Real-to-Virtual Domain Unification for End-to-End Autonomous Driving

TL;DR

This paper introduces DU-drive, an unsupervised framework that unifies real and virtual data for end-to-end autonomous driving, improving generalization and performance by transforming real data into a virtual domain.

Contribution

The paper proposes a novel real-to-virtual domain unification method that reduces domain shift and leverages unlimited virtual data for autonomous driving.

Findings

Outperforms existing methods on public datasets and simulators.

Effectively eliminates domain shift across diverse data sources.

Improves prediction accuracy and interpretability in autonomous driving tasks.

Abstract

In the spectrum of vision-based autonomous driving, vanilla end-to-end models are not interpretable and suboptimal in performance, while mediated perception models require additional intermediate representations such as segmentation masks or detection bounding boxes, whose annotation can be prohibitively expensive as we move to a larger scale. More critically, all prior works fail to deal with the notorious domain shift if we were to merge data collected from different sources, which greatly hinders the model generalization ability. In this work, we address the above limitations by taking advantage of virtual data collected from driving simulators, and present DU-drive, an unsupervised real-to-virtual domain unification framework for end-to-end autonomous driving. It first transforms real driving data to its less complex counterpart in the virtual domain and then predicts vehicle control commands from the generated virtual image. Our framework has three unique advantages: 1) it maps driving data collected from a variety of source distributions into a unified domain, effectively eliminating domain shift; 2) the learned virtual representation is simpler than the input real image and closer in form to the "minimum sufficient statistic" for the prediction task, which relieves the burden of the compression phase while optimizing the information bottleneck tradeoff and leads to superior prediction performance; 3) it takes advantage of annotated virtual data which is unlimited and free to obtain. Extensive experiments on two public driving datasets and two driving simulators demonstrate the performance superiority and interpretive capability of DU-drive.