DynNPC: Finding More Violations Induced by ADS in Simulation Testing through Dynamic NPC Behavior Generation
For ADS testing, DynNPC addresses the problem of unrealistic NPC behaviors and low search efficiency, providing a more effective method to find ADS-induced violations.
DynNPC generates more violation scenarios induced by autonomous driving systems (ADS) by allowing NPC vehicles to dynamically adjust behaviors based on traffic signals and Ego vehicle actions, outperforming state-of-the-art approaches in effectiveness and efficiency.
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.