Promptable Closed-loop Traffic Simulation

TL;DR

ProSim is a novel multimodal promptable closed-loop traffic simulation framework that enables user-controlled, realistic traffic scenario generation, supporting autonomous driving research with a large paired dataset and competitive performance.

Contribution

The paper introduces ProSim, a new promptable traffic simulation system with a large dataset, advancing controllability and realism in autonomous driving simulations.

Findings

ProSim achieves high prompt controllability.

ProSim performs competitively on the Waymo Sim Agents Challenge.

ProSim includes a large multimodal prompt-scenario dataset.

Abstract

Simulation stands as a cornerstone for safe and efficient autonomous driving development. At its core a simulation system ought to produce realistic, reactive, and controllable traffic patterns. In this paper, we propose ProSim, a multimodal promptable closed-loop traffic simulation framework. ProSim allows the user to give a complex set of numerical, categorical or textual prompts to instruct each agent's behavior and intention. ProSim then rolls out a traffic scenario in a closed-loop manner, modeling each agent's interaction with other traffic participants. Our experiments show that ProSim achieves high prompt controllability given different user prompts, while reaching competitive performance on the Waymo Sim Agents Challenge when no prompt is given. To support research on promptable traffic simulation, we create ProSim-Instruct-520k, a multimodal prompt-scenario paired driving dataset with over 10M text prompts for over 520k real-world driving scenarios. We will release code of ProSim as well as data and labeling tools of ProSim-Instruct-520k at https://ariostgx.github.io/ProSim.