CAT: Closed-loop Adversarial Training for Safe End-to-End Driving

Linrui Zhang, Zhenghao Peng, Quanyi Li, Bolei Zhou

Keywords: Safety-Critical Scenario Generation, Adversarial Training, End-to-End Driving

Abstract: Driving safety is a top priority for autonomous vehicles. Orthogonal to prior work handling accident-prone traffic events by algorithm designs at the policy level, we investigate a \textbf{C}losed-loop \textbf{A}dversarial \textbf{T}raining (CAT) framework for safe end-to-end driving in this paper through the lens of environment augmentation. CAT aims to continuously improve the safety of driving agents by training the agent on safety-critical scenarios that are dynamically generated over time. A novel resampling technique is developed to turn log-replay real-world driving scenarios into safety-critical ones via probabilistic factorization, where the adversarial traffic generation is modeled as the multiplication of standard motion prediction sub-problems. Consequently, CAT can launch more efficient physical attacks compared to existing safety-critical scenario generation methods and yields a significantly less computational cost in the iterative learning pipeline. We incorporate CAT into the MetaDrive simulator and validate our approach on hundreds of driving scenarios imported from real-world driving datasets. Experimental results demonstrate that CAT can effectively generate adversarial scenarios countering the agent being trained. After training, the agent can achieve superior driving safety in both log-replay and safety-critical traffic scenarios on the held-out test set. Code and data are available at: https://metadriverse.github.io/cat

Student First Author: yes

Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)

Video: https://metadriverse.github.io/cat

Website: https://metadriverse.github.io/cat

Code: https://github.com/metadriverse/cat