Recently, a number of simulation testing approaches have been proposed to generate diverse driving scenarios for autonomous driving systems (ADSs) testing. However, the behaviors of NPC vehicles in these scenarios generated by previous approaches are predefined and mutated before simulation execution, ignoring traffic signals and the behaviors of the Ego vehicle. Thus, a large number of the violations they found are induced by unrealistic behaviors of NPC vehicles, revealing no bugs of ADSs. Besides, the vast scenario search space of NPC behaviors during the iterative mutations limits the efficiency of previous approaches. To address these limitations, we propose a novel scenario-based testing framework, DynNPC, to generate more violation scenarios induced by the ADS. Specifically, DynNPC allows NPC vehicles to dynamically generate behaviors using different driving strategies during simulation execution based on traffic signals and the real-time behavior of the Ego vehicle. We compare DynNPC with state-of-the-art scenario-based testing approaches. Our evaluation has demonstrated the effectiveness and efficiency of DynNPC in finding more violation scenarios induced by the ADS.

翻译：摘要：近期，研究者提出了多种仿真测试方法，用于生成多样化的驾驶场景以测试自动驾驶系统。然而，先前方法生成的场景中，非玩家角色车辆的行为在仿真执行前被预定义和变异，忽略了交通信号及主车行为。因此，它们发现的大量违规场景是由非玩家角色车辆的不真实行为引发的，并未揭示自动驾驶系统的缺陷。此外，迭代变异过程中非玩家角色行为的巨大场景搜索空间限制了先前方法的效率。为解决这些局限，我们提出了一种新颖的基于场景的测试框架DynNPC，用于生成更多由自动驾驶系统引发的违规场景。具体而言，DynNPC允许非玩家角色车辆在仿真执行期间，根据交通信号和主车的实时行为，动态采用不同驾驶策略生成行为。我们将DynNPC与最先进的基于场景的测试方法进行了对比。评估结果表明，DynNPC在发现更多由自动驾驶系统引发的违规场景方面具有有效性和高效性。