IntTrajSim: Trajectory Prediction for Simulating Multi-Vehicle driving at Signalized Intersections
This work addresses the need for more realistic traffic simulators at intersections, which is crucial for safety and efficiency, but it is incremental as it builds on existing deep generative modeling approaches.
The authors tackled the problem of creating a data-driven traffic simulator for signalized intersections by proposing new traffic engineering metrics and a simulation-in-the-loop pipeline to evaluate generative trajectory prediction models, resulting in a multi-headed self-attention-based model that outperforms previous models on these metrics.
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.