The growing demand for air travel requires technological advancements in air traffic management as well as mechanisms for monitoring and ensuring safe and efficient operations.

Some trends…

A close call…

A runway incursion at Boston-Logan Intl. Airport (2x speed)

February 27, 2023

To improve airport safety and efficiency and encourage further research in this direction we introduce Amelia, a large-scale dataset of airport surface movement and a toolkit for data analysis, visualization, benchmarking, and behavior modeling.

Our dataset, Amelia-42 comprises more than two year’s worth of data collection across 42 airports and TRACON facilities within the US National Airspace System, which is ∼9.19TB of raw data. We also release Amelia42-Mini, a 15-day sample per airport, fully processed data on HuggingFace for ease of use.

Additionally, inspired by the success of motion prediction models in the AV domain for safety monitoring and multi-agent coordination, we introduce Amelia-TF, a transformer-based large multi-agent multi-airport trajectory forecasting model. Trained on Amelia10-Bench, consisting on 292 days or over 9B tokens of position data encompassing 10 different airports, available on HuggingFace.

Amelia-42

A Large-Scale Dataset for Airport Surface Movement

Amelia-TF

A large model for airport surface movement forecasting.

Amelia Framework

A framework for airport surface movement

Our Code

Amelia-SWIM

Airport surface movement data collection and pre-preprocessing tools

Amelia-Maps

Airport map data collection and processing tools

Amelia-DataTools

Trajectory and map data analysis and verification tools

Amelia-Scenes

Scene post-processing and characterization tool

Amelia-TF

Trajectory forecasting model

Amelia-Inference

Standalone trajectory prediction tool

Principal investigators

Jean Oh

Bot Intelligence Group (BIG), CMU

Sebastian Scherer

AirLab, CMU

Team members

Ingrid Navarro

Bot Intelligence Group (BIG), CMU

Pablo Ortega-Kral

Bot Intelligence Group (BIG), CMU

Jay Patrikar

The Airlab, CMU

Alonso Cano

Bot Intelligence Group (BIG), CMU

Haichuan (Jack) Wang

The Airlab, CMU

Collaborators

Zelin Ye

The Airlab, CMU

Jong Hoon Park

Bot Intelligence Group (BIG), CMU

Avi Amalanshu

The Airlab, CMU

Papers

Amelia: A Large Model and Dataset for Airport Surface Movement Forecasting (non archival)

Ingrid Navarro *, Pablo Ortega-Kral *, Jay Patrikar *, Haichuan Wang, Zelin Ye, Jong Hoon Park, Jean Oh and Sebastian Scherer

*Denotes equal contribution

🏆 Best Student Paper Award

@inbook{navarro2024amelia,
  author = {Ingrid Navarro and Pablo Ortega and Jay Patrikar and Haichuan Wang and Zelin Ye and Jong Hoon Park and Jean Oh and Sebastian Scherer},
  title = {AmeliaTF: A Large Model and Dataset for Airport Surface Movement Forecasting},
  booktitle = {AIAA AVIATION FORUM AND ASCEND 2024},
  chapter = {},
  pages = {},
  doi = {10.2514/6.2024-4251},
  URL = {https://arc.aiaa.org/doi/abs/10.2514/6.2024-4251},
  eprint = {https://arc.aiaa.org/doi/pdf/10.2514/6.2024-4251},
}