Trajectory Prediction for Vehicle Conflict Identification at Intersections Using Sequence-to-Sequence Recurrent Neural Networks

TL;DR

This paper introduces a sequence-to-sequence RNN model for predicting vehicle trajectories at intersections, improving conflict detection accuracy by maintaining precise vehicle geometries and outperforming existing models.

Contribution

The study develops a novel RNN-based trajectory prediction method that enhances conflict analysis accuracy by predicting vehicle positions and headings, preserving geometric details.

Findings

The proposed model outperforms existing trajectory prediction models.

Bounding box-based conflict detection is more accurate than center point methods.

Accurate vehicle geometry representation improves conflict severity estimation.

Abstract

Surrogate safety measures in the form of conflict indicators are indispensable components of the proactive traffic safety toolbox. Conflict indicators can be classified into past-trajectory-based conflicts and predicted-trajectory-based conflicts. While the calculation of the former class of conflicts is deterministic and unambiguous, the latter category is computed using predicted vehicle trajectories and is thus more stochastic. Consequently, the accuracy of prediction-based conflicts is contingent on the accuracy of the utilized trajectory prediction algorithm. Trajectory prediction can be a challenging task, particularly at intersections where vehicle maneuvers are diverse. Furthermore, due to limitations relating to the road user trajectory extraction pipelines, accurate geometric representation of vehicles during conflict analysis is a challenging task. Misrepresented geometries distort the real distances between vehicles under observation. In this research, a prediction-based conflict identification methodology was proposed. A sequence-to-sequence Recurrent Neural Network was developed to sequentially predict future vehicle trajectories for up to 3 seconds ahead. Furthermore, the proposed network was trained using the CitySim Dataset to forecast both future vehicle positions and headings to facilitate the prediction of future bounding boxes, thus maintaining accurate vehicle geometric representations. It was experimentally determined that the proposed method outperformed frequently used trajectory prediction models for conflict analysis at intersections. A comparison between Time-to-Collision (TTC) conflict identification using vehicle bounding boxes versus the commonly used vehicle center points for geometric representation was conducted. Compared to the bounding box method, the center point approach often failed to identify TTC conflicts or underestimated their severity.