AI RESEARCH
ART: Adaptive Relational Transformer for Pedestrian Trajectory Prediction with Temporal-Aware Relations
arXiv CS.AI
•
ArXi:2604.03649v1 Announce Type: cross Accurate prediction of real-world pedestrian trajectories is crucial for a wide range of robot-related applications. Recent approaches typically adopt graph-based or transformer-based frameworks to model interactions. Despite their effectiveness, these methods either