APPROACH FOR 4-D TRAJECTORY MANAGEMENT BASED ON HMM AND TRAJECTORY SIMILARITY

Authors

Yi Lin, National Key Laboratory of Fundamental Science on Synthetic Vision, SichuanUniversity, Chengdu, Sichuan, China.National Key Laboratory of Air Traffic Control Automatization System Technology, Sichuan University, Chengdu, Sichuan, China.Department of Civil and Environmental Engineering, University of WisconsinMadison, Madison, WI, USA.
Bo Yang, National Key Laboratory of Fundamental Science on Synthetic Vision, SichuanUniversity, Chengdu, Sichuan, China.National Key Laboratory of Air Traffic Control Automatization System Technology, Sichuan University, Chengdu, Sichuan, China.
Jianwei Zhang, National Key Laboratory of Fundamental Science on Synthetic Vision, SichuanUniversity, Chengdu, Sichuan, China.National Key Laboratory of Air Traffic Control Automatization System Technology, Sichuan University, Chengdu, Sichuan, China.
Hong Liu, National Key Laboratory of Fundamental Science on Synthetic Vision, SichuanUniversity, Chengdu, Sichuan, China.National Key Laboratory of Air Traffic Control Automatization System Technology, Sichuan University, Chengdu, Sichuan, China.

Abstract

To improve the accuracy and stability of flight trajectory prediction, a novel four-dimensional (4-D) trajectory management approach is proposed in this paper, which consists of the estimation and updating procedure. Historical flight trajectories are proved to be safe and feasible based on the real-time traffic situation, and serve as the data foundation of 4-D trajectory management in this paper. To achieve the goal of 4-D trajectory management, we firstly apply probabilistic statistical models and machine learning approach to predict the fly-over time and altitude of waypoints along the planning route before the flight takes off. Hidden Markov Models (HMMs) are regarded as the probabilistic model to represent the position and altitude transition patterns of the aircraft during the flight operation. The EM algorithm is applied to optimize model parameters of HMMs to fit the training data (historical trajectory set). Then the models with optimized parameters are used to predict the pre-takeoff 4-D trajectory by inferring an optimal hidden state sequence. Finally, after the flight takes off, we propose an algorithm to correct the pre-takeoff prediction results by considering the trajectory similarity between collected path of current execution and its historical trajectories. Simulations with real data show that the prediction results (fly-over time and altitude) of our proposed algorithm are more accurate than that of other existing methods, and would tend to be more credible after correcting with the proposed algorithm. Moreover, the prediction errors of our approach are stable during the whole flight, which is the

Recommended Citation

Lin, Yi; Yang, Bo; Zhang, Jianwei; and Liu, Hong (2019) "APPROACH FOR 4-D TRAJECTORY MANAGEMENT BASED ON HMM AND TRAJECTORY SIMILARITY," Journal of Marine Science and Technology: Vol. 27: Iss. 3, Article 7.
DOI: 10.6119/JMST.201906_27(3).0007
Available at: https://jmstt.ntou.edu.tw/journal/vol27/iss3/7