论文标题
谁让驾驶员停止？迈向以驾驶员为中心的风险评估：通过因果推理的风险对象识别
Who Make Drivers Stop? Towards Driver-centric Risk Assessment: Risk Object Identification via Causal Inference
论文作者
论文摘要
由于驾驶员错误，大量的人死于道路事故。为了减少死亡，开发智能驾驶系统协助驾驶员确定潜在的风险是迫切需要的。通常根据现有作品的碰撞预测来定义危险情况。但是，碰撞只是潜在风险的来源，需要更通用的定义。在这项工作中，我们提出了一种以驾驶员为中心的风险定义，即影响驾驶员行为的物体是风险的。引入了一个称为风险对象识别的新任务。我们将任务作为原因效应问题提出，并基于因果推断提供了一种新颖的两阶段风险对象识别框架，该框架与提议的对象级可操作驾驶模型。与本田研究所驾驶数据集（HDD）上强的基线相比，我们证明了风险对象识别的良好性能。我们的框架在强大的基线上实现了7.5％的平均表现。
A significant amount of people die in road accidents due to driver errors. To reduce fatalities, developing intelligent driving systems assisting drivers to identify potential risks is in an urgent need. Risky situations are generally defined based on collision prediction in the existing works. However, collision is only a source of potential risks, and a more generic definition is required. In this work, we propose a novel driver-centric definition of risk, i.e., objects influencing drivers' behavior are risky. A new task called risk object identification is introduced. We formulate the task as the cause-effect problem and present a novel two-stage risk object identification framework based on causal inference with the proposed object-level manipulable driving model. We demonstrate favorable performance on risk object identification compared with strong baselines on the Honda Research Institute Driving Dataset (HDD). Our framework achieves a substantial average performance boost over a strong baseline by 7.5%.
