Realistic Corner Case Generation for Autonomous Vehicles with Multimodal Large Language Model
This work addresses the need for more effective safety testing in autonomous vehicles by improving scenario generation, though it is incremental as it builds on existing LLM and simulation tools.
The authors tackled the problem of generating realistic corner cases for autonomous vehicle testing by introducing AutoScenario, a multimodal LLM-based framework that converts real-world data into textual representations and integrates with simulators, resulting in the generation of diverse and novel scenarios tailored to specific requirements.
To guarantee the safety and reliability of autonomous vehicle (AV) systems, corner cases play a crucial role in exploring the system's behavior under rare and challenging conditions within simulation environments. However, current approaches often fall short in meeting diverse testing needs and struggle to generalize to novel, high-risk scenarios that closely mirror real-world conditions. To tackle this challenge, we present AutoScenario, a multimodal Large Language Model (LLM)-based framework for realistic corner case generation. It converts safety-critical real-world data from multiple sources into textual representations, enabling the generalization of key risk factors while leveraging the extensive world knowledge and advanced reasoning capabilities of LLMs.Furthermore, it integrates tools from the Simulation of Urban Mobility (SUMO) and CARLA simulators to simplify and execute the code generated by LLMs. Our experiments demonstrate that AutoScenario can generate realistic and challenging test scenarios, precisely tailored to specific testing requirements or textual descriptions. Additionally, we validated its ability to produce diverse and novel scenarios derived from multimodal real-world data involving risky situations, harnessing the powerful generalization capabilities of LLMs to effectively simulate a wide range of corner cases.