Predicting Pedestrian Injury Metrics Based on Vehicle Front-End Design

Simulations provide vehicle designers with the capability to evaluate the safety of their designs in a wide variety of scenarios. However, the high-fidelity simulations required for safety assessment carry significant computational costs. As such, the engineering team must carefully select automotive designs to simulate, and use the results obtained to accurately predict the performance of new designs over a wide range of metrics. This paper describes the modeling of automotive simulation outputs to accurately predict a large number of widely used pedestrian injury metrics given the vehicle front-end design. The models in this paper allow the vehicle designer to identify and focus on the variables that most affect the different injury metrics, and determine which variables are most important to the overall safety performance of the vehicle.