Exploring rounD Dataset for Domain Generalization in Autonomous Vehicle Trajectory Prediction

This paper analyzes the rounD dataset to advance motion forecasting algorithms for autonomous vehicles navigating complex roundabout environments. We develop a trajectory prediction framework inspired by Gated Recurrent Unit (GRU) networks and graph-based modules to effectively model vehicle interactions. Our primary objective is to evaluate the generalizability of the proposed model across diverse training and testing datasets. Through extensive experiments, we investigate how varying data distributions-such as different road configurations and recording times-impact the model's prediction accuracy and robustness. This study provides key insights into the challenges of domain generalization in autonomous vehicle trajectory prediction.