ActiveAD：面向规划的端到端自动驾驶主动学习
ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving
提出面向规划任务的主动学习采样策略，通过多样性指标解决冷启动、不确定性指标选择关键样本，可复用于视觉模型训练中的数据高效标注场景。
原文依据 we propose ActiveAD, a planning-oriented active learning strategy designed to enhance sampling and labeling efficiency in end-to-end autonomous driving.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论端到端可微学习已成为自动驾驶（AD）中的一种重要范式。该方法的一个显著瓶颈在于其对高质量标注数据（如3D边界框和语义分割）的巨大需求，而这些数据的人工标注成本尤其高昂。自动驾驶数据集中的长尾分布加剧了这一挑战，其中收集到的大部分数据可能是平凡的（例如在直道上直行），只有少数实例对安全至关重要。本文提出ActiveAD，一种面向规划的主动学习策略，旨在提升端到端自动驾驶中的采样与标注效率。ActiveAD基于我们新开发的指标，逐步对收集到的原始数据进行部分标注。我们设计了创新的多样性指标以增强初始样本选择，解决冷启动问题。此外，我们开发了不确定性指标，在后续批次选择中为路线规划的最终目的挑选有价值的样本。实证结果表明，我们的方法显著超越了传统主动学习方法。值得注意的是，我们的方法在开环nuScenes和闭环CARLA评估中仅使用30%的数据，就达到了与最优端到端自动驾驶方法相当的结果。
英文原文摘要 1370 字符
End-to-end differentiable learning has emerged as a prominent paradigm in autonomous driving (AD). A significant bottleneck in this approach is its substantial demand for high-quality labeled data, such as 3D bounding boxes and semantic segmentation, which are especially expensive to annotate manually. This challenge is exacerbated by the long tailed distribution in AD datasets, where a substantial portion of the collected data might be trivial (e.g. simply driving straight on a straight road) and only a minority of instances are critical to safety. In this paper, we propose ActiveAD, a planning-oriented active learning strategy designed to enhance sampling and labeling efficiency in end-to-end autonomous driving. ActiveAD progressively annotates parts of collected raw data based on our newly developed metrics. We design innovative diversity metrics to enhance initial sample selection, addressing the cold-start problem. Furthermore, we develop uncertainty metrics to select valuable samples for the ultimate purpose of route planning during subsequent batch selection. Empirical results demonstrate that our approach significantly surpasses traditional active learning methods. Remarkably, our method achieves comparable results to state-of-the-art end-to-end AD methods - by using only 30% data in both open-loop nuScenes and closed-loop CARLA evaluation.