Autonomous driving systems have witnessed a significant development during the past years thanks to the advance in machine learning-enabled sensing and decision-making algorithms. One critical challenge for their massive deployment in the real world is their safety evaluation. Most existing driving systems are still trained and evaluated on naturalistic scenarios collected from daily life or heuristically-generated adversarial ones. However, the large population of cars, in general, leads to an extremely low collision rate, indicating that the safety-critical scenarios are rare in the collected real-world data. Thus, methods to artificially generate scenarios become crucial to measure the risk and reduce the cost. In this survey, we focus on the algorithms of safety-critical scenario generation in autonomous driving. We first provide a comprehensive taxonomy of existing algorithms by dividing them into three categories: data-driven generation, adversarial generation, and knowledge-based generation. Then, we discuss useful tools for scenario generation, including simulation platforms and packages. Finally, we extend our discussion to five main challenges of current works -- fidelity, efficiency, diversity, transferability, controllability -- and research opportunities lighted up by these challenges.
翻译:在过去几年里,自主驾驶系统经历了一个重大的发展,这归功于机器学习辅助遥感和决策算法的进步。在现实世界中大规模部署这些系统的一个关键挑战是安全评价。大多数现有的驾驶系统仍然在从日常生活中收集的自然假设情景或超自然产生的对抗性假设情景方面接受训练和评价。然而,汽车数量庞大,一般而言,碰撞率极低,表明所收集的真实世界数据很少出现安全危急假设情景。因此,人为生成假设情景的方法对于衡量风险和降低成本至关重要。在本次调查中,我们侧重于自主驾驶中安全临界情景生成的算法。我们首先通过将现有算法分为三类提供全面的分类:数据驱动生成、对抗生成和知识生成。然后,我们讨论生成假设情景的有用工具,包括模拟平台和成套数据。最后,我们将我们的讨论扩大到当前工作的五大挑战 -- -- 忠诚、效率、多样性、可转移性、可转移性、可控性 -- -- 以及由这些挑战所减轻的研究机会。