一句话：提出ThirdEye，将XAI注意力图转为置信度分数，用于运行时监控并区分安全与不安全驾驶行为。
自动驾驶系统需要在未知和不确定场景下在线识别异常条件，以保证安全。本文提出一种根植于可解释人工智能（XAI）所计算注意力图的运行时监控技术。其核心思想是：不常见的注意力图往往对应意外的运行时条件；因此可将注意力图转化为置信度分数，用于区分安全与不安全的驾驶行为。作者实现了名为 ThirdEye 的工具。摘要未报告具体数据集、指标或定量结果，但评估目标可理解为利用注意力图导出的置信度对驾驶行为进行安全/不安全判别。
Automated online recognition of unexpected conditions is an indispensable component of autonomous vehicles to ensure safety even in unknown and uncertain situations. In this paper we propose a runtime monitoring technique rooted in the attention maps computed by explainable artificial intelligence techniques. Our approach, implemented in a tool called ThirdEye, turns attention maps into confidence scores that are used to discriminate safe from unsafe driving behaviours. The intuition is that uncommon attention maps are associated with unexpected runtime conditions.