NetTraj: A Network-based Vehicle Trajectory Prediction Model with Directional Representation and Spatiotemporal Attention Mechanisms

TL;DR

NetTraj is a novel vehicle trajectory prediction model that uses a network-based representation with directional and spatiotemporal attention mechanisms, significantly improving prediction accuracy in city-scale road networks.

Contribution

The paper introduces a network-based trajectory representation and combines local graph and temporal attention mechanisms, advancing vehicle trajectory prediction over existing cell-based methods.

Findings

NetTraj outperforms state-of-the-art methods on large-scale taxi datasets.

The directional and network-based representation improves spatial dependency modeling.

Spatiotemporal attention mechanisms enhance temporal dependency capture.

Abstract

Trajectory prediction of vehicles in city-scale road networks is of great importance to various location-based applications such as vehicle navigation, traffic management, and location-based recommendations. Existing methods typically represent a trajectory as a sequence of grid cells, road segments or intention sets. None of them is ideal, as the cell-based representation ignores the road network structures and the other two are less efficient in analyzing city-scale road networks. Moreover, previous models barely leverage spatial dependencies or only consider them at the grid cell level, ignoring the non-Euclidean spatial structure shaped by irregular road networks. To address these problems, we propose a network-based vehicle trajectory prediction model named NetTraj, which represents each trajectory as a sequence of intersections and associated movement directions, and then feeds them into a LSTM encoder-decoder network for future trajectory generation. Furthermore, we introduce a local graph attention mechanism to capture network-level spatial dependencies of trajectories, and a temporal attention mechanism with a sliding context window to capture both short- and long-term temporal dependencies in trajectory data. Extensive experiments based on two real-world large-scale taxi trajectory datasets show that NetTraj outperforms the existing state-of-the-art methods for vehicle trajectory prediction, validating the effectiveness of the proposed trajectory representation method and spatiotemporal attention mechanisms.