AuthSim: Towards Authentic and Effective Safety-critical Scenario Generation for Autonomous Driving Tests

TL;DR

AuthSim is a novel platform that generates more authentic and effective safety-critical scenarios for testing autonomous driving systems by integrating a three-layer safety region model with reinforcement learning, improving scenario realism and robustness.

Contribution

This paper introduces AuthSim, the first comprehensive platform combining a three-layer safety region model with reinforcement learning to enhance scenario authenticity and effectiveness.

Findings

AuthSim achieves a 5.25% improvement in average cut-in distance.

AuthSim enhances average collision interval time by 27.12%.

AuthSim outperforms existing methods in generating safety-critical scenarios.

Abstract

Generating adversarial safety-critical scenarios is a pivotal method for testing autonomous driving systems, as it identifies potential weaknesses and enhances system robustness and reliability. However, existing approaches predominantly emphasize unrestricted collision scenarios, prompting non-player character (NPC) vehicles to attack the ego vehicle indiscriminately. These works overlook these scenarios' authenticity, rationality, and relevance, resulting in numerous extreme, contrived, and largely unrealistic collision events involving aggressive NPC vehicles. To rectify this issue, we propose a three-layer relative safety region model, which partitions the area based on danger levels and increases the likelihood of NPC vehicles entering relative boundary regions. This model directs NPC vehicles to engage in adversarial actions within relatively safe boundary regions, thereby augmenting the scenarios' authenticity. We introduce AuthSim, a comprehensive platform for generating authentic and effective safety-critical scenarios by integrating the three-layer relative safety region model with reinforcement learning. To our knowledge, this is the first attempt to address the authenticity and effectiveness of autonomous driving system test scenarios comprehensively. Extensive experiments demonstrate that AuthSim outperforms existing methods in generating effective safety-critical scenarios. Notably, AuthSim achieves a 5.25% improvement in average cut-in distance and a 27.12% enhancement in average collision interval time, while maintaining higher efficiency in generating effective safety-critical scenarios compared to existing methods. This underscores its significant advantage in producing authentic scenarios over current methodologies.