LLMScenario: Large Language Model Driven Scenario Generation

doi:10.1109/TSMC.2024.3392930

LLMScenario: Large Language Model Driven Scenario Generation

2024-11-01

2

PRE

AI

DOI：10.1109/TSMC.2024.3392930

Original

Original request for help

Save

Abstract

En 中文

Scenario engineering plays a vital role in various Industry 5.0 applications. In the field of autonomous driving systems, driving scenario data are important for the training and testing of critical modules. However, the corner scenario cases are usually rare and necessary to be extended. Existing methods cannot handle the interpretation and reasoning of the generation process well, which reduces the reliability and usability of the generated scenarios. With the rapid development of Foundation Models, especially the large language model (LLM), we can conduct scenario generation via more powerful tools. In this article, we propose LLMScenario, a novel LLM-driven scenario generation framework, which is composed of scenario prompt engineering, LLM scenario generation, and evaluation feedback tuning. The minimum scenario description specific to LLM is given by scenario analysis and ablation studies. We also appropriately design the score functions in terms of reality and rarity to evaluate the generated scenarios. The model performance is further enhanced through chain-of-thoughts and experiences. Different LLMs are also compared with our framework. Experimental results on naturalistic datasets demonstrate the effectiveness of LLMScenario, which can provide solid support for scenario engineering in Industry 5.0.

Keywords:

Scenario generation

Cognition

Autonomous vehicles

Tuning

Testing

Semantics

Task analysis

Large language model (LLM)

scenario engineering

scenario generation

LLMScenario: Large Language Model Driven Scenario Generation

Abstract

Journal

Organization