The Application of Driver Models in the Safety Assessment of Autonomous Vehicles: A Survey

Driver models play a vital role in developing and verifying autonomous vehicles (AVs). Previously, they are mainly applied in traffic flow simulation to model realistic driver behavior. With the development of AVs, driver models attract much attention again due to their potential contributions to AV certification. The simulation-based testing method is considered an effective measure to accelerate AV testing due to its safe and efficient characteristics. Nonetheless, realistic driver models are prerequisites for valid simulation results. Additionally, an AV is assumed to be at least as safe as a careful and competent driver. Therefore, driver models are inevitable for AV safety assessment. However, no comparison or discussion of driver models is available regarding their utility to AVs in the last five years despite their necessities in the release of AVs. This motivates us to present a comprehensive survey of driver models in the paper and compare their applicability. Requirements for driver models in terms of their application to AV safety assessment are discussed. A summary of driver models for simulation-based testing and AV certification is provided. Evaluation metrics are defined to compare their strength and weakness. Finally, an architecture for a careful and competent driver model is proposed. Challenges and future work are elaborated. This study gives related researchers especially regulators an overview and helps them to define appropriate driver models for AVs.