A Structure-Aware Lane Graph Transformer Model for Vehicle Trajectory Prediction

TL;DR

This paper introduces a structure-aware Lane Graph Transformer model that encodes map topology into attention mechanisms, significantly improving vehicle trajectory prediction accuracy for autonomous driving.

Contribution

The novel LGT model incorporates map topology into attention mechanisms using RPE and SPD matrices, enhancing prediction performance over existing models.

Findings

Achieved 60.73% reduction in minFDE6 compared to baseline.

Reduced b-minFDE6 by 2.65% over LaneGCN.

Map topology consideration improved accuracy by 4.24%.

Abstract

Accurate prediction of future trajectories for surrounding vehicles is vital for the safe operation of autonomous vehicles. This study proposes a Lane Graph Transformer (LGT) model with structure-aware capabilities. Its key contribution lies in encoding the map topology structure into the attention mechanism. To address variations in lane information from different directions, four Relative Positional Encoding (RPE) matrices are introduced to capture the local details of the map topology structure. Additionally, two Shortest Path Distance (SPD) matrices are employed to capture distance information between two accessible lanes. Numerical results indicate that the proposed LGT model achieves a significantly higher prediction performance on the Argoverse 2 dataset. Specifically, the minFDE$_6$ metric was decreased by 60.73% compared to the Argoverse 2 baseline model (Nearest Neighbor) and the b-minFDE$_6$ metric was reduced by 2.65% compared to the baseline LaneGCN model. Furthermore, ablation experiments demonstrated that the consideration of map topology structure led to a 4.24% drop in the b-minFDE$_6$ metric, validating the effectiveness of this model.