CaDRE: Controllable and Diverse Generation of Safety-Critical Driving Scenarios using Real-World Trajectories

TL;DR

CaDRE is a novel framework that generates realistic, diverse, and controllable safety-critical driving scenarios for autonomous vehicle testing, improving sample efficiency over existing methods.

Contribution

The paper introduces CaDRE, a new approach that combines real-world data, domain knowledge, and optimization to generate safety-critical scenarios more effectively.

Findings

Outperforms existing RL and sampling methods in diversity and quality.

Demonstrates effectiveness across three traffic scenario types.

Achieves higher sample efficiency in scenario generation.

Abstract

Simulation is an indispensable tool in the development and testing of autonomous vehicles (AVs), offering an efficient and safe alternative to road testing. An outstanding challenge with simulation-based testing is the generation of safety-critical scenarios, which are essential to ensure that AVs can handle rare but potentially fatal situations. This paper addresses this challenge by introducing a novel framework, CaDRE, to generate realistic, diverse, and controllable safety-critical scenarios. Our approach optimizes for both the quality and diversity of scenarios by employing a unique formulation and algorithm that integrates real-world scenarios, domain knowledge, and black-box optimization. We validate the effectiveness of our framework through extensive testing in three representative types of traffic scenarios. The results demonstrate superior performance in generating diverse and high-quality scenarios with greater sample efficiency than existing reinforcement learning (RL) and sampling-based methods.