Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation

TL;DR

InfGen is a novel unified model that enables stable, long-term traffic simulation by interleaving autoregressive motion and scene generation, outperforming existing methods in long-term scenarios.

Contribution

This paper introduces InfGen, a unified next-token prediction model that seamlessly switches between motion simulation and scene generation for long-term traffic simulation.

Findings

State-of-the-art in short-term traffic simulation (9s).

Significantly better performance in long-term (30s) simulation.

Enables stable long-term rollout of traffic scenarios.

Abstract

An ideal traffic simulator replicates the realistic long-term point-to-point trip that a self-driving system experiences during deployment. Prior models and benchmarks focus on closed-loop motion simulation for initial agents in a scene. This is problematic for long-term simulation. Agents enter and exit the scene as the ego vehicle enters new regions. We propose InfGen, a unified next-token prediction model that performs interleaved closed-loop motion simulation and scene generation. InfGen automatically switches between closed-loop motion simulation and scene generation mode. It enables stable long-term rollout simulation. InfGen performs at the state-of-the-art in short-term (9s) traffic simulation, and significantly outperforms all other methods in long-term (30s) simulation. The code and model of InfGen will be released at https://orangesodahub.github.io/InfGen