ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles

TL;DR

ChatScene is a novel LLM-based system that generates safety-critical autonomous vehicle scenarios from natural language instructions, improving safety testing and model robustness in simulation environments.

Contribution

It introduces a comprehensive framework combining language understanding, scenario decomposition, domain-specific code generation, and knowledge retrieval for safety-critical scenario creation.

Findings

15% increase in collision rates compared to baselines

9% reduction in collisions after fine-tuning with generated scenarios

Effective bridging of textual descriptions and CARLA simulations

Abstract

We present ChatScene, a Large Language Model (LLM)-based agent that leverages the capabilities of LLMs to generate safety-critical scenarios for autonomous vehicles. Given unstructured language instructions, the agent first generates textually described traffic scenarios using LLMs. These scenario descriptions are subsequently broken down into several sub-descriptions for specified details such as behaviors and locations of vehicles. The agent then distinctively transforms the textually described sub-scenarios into domain-specific languages, which then generate actual code for prediction and control in simulators, facilitating the creation of diverse and complex scenarios within the CARLA simulation environment. A key part of our agent is a comprehensive knowledge retrieval component, which efficiently translates specific textual descriptions into corresponding domain-specific code snippets by training a knowledge database containing the scenario description and code pairs. Extensive experimental results underscore the efficacy of ChatScene in improving the safety of autonomous vehicles. For instance, the scenarios generated by ChatScene show a 15% increase in collision rates compared to state-of-the-art baselines when tested against different reinforcement learning-based ego vehicles. Furthermore, we show that by using our generated safety-critical scenarios to fine-tune different RL-based autonomous driving models, they can achieve a 9% reduction in collision rates, surpassing current SOTA methods. ChatScene effectively bridges the gap between textual descriptions of traffic scenarios and practical CARLA simulations, providing a unified way to conveniently generate safety-critical scenarios for safety testing and improvement for AVs.