用物理因果审计端到端驾驶规划器 Physics-Grounded Causal Auditing of End-to-End Driving Planners

精读摘要

模仿学习训练的端到端自动驾驶规划器容易学到统计捷径：把恰好与专家动作同时出现的场景元素（路边物体、建筑立面）与驾驶决策关联，而不是与真正因果决定决策的变量关联。这种「因果混淆」会在长尾场景中悄悄侵蚀可靠性，而且难以察觉——主流的开环指标（L2 位移与碰撞率）由自车状态主导，无法反映规划器是否真的理解了场景。研究提出基于物理的因果审计方法，专门检测这类隐患。 End-to-end driving planners trained by imitation are prone to statistical shortcuts, associating scene elements that merely co-occur with expert actions rather than variables that causally determine them. This causal confusion silently compromises reliability in long-tail scenarios and is hard to detect because open-loop metrics like L2 displacement and collision rate are dominated by ego status. The work proposes physics-grounded causal auditing to detect such failures.