In autonomous driving, detection of abnormal driving behaviors is essential to ensure the safety of vehicle controllers. Prior works in vehicle anomaly detection have shown that modeling interactions between agents improves detection accuracy, but certain abnormal behaviors where structured road information is paramount are poorly identified, such as wrong-way and off-road driving. We propose a novel unsupervised framework for highway anomaly detection named Structural Attention-Based Recurrent VAE (SABeR-VAE), which explicitly uses the structure of the environment to aid anomaly identification. Specifically, we use a vehicle self-attention module to learn the relations among vehicles on a road, and a separate lane-vehicle attention module to model the importance of permissible lanes to aid in trajectory prediction. Conditioned on the attention modules' outputs, a recurrent encoder-decoder architecture with a stochastic Koopman operator-propagated latent space predicts the next states of vehicles. Our model is trained end-to-end to minimize prediction loss on normal vehicle behaviors, and is deployed to detect anomalies in (ab)normal scenarios. By combining the heterogeneous vehicle and lane information, SABeR-VAE and its deterministic variant, SABeR-AE, improve abnormal AUPR by 18% and 25% respectively on the simulated MAAD highway dataset over STGAE-KDE. Furthermore, we show that the learned Koopman operator in SABeR-VAE enforces interpretable structure in the variational latent space. The results of our method indeed show that modeling environmental factors is essential to detecting a diverse set of anomalies in deployment. For code implementation, please visit https://sites.google.com/illinois.edu/saber-vae.

翻译：在自动驾驶中，检测异常驾驶行为对于确保车辆控制器的安全性至关重要。先前在车辆异常检测方面的研究表明，对智能体间交互进行建模可提升检测精度，但某些严重依赖结构化道路信息的异常行为（如逆行和越野驾驶）仍难以准确识别。我们提出一种名为"基于结构注意力的循环变分自编码器"（SABeR-VAE）的无监督高速公路异常检测框架，该框架显式利用环境结构辅助异常识别。具体而言，我们采用车辆自注意力模块学习道路上车辆间的关联性，并设计独立的车道-车辆注意力模块对可行驶车道的重要性进行建模以辅助轨迹预测。基于注意力模块输出，一种结合随机Koopman算子传播潜空间的循环编码器-解码器架构可预测车辆后续状态。模型以端到端方式训练以最小化正常车辆行为的预测损失，并部署于（异）常场景中检测异常。通过融合异构的车辆与车道信息，SABeR-VAE及其确定性变体SABeR-AE在模拟MAAD高速公路数据集上相比于STGAE-KDE分别将异常AUPR提升18%和25%。此外，研究表明SABeR-VAE中学习的Koopman算子在变分潜空间中强制生成可解释结构。实验结果充分证明，建模环境因素对于在部署中检测多样化异常至关重要。代码实现请访问：https://sites.google.com/illinois.edu/saber-vae。