Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces DESCENT, a transformer-based architecture tailored for predicting airport surface movements, addressing the challenges posed by heterogeneous dynamics and strict topological constraints. By employing a Potential Reachable Set (PRS) context sampling mechanism, DESCENT effectively gathers relevant airfield context across various operational phases, leading to enhanced trajectory forecasting. Evaluations on the Amelia-10 benchmark reveal that DESCENT significantly outperforms existing methods, particularly in safety-critical situations where long-horizon context is crucial for safe navigation.
DESCENT achieves unprecedented accuracy in airport surface movement predictions, especially in safety-critical scenarios, by leveraging adaptive context sampling.
Advanced automation is a key technology for enhancing the safety of ground operations amidst the increasing density of commercial air traffic. While motion forecasting is a well-studied task in autonomous driving, its application to airport surface movements remains underexplored. To enable efficient and accurate prediction in this domain, we propose DESCENT, a transformer-based architecture designed to handle heterogeneous dynamics and strict topological constraints. Our approach features a Potential Reachable Set (PRS) context sampling mechanism that adaptively collects airfield environment context across diverse operational phases. Combined with a detection transformer-based decoder, DESCENT generates accurate trajectory forecasts. Extensive evaluations on the Amelia-10 benchmark demonstrate significant performance improvements over state-of-the-art baselines. These gains are especially pronounced in safety-critical scenarios, where our domain-aware sampling provides critical long-horizon context necessary for safe navigation.