As autonomous driving technology matures, safety and robustness of its key components, including trajectory prediction, is vital. Though real-world datasets, such as Waymo Open Motion, provide realistic recorded scenarios for model development, they often lack truly safety-critical situations. Rather than utilizing unrealistic simulation or dangerous real-world testing, we instead propose a framework to characterize such datasets and find hidden safety-relevant scenarios within. Our approach expands the spectrum of safety-relevance, allowing us to study trajectory prediction models under a safety-informed, distribution shift setting. We contribute a generalized scenario characterization method, a novel scoring scheme to find subtly-avoided risky scenarios, and an evaluation of trajectory prediction models in this setting. We further contribute a remediation strategy, achieving a 10% average reduction in prediction collision rates. To facilitate future research, we release our code to the public: github.com/cmubig/SafeShift

翻译：随着自动驾驶技术的成熟，其关键组件（包括轨迹预测）的安全性和鲁棒性至关重要。尽管真实世界数据集（如Waymo Open Motion）为模型开发提供了逼真的记录场景，但它们往往缺乏真正的安全关键情境。我们并未使用不现实的模拟或危险的真实世界测试，而是提出一个框架来描述此类数据集，并在其中发现隐藏的安全相关场景。我们的方法扩展了安全相关性光谱，使我们能够在安全信息分布偏移设置下研究轨迹预测模型。我们贡献了一种通用的场景表征方法、一种用于发现被微妙避免的风险场景的新型评分方案，以及在此设置下对轨迹预测模型的评估。我们进一步提出一种补救策略，平均降低10%的预测碰撞率。为促进未来研究，我们公开了代码：github.com/cmubig/SafeShift