Collision Snapshot Guided Time-Reversed Safety-Critical Scenario Generation

Summary

The generation of safety-critical traffic scenarios is essential for training and evaluating autonomous vehicles.

Abstract Summary

The generation of safety-critical traffic scenarios is essential for training and evaluating autonomous vehicles. Prior approaches typically perturb the trajectories of existing agents in a traffic scenario using simplified adversarial objectives to induce safety-critical interactions, which can limit the plausibility and diversity of the generated scenarios. Although inserting new adversarial vehicles can alleviate this limitation, determining when and where to introduce them in a scenario-specific manner remains challenging. In this work, we introduce \underline{CO}llision \underline{S}napshot guided \underline{T}im\underline{E}-\underline{R}eversed safety-critical scenario generation (COSTER), a framework that leverages learned traffic priors to determine plausible collision times and locations. COSTER first constructs a collision snapshot by inserting a new vehicle in contact with the target vehicle at the identified collision state within a traffic scenario. Starting from this collision snapshot, a conditional variational autoencoder is used to perform a time-reversed rollout, reconstructing the trajectory of the inserted vehicle backward toward earlier timesteps. Experiments show that COSTER outperforms existing methods in plausibility, diversity, and data efficiency. Moreover, agents trained on COSTER-generated scenarios reduce collision rates by 31\% on safety-critical scenarios from the Waymo Open Motion Dataset while also improving ego task completion. The project website is available at https://anonym-121.github.io/COSTER/.

Key Points

The generation of safety-critical traffic scenarios is essential for training and evaluating autonomous vehicles.
Prior approaches typically perturb the trajectories of existing agents in a traffic scenario using simplified adversarial objectives to induce safety-critical interactions, which can limit the plausibility and diversity of the generated scenarios.
Although inserting new adversarial vehicles can alleviate this limitation, determining when and where to introduce them in a scenario-specific manner remains challenging.
In this work, we introduce \underline{CO}llision \underline{S}napshot guided \underline{T}im\underline{E}-\underline{R}eversed safety-critical scenario generation (COSTER), a framework that leverages learned traffic priors to determine plausible collision times and locations.
COSTER first constructs a collision snapshot by inserting a new vehicle in contact with the target vehicle at the identified collision state within a traffic scenario.

Proposed Method

A traffic scenario is denoted as $S_{1:T}=(M,\mathcal{T}_{1:T})$, where $M$ represents the vectorized map and $\mathcal{T}_{1:T}=\{\tau_{1:T}^{1},\ldots,\tau_{1:T}^{N}\}$ denotes the set of trajectories for $N$ vehicles over $T$ timesteps. Each trajectory $\tau_{1:T}^{n}$ consists of the vehicle states across time, represented as $\{s_{1}^{n},\ldots,s_{T}^{n}\}$.

Experiments

We train the models described in Sec. III-B and Sec. III-D using the Waymo Open Motion Dataset v1.1 (WOMD), which contains 9-second scenarios (530,000 scenes). The local region width is set to $w_{r}=5\,\text{m}$. The longitudinal and lateral semi-axis lengths, $\rho_{\mathrm{long}}$ and $\rho_{\mathrm{lat}}$, are set to twice the ego vehicle’s length and width, respectively. The trajectory generation horizon in Sec.

Sources and Demonstrations

Figures are reproduced from Kim et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.