UniGen: Unified Modeling of Initial Agent States and Trajectories for Generating Autonomous Driving Scenarios

TL;DR

UniGen is a unified modeling approach that generates realistic autonomous driving scenarios by jointly predicting agent positions, initial states, and trajectories conditioned on existing scene context, improving scenario realism and safety.

Contribution

It introduces a unified model for all scenario elements and autoregressive agent injection, enhancing the realism and safety of generated traffic scenarios.

Findings

Outperforms prior state-of-the-art on Waymo dataset

Produces realistic scenarios with low collision rates

Effectively models all scenario elements jointly

Abstract

This paper introduces UniGen, a novel approach to generating new traffic scenarios for evaluating and improving autonomous driving software through simulation. Our approach models all driving scenario elements in a unified model: the position of new agents, their initial state, and their future motion trajectories. By predicting the distributions of all these variables from a shared global scenario embedding, we ensure that the final generated scenario is fully conditioned on all available context in the existing scene. Our unified modeling approach, combined with autoregressive agent injection, conditions the placement and motion trajectory of every new agent on all existing agents and their trajectories, leading to realistic scenarios with low collision rates. Our experimental results show that UniGen outperforms prior state of the art on the Waymo Open Motion Dataset.