Lane-Aware Graph Attention Network for Multi-Vehicle Trajectory Prediction in Expressway Merge Zones

TL;DR

This paper introduces a lane-aware graph attention network for predicting multi-vehicle trajectories in expressway merge zones, emphasizing safety metrics and transferability across datasets.

Contribution

It proposes a novel lane-aware graph attention model that encodes vehicle interactions and prioritizes merge-conflict interactions, improving prediction accuracy and safety assessment.

Findings

Fine-tuned model achieves ADE of 0.865 m at 1s horizon.

Model reduces transfer gap when fine-tuned on drone data.

Using unfiltered NGSIM data reveals limits of raw-condition generalization.

Abstract

Accurate multi-vehicle trajectory prediction in expressway merge and diverge areas is fundamental to the decision-making frameworks of autonomous vehicle systems. However, the majority of existing graph-based prediction models are developed and validated on mainline freeway segments and do not address the geometrically distinct interaction structures that characterize merge zones. Furthermore, standard evaluation protocols rely exclusively on displacement error metrics, leaving the safety consequences of predicted trajectories unquantified. This paper proposes a Lane-Aware Graph Attention Network (LA-GAT) that encodes vehicle interaction within dynamic scene graphs, augmented with a trainable lane-relationship attention bias that prioritizes merge-conflict interactions from the outset of training. The model is pre-trained on the raw NGSIM US-101 and I-80 datasets and subsequently fine-tuned on UAV-captured UTE SQM-W-1 trajectory data from a Chinese expressway merge area, with final evaluation on the held-out SQM-W-2 dataset. Evaluation spans both displacement metrics (ADE, FDE at 1s, 3s, 5s horizons) and surrogate safety measures (TTC violation rate, DRAC exceedance rate, collision rate). Fine-tuned results on SQM-W-2 yield ADE of 0.865 m at 1s and 2.518 m at 3s, demonstrating that drone-informed fine-tuning substantially reduces the cross-dataset transfer gap. The deliberate use of unfiltered NGSIM data is shown to characterize raw-condition generalization limits, with the performance degradation attributed to the well-documented measurement errors in that dataset.