Summary of Can Llms Understand Social Norms in Autonomous Driving Games?, by Boxuan Wang et al.
Can LLMs Understand Social Norms in Autonomous Driving Games?
by Boxuan Wang, Haonan Duan, Yanhao Feng, Xu Chen, Yongjie Fu, Zhaobin Mo, Xuan Di
First submitted to arxiv on: 22 Aug 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper investigates the application of Large Language Models (LLMs) in understanding and modeling social norms in autonomous driving games. By introducing LLMs as intelligent agents into Markov games, researchers simulate interactions to evaluate the performance of these agents in various scenarios. The study explores two driving scenarios: unsignalized intersection and highway platoon. Results show that LLM-based agents can handle dynamically changing environments and social norms emerge among individual agents. Notably, agents tend to adopt a conservative driving policy when facing potential car crashes in the intersection game. This work highlights the benefits of using LLMs in autonomous driving games, including their strong operability and analyzability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine playing a game where you make decisions based on text prompts. This paper explores how computers can learn to play these kinds of games by understanding social norms. Social norms are shared standards that guide behavior in a group. The researchers used Large Language Models, which are advanced computer programs, to simulate interactions and see how they behave in different scenarios. They found that these models can handle changing environments and develop their own rules for playing the game. This is important because it could help develop more realistic artificial intelligence in areas like self-driving cars. |
