CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generation-猫眼课题宝

DOI：

发表时间：

2021-10

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Wenhao Ding;Hao-ming Lin;Bo Li;Ding Zhao

生成至关重要但难以收集的安全关键场景提供了评估自动驾驶系统稳健性的有效方法。然而，场景的多样性和生成方法的效率受到安全关键场景的稀有性和结构的严重限制。因此，现有的仅根据观测数据估计分布的生成模型并不能令人满意地解决这个问题。在本文中，我们将因果关系作为先验集成到场景生成中，并提出了一种基于流的生成框架，因果自回归流（CausalAF）。 CausalAF 鼓励生成模型通过新颖的因果屏蔽操作来揭示和跟踪生成对象之间的因果关系，而不是仅从观测数据中搜索样本。通过学习生成的场景如何导致风险情况的因果机制，而不是仅仅从数据中学习相关性，CausalAF 显着提高了学习效率。对三种异构流量场景的大量实验表明，CausalAF 需要更少的优化资源来有效生成安全关键场景。我们还表明，使用生成的场景作为额外的训练样本可以根据经验提高自动驾驶算法的鲁棒性。

Generating safety-critical scenarios, which are crucial yet difficult to collect, provides an effective way to evaluate the robustness of autonomous driving systems. However, the diversity of scenarios and efficiency of generation methods are heavily restricted by the rareness and structure of safety-critical scenarios. Therefore, existing generative models that only estimate distributions from observational data are not satisfying to solve this problem. In this paper, we integrate causality as a prior into the scenario generation and propose a flow-based generative framework, Causal Autoregressive Flow (CausalAF). CausalAF encourages the generative model to uncover and follow the causal relationship among generated objects via novel causal masking operations instead of searching the sample only from observational data. By learning the cause-and-effect mechanism of how the generated scenario causes risk situations rather than just learning correlations from data, CausalAF significantly improves learning efficiency. Extensive experiments on three heterogeneous traffic scenarios illustrate that CausalAF requires much fewer optimization resources to effectively generate safety-critical scenarios. We also show that using generated scenarios as additional training samples empirically improves the robustness of autonomous driving algorithms.

CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generation

文献摘要

相似文献