ASCENT: Transformer-Based Aircraft Trajectory Prediction in Non-Towered Terminal Airspace

TL;DR

ASCENT is a lightweight transformer model that accurately predicts multi-modal 3D aircraft trajectories in non-towered airspace, enhancing safety and real-time decision-making.

Contribution

The paper introduces ASCENT, a novel transformer-based model with domain-aware normalization and parameterized outputs for improved aircraft trajectory forecasting.

Findings

Outperforms prior baselines on TrajAir and TartanAviation datasets

Effectively captures motion dynamics with the encoder

Enables diverse maneuver hypotheses with low latency

Abstract

Accurate trajectory prediction can improve General Aviation safety in non-towered terminal airspace, where high traffic density increases accident risk. We present ASCENT, a lightweight transformer-based model for multi-modal 3D aircraft trajectory forecasting, which integrates domain-aware 3D coordinate normalization and parameterized predictions. ASCENT employs a transformer-based motion encoder and a query-based decoder, enabling the generation of diverse maneuver hypotheses with low latency. Experiments on the TrajAir and TartanAviation datasets demonstrate that our model outperforms prior baselines, as the encoder effectively captures motion dynamics and the decoder aligns with structured aircraft traffic patterns. Furthermore, ablation studies confirm the contributions of the decoder design, coordinate-frame modeling, and parameterized outputs. These results establish ASCENT as an effective approach for real-time aircraft trajectory prediction in non-towered terminal airspace.