XQ, 2015. Efficient compression of 4D–trajectory data in air traffic management. IEEE Trans Intell Transp Syst, 16(2):844–853.Google Scholar
  25. Xie AM, Cheng P, 2015. 4D approaching trajectory design in terminal area based on radar data. Appl Mech Mater, 740:731–735. CrossRefGoogle Scholar
  26. Yepes JL, Hwang I, Rotea M, 2007. New algorithms for aircraft intent inference and trajectory prediction. J Guid Contr Dynam, 30(2):370–382. CrossRefGoogle Scholar
  27. Zahariand A, Jaafar J, 2015. Combining hidden Markov model and case based reasoning for time series forecasting. Commun Comput Inform Sci, 513:237–247. CrossRefGoogle Scholar
  28. Zhang JF, Jiang HX, Wu XG, 2014. 4D trajectory prediction based on BADA and aircraft intent. J Southwest Jiaotong Univ, 49(3):553–558.Google Scholar
  29. Zheng Y, Zhou XF, 2012. Computing with Spatial Trajectories. Springer, New York, USA, p.337–394.Google Scholar

Copyright information

© Zhejiang University and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.National Key Laboratory of Fundamental Science on Synthetic VisionSichuan UniversityChengduChina
  2. 2.National Key Laboratory of Air Traffic Control Automation System TechnologySichuan UniversityChengduChina

Personalised recommendations