Can LLMs Understand Social Norms in Autonomous Driving Games?

Social norm is defined as a shared standard of acceptable behavior in a society. The emergence of social norms fosters coordination among agents without any hard-coded rules, which is crucial for the large-scale deployment of autonomous vehicles (AVs) in an intelligent transportation system. This paper explores the application of large language models (LLMs) in understanding and modeling social norms in autonomous driving games. We introduce LLMs into autonomous driving games as intelligent agents who make decisions according to text prompts. These agents are referred to as LLM agents. Our framework involves LLM agents playing Markov games in a multi-agent system (MAS), allowing us to investigate the emergence of social norms among individual agents. We aim to identify social norms by designing prompts and utilizing LLMs on textual information related to the environment setup and the observations of LLM agents. Using the OpenAI Chat API powered by GPT-4.0, we conduct experiments to simulate interactions and evaluate the performance of LLM agents in two driving scenarios: unsignalized intersection and highway platoon. The results show that LLM agents can handle dynamically changing environments in Markov games, and social norms evolve among LLM agents in both scenarios. In the intersection game, LLM agents tend to adopt a conservative driving policy when facing a potential car crash. The advantage of LLM agents in games lies in their strong operability and analyzability, facilitating experimental design.