ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving

TL;DR

This paper introduces a planning-oriented active learning approach for end-to-end autonomous driving that reduces data annotation needs by selectively labeling the most useful samples, achieving high performance with less data.

Contribution

The paper proposes a novel planning-oriented active learning method tailored for autonomous driving, focusing on data efficiency and sample selection based on diversity and usefulness.

Findings

Outperforms general active learning methods significantly.

Achieves comparable performance to state-of-the-art methods with only 30% of data.

Reduces annotation costs while maintaining high driving performance.

Abstract

End-to-end differentiable learning for autonomous driving (AD) has recently become a prominent paradigm. One main bottleneck lies in its voracious appetite for high-quality labeled data e.g. 3D bounding boxes and semantic segmentation, which are notoriously expensive to manually annotate. The difficulty is further pronounced due to the prominent fact that the behaviors within samples in AD often suffer from long tailed distribution. In other words, a large part of collected data can be trivial (e.g. simply driving forward in a straight road) and only a few cases are safety-critical. In this paper, we explore a practically important yet under-explored problem about how to achieve sample and label efficiency for end-to-end AD. Specifically, we design a planning-oriented active learning method which progressively annotates part of collected raw data according to the proposed diversity and usefulness criteria for planning routes. Empirically, we show that our planning-oriented approach could outperform general active learning methods by a large margin. Notably, our method achieves comparable performance with state-of-the-art end-to-end AD methods - by using only 30% nuScenes data. We hope our work could inspire future works to explore end-to-end AD from a data-centric perspective in addition to methodology efforts.