Enactor: From Traffic Simulators to Surrogate World Models

TL;DR

This paper introduces Enactor, a transformer-based generative model that captures realistic traffic actor interactions and generates physically consistent long-term trajectories, improving traffic simulation accuracy and efficiency.

Contribution

Enactor is the first actor-centric model that explicitly captures complex interactions and intersection dynamics using transformers, outperforming traditional methods with fewer training samples.

Findings

Effectively captures complex actor-actor interactions.

Generates physically consistent long-horizon trajectories.

Outperforms baseline by over 10x in KL-Divergence.

Abstract

Traffic microsimulators are widely used to evaluate road network performance under various ``what-if" conditions. However, the behavior models controlling the actions of the actors are overly simplistic and fails to capture realistic actor-actor interactions. Deep learning-based methods have been applied to model vehicles and pedestrians as ``agents" responding to their surrounding ``environment" (including lanes, signals, and neighboring agents). Although effective in learning actor-actor interaction, these approaches fail to generate physically consistent trajectories over long time periods, and they do not explicitly address the complex dynamics that arise at traffic intersections which is a critical location in urban networks. Inspired by the World Model paradigm, we have developed an actor centric generative model using transformer-based architecture that is able to capture the actor-actor interaction, at the same time understanding the geometry to the traffic intersection to generate physically grounded trajectories that are based on learned behavior. Moreover, we test the model in a live ``simulation-in-the-loop" setting, where we generate the initial conditions of the actors using SUMO and then let the model control the dynamics of the actors. We let the simulation run for 40000 timesteps (4000 seconds), testing the performance of the model on long timerange and evaluating the trajectories on traffic engineering related metrics. Experimental results demonstrate that the proposed framework effectively captures complex actor-actor interactions and generates long-horizon, physically consistent trajectories, while requiring significantly fewer training samples than traditional agent-centric generative approaches. Our model is able to outperform the baseline in traffic related as well as aggregate metrics where our model beats the baseline by more than 10x on the KL-Divergence.