DriveGPT: Scaling Autoregressive Behavior Models for Driving
Xin Huang, Eric M Wolff, Paul Vernaza, Tung Phan-Minh, Hongge Chen, David S Hayden, Mark Edmonds, Brian Pierce
Abstract
We present DriveGPT, a scalable behavior model for autonomous driving. We model driving as a sequential decision-making task, and learn a transformer model to predict future agent states as tokens in an autoregressive fashion. We scale up our model parameters and training data by multiple orders of magnitude, enabling us to explore the scaling properties in terms of dataset size, model parameters, and compute. We evaluate DriveGPT across different scales in a planning task, through both quantitative metrics and qualitative examples, including closed-loop driving in complex real-world scenarios. In a separate prediction task, DriveGPT outperforms state-of-the-art baselines and exhibits improved performance by pretraining on a large-scale dataset, further validating the benefits of data scaling.
BibTeX
@inproceedings{
huang2025drivegpt,
title={Drive{GPT}: Scaling Autoregressive Behavior Models for Driving},
author={Xin Huang and Eric M Wolff and Paul Vernaza and Tung Phan-Minh and Hongge Chen and David S Hayden and Mark Edmonds and Brian Pierce and Xinxin Chen and Pratik Elias Jacob and Xiaobai Chen and Chingiz Tairbekov and Pratik Agarwal and Tianshi Gao and Yuning Chai and Siddhartha Srinivasa},
booktitle={Forty-second International Conference on Machine Learning},
year={2025},
url={https://openreview.net/forum?id=SBUxQakoJJ}
}