用海量无标签数据训练更安全的自动刹车系统，实测效果远超传统规则。
Scaling Learning-based AEB with Massive Unlabeled Data
- 基于教师生成伪标签，结合小样本标注数据反馈优化模型。
- 在10亿条驾驶数据上训练后，误触发率低于100:1，事故前行驶里程提升35%。
- 适合自动驾驶安全系统研发、量产部署中的算法工程师参考。
本文研究如何在生产约束下，利用海量无标签车队数据扩展基于学习的自动紧急制动（AEB）系统。方法基于元反馈半监督学习（MF-SSL），由教师模型为无标签驾驶数据生成伪标签，并使用少量标注锚点作为关键安全反馈进行更新。然而，在实际部署中，锚点歧义与标注-无标签数据不匹配会放大伪标签错误，引发虚假触发。为此，提出稳定化的MF-SSL框架：(i) 噪声感知解耦，剔除易混淆锚点以避免教师更新路径污染；(ii) 基于运动学门控的伪标签生成并引入教师冲突惩罚，抑制不匹配导致的风险幻觉，同时保持广泛覆盖。大量实验表明，随着无标签数据从100万到10亿个窗口规模扩展，安全性持续提升且舒适性保持稳定。训练完成的学生模型已部署至数十万辆汽车，验证里程超10^9公里，正激活与误激活比例超过100:1，事故前行驶里程相较仅依赖规则的生产基线提升35%。
原文摘要 · Abstract (English)
This paper studies how to scale learning-based automatic emergency braking (AEB) with massive unlabeled fleet data under production constraints. Our approach is based on meta-feedback semi-supervised learning (MF-SSL), where a teacher generates pseudo labels for unlabeled driving data and is updated using a small labeled anchor set as safety-critical feedback. In production, anchor ambiguity and labeled-unlabeled mismatch can amplify systematic pseudo-label errors, leading to spurious triggers. We propose a stabilized MF-SSL framework with (i) Noise-Aware Decoupling, which removes ambiguity-prone anchors from the teacher's supervised update path, and (ii) kinematics-gated pseudo-labeling with a teacher conflict penalty to suppress mismatch-induced risk hallucinations on unlabeled data while maintaining broad coverage. Extensive experiments show consistent gains as unlabeled data scale from 1M to 1B windows, improving safety while keeping comfort stable. The 1B-trained student model is deployed to hundreds of thousands of vehicles and validated over \$10^9$ km of driving, achieving a positive-to-false activation ratio exceeding 100:1 and a 35% improvement in accident-free driving mileage over a production rule-only baseline.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。