High-fidelity Aircraft Trajectory Generation Using a Flow-based Generative Model
Open Access
- 1 January 2026
- journal article
- Published by Japan Society for Aeronautical and Space Sciences in TRANSACTIONS OF THE JAPAN SOCIETY FOR AERONAUTICAL AND SPACE SCIENCES
- Vol. 69 (1) , 9-18
Abstract
Aircraft trajectory generation is one of the key technologies for realizing and researching a highly efficient air traffic system. Fast-time simulations are used for the initial evaluation of newly proposed operational concepts, and the employed scenarios must be faithful to actual aircraft operations and include a wide range of possible future events. In addition, since aircraft trajectories are influenced by numerous complex factors, incorporating these factors into the generation process is essential to improve the fidelity of the generated trajectories. This study employed a deep generative model to capture these factors, with surrounding traffic conditions selected as a representative example. In particular, a flow-based generative model was employed to obtain the generation probability of the trajectory to allow evaluation based on the probability of events occurring in the simulation. The generated trajectories were confirmed to be consistent with the operational flight envelope and surrounding traffic using publicly available track data.Keywords
This publication has 16 references indexed in Scilit:
- A Generalized Approach to Aircraft Trajectory Prediction via Supervised Deep LearningIEEE Access, 2023
- Deep generative modelling of aircraft trajectories in terminal maneuvering areasMachine Learning with Applications, 2022
- Quantitative Evaluation of Controlled Arrival Flow Connecting into Point Merge System at Tokyo International Airport2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Long-term 4D trajectory prediction using generative adversarial networksTransportation Research Part C: Emerging Technologies, 2022
- Quantitative Analysis of Conflict Between Aircraft by Using Radar Track DataLecture Notes in Electrical Engineering, 2017
- Arrival Time Assignment by Dynamic Programming OptimizationLecture Notes in Electrical Engineering, 2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- The Eigenvalues of Mega-dimensional Matrices1989
- A Stochastic Estimator of the Trace of the Influence Matrix for Laplacian Smoothing SplinesCommunications in Statistics - Simulation and Computation, 1989