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

2026-03-17

AI Summary

This work proposes ASCENT, a lightweight, Transformer-based multimodal 3D trajectory prediction model designed to address safety risks posed by high-density general aviation traffic in uncontrolled terminal airspace. The approach introduces several innovations, including domain-aware 3D coordinate normalization, parameterized trajectory representation, and a query-based decoding mechanism, which collectively enable effective modeling of structured air traffic patterns and generation of diverse, low-latency flight maneuver hypotheses. Experimental results on the TrajAir and TartanAviation datasets demonstrate that ASCENT significantly outperforms existing baselines, accurately capturing aircraft dynamics while aligning with airspace geometry, thereby proving suitable for real-time trajectory prediction applications.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• trajectory prediction
• non-towered airspace
• General Aviation
• aircraft safety
• terminal airspace

Innovation

• transformer-based trajectory prediction
• 3D coordinate normalization
• parameterized output
• query-based decoder
• non-towered airspace