CMTS: Conditional Multiple Trajectory Synthesizer for Generating Safety-critical Driving Scenarios

TL;DR

This paper introduces CMTS, a generative framework that synthesizes safety-critical near-miss driving scenarios conditioned on road maps, enhancing autonomous driving datasets and improving trajectory prediction in risky situations.

Contribution

The paper presents a novel Variational Bayesian-based generative model, CMTS, that synthesizes near-miss driving data conditioned on road maps, bridging safe and collision data for better autonomous driving evaluation.

Findings

Augmented datasets include more near-miss scenarios.

Improved trajectory prediction accuracy.

Enhanced capability to handle risky driving situations.

Abstract

Naturalistic driving trajectories are crucial for the performance of autonomous driving algorithms. However, most of the data is collected in safe scenarios leading to the duplication of trajectories which are easy to be handled by currently developed algorithms. When considering safety, testing algorithms in near-miss scenarios that rarely show up in off-the-shelf datasets is a vital part of the evaluation. As a remedy, we propose a near-miss data synthesizing framework based on Variational Bayesian methods and term it as Conditional Multiple Trajectory Synthesizer (CMTS). We leverage a generative model conditioned on road maps to bridge safe and collision driving data by representing their distribution in the latent space. By sampling from the near-miss distribution, we can synthesize safety-critical data crucial for understanding traffic scenarios but not shown in neither the original dataset nor the collision dataset. Our experimental results demonstrate that the augmented dataset covers more kinds of driving scenarios, especially the near-miss ones, which help improve the trajectory prediction accuracy and the capability of dealing with risky driving scenarios.