Bridging Traffic State and Trajectory for Dynamic Road Network and Trajectory Representation Learning

TL;DR

This paper introduces TRACK, a framework that combines traffic state and trajectory data using graph attention and transformer models to improve dynamic road network and trajectory representations for urban traffic management.

Contribution

TRACK is the first to integrate traffic state and trajectory data with graph attention and transformer models for dynamic representation learning.

Findings

Outperforms state-of-the-art baselines in traffic prediction tasks.

Effectively captures spatial-temporal dynamics of urban traffic.

Demonstrates robustness across multiple real-world datasets.

Abstract

Effective urban traffic management is vital for sustainable city development, relying on intelligent systems with machine learning tasks such as traffic flow prediction and travel time estimation. Traditional approaches usually focus on static road network and trajectory representation learning, and overlook the dynamic nature of traffic states and trajectories, which is crucial for downstream tasks. To address this gap, we propose TRACK, a novel framework to bridge traffic state and trajectory data for dynamic road network and trajectory representation learning. TRACK leverages graph attention networks (GAT) to encode static and spatial road segment features, and introduces a transformer-based model for trajectory representation learning. By incorporating transition probabilities from trajectory data into GAT attention weights, TRACK captures dynamic spatial features of road segments. Meanwhile, TRACK designs a traffic transformer encoder to capture the spatial-temporal dynamics of road segments from traffic state data. To further enhance dynamic representations, TRACK proposes a co-attentional transformer encoder and a trajectory-traffic state matching task. Extensive experiments on real-life urban traffic datasets demonstrate the superiority of TRACK over state-of-the-art baselines. Case studies confirm TRACK's ability to capture spatial-temporal dynamics effectively.