DriveGPT: Scaling Autoregressive Behavior Models for Driving
This work addresses autonomous driving for improved safety and efficiency, but it is incremental as it builds on existing transformer and scaling paradigms.
The authors tackled the problem of autonomous driving by modeling it as a sequential decision-making task with DriveGPT, a scalable autoregressive transformer, and achieved improved performance in prediction tasks, outperforming state-of-the-art baselines through large-scale data and model scaling.
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.