Driving Everywhere with Large Language Model Policy Adaptation

The article presents LLaDA, a tool that enables autonomous vehicles and human drivers to adapt to different traffic rules in new environments. LLaDA leverages the capabilities of large language models to interpret local traffic rules. It has been shown to be effective in real-world scenarios and outperforms baseline planning approaches. The tool can be immediately applied to any autonomous driving system to improve performance in new locations with different traffic rules.

Publication date: 9 Feb 2024
Project Page: Not provided
Paper: https://arxiv.org/pdf/2402.05932