IntTrajSim: Trajectory Prediction for Simulating Multi-Vehicle driving at Signalized Intersections

TL;DR

This paper introduces IntTrajSim, a data-driven, deep learning-based traffic intersection simulator that predicts vehicle trajectories and evaluates them using traffic engineering metrics, improving realism over rule-based models.

Contribution

The paper presents a novel simulation-in-the-loop pipeline and a multi-headed self-attention trajectory prediction model incorporating signal data, tailored for traffic engineering evaluation.

Findings

The proposed model outperforms previous models on traffic engineering metrics.

The simulation-in-the-loop pipeline enables realistic micro- and macro-traffic behavior evaluation.

Incorporating signal information improves trajectory prediction accuracy.

Abstract

Traffic simulators are widely used to study the operational efficiency of road infrastructure, but their rule-based approach limits their ability to mimic real-world driving behavior. Traffic intersections are critical components of the road infrastructure, both in terms of safety risk (nearly 28% of fatal crashes and 58% of nonfatal crashes happen at intersections) as well as the operational efficiency of a road corridor. This raises an important question: can we create a data-driven simulator that can mimic the macro- and micro-statistics of the driving behavior at a traffic intersection? Deep Generative Modeling-based trajectory prediction models provide a good starting point to model the complex dynamics of vehicles at an intersection. But they are not tested in a "live" micro-simulation scenario and are not evaluated on traffic engineering-related metrics. In this study, we propose traffic engineering-related metrics to evaluate generative trajectory prediction models and provide a simulation-in-the-loop pipeline to do so. We also provide a multi-headed self-attention-based trajectory prediction model that incorporates the signal information, which outperforms our previous models on the evaluation metrics.