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 introduce unnecessary computational overhead or struggle to represent the diverse and time-varying characteristics of human interactions. In this work, we present an Adaptive Relational Transformer (ART), which introduces a Temporal-Aware Relation Graph (TARG) to explicitly capture the evolution of pairwise interactions and an Adaptive Interaction Pruning (AIP) mechanism to reduce redundant computations efficiently. Extensive evaluations on ETH/UCY and NBA benchmarks show that ART delivers state-of-the-art accuracy with high computational efficiency.
@article{arxiv.2604.03649,
title = {ART: Adaptive Relational Transformer for Pedestrian Trajectory Prediction with Temporal-Aware Relations},
author = {Ruochen Li and Ziyi Chang and Junyan Hu and Jiannan Li and Amir Atapour-Abarghouei and Hubert P. H. Shum},
journal= {arXiv preprint arXiv:2604.03649},
year = {2026}
}