Driving Everywhere with
Large Language Model Policy Adaptation

1NVIDIA Research, 2University of Southern California, 3University of Washington, 3Stanford University
Example Image

Driving Everywhere with Large Language Driving Assistant (LLaDA).

Abstract

Adapting driving behavior to new environments, customs, and laws is a long-standing problem in autonomous driving, precluding the widespread deployment of autonomous vehicles (AVs).

In this paper, we present LLaDA, a simple yet powerful tool that enables human drivers and autonomous vehicles alike to drive everywhere by adapting their tasks and motion plans to traffic rules in new locations. LLaDA achieves this by leveraging the impressive zero-shot generalizability of large language models (LLMs) in interpreting the traffic rules in the local driver handbook. Through an extensive user study, we show that LLaDA's instructions are useful in disambiguating in-the-wild unexpected situations. We also demonstrate LLaDA's ability to adapt AV motion planning policies in real-world datasets; LLaDA outperforms baseline planning approaches on all our metrics.

Functions

Example Image
We show a few examples of LLaDA to help drivers drive everywhere with language policy. We show LLaDA could help the drivers obtain prompt notification and correct their corresponding behaviors in different countries with diverse plans and diverse unexpected situations. Also, it is obvious that LLM cannot provide accurate instruction based on each location without the background of the traffic code.

Updates

Thanks for your interest in LLaDA! We will update more details shortly. Stay tuned!

BibTeX

@inproceedings{li2024llada,
        title={Driving Everywhere with Large Language Model Policy Adaptation},
        author={Li, Boyi and Wang, Yue and Mao, Jiageng and Ivanovic, Boris and Veer, Sushant and Leung, Karen and Pavone, Marco},
        journal={CVPR},
        year={2024},
      }
This website template is borrowed from Nerfies.