This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Pedestrian Safety Performance Prediction using Machine Learning Techniques
ISSN: 0148-7191, e-ISSN: 2688-3627
Published September 22, 2021 by SAE International in United States
This content contains downloadable datasetsAnnotation ability available
As per WHO 2018 report, pedestrian fatalities account for 23% of world road accident fatalities. Every day 850 pedestrians lose their lives in the world. As per MoRTH 2018 report, 16% of road accident fatalities are of pedestrians in India. Everyday 64 pedestrians lose their lives in India.
Based on accident data, one of the most common reason for the pedestrian fatality is head injury due to primary contact from vehicle front-end structure. Pedestrian head injury performance highly depends on front-end styling, bonnet stiffness, clearance with aggregates underneath the bonnet and hard contact points.
During concept stage of vehicle development, safety recommendation on front-end design is provided based on geometric assessment of the class A surface. This paper presents the novel approach of using machine-learning algorithms to predict the head injury performance at the early stage of vehicle design using the knowledge of existing vehicle simulation data and new vehicle design features. Machine learning based mathematical model has been developed considering critical design parameters such as clearance with aggregates, impact point location with respect to hard points, stiffness of bonnet as input variables and head injury criteria (HIC) as output variable from existing vehicles. Different supervised machine learning algorithms such as random forest, neural networks, logistic regression and supporting vector regression are trained and tested using available data. Subsequently, the suitable mathematical model was selected based on the model score. Identified model was able to predict the pedestrian head injury criteria (HIC) within 20% of margin of error for majority of the impact points. This approach has significant potential and provides opportunities for giving directional feedback during early stage of the vehicle development.
Data Sets - Support Documents
|Unnamed Dataset 1|
|Unnamed Dataset 2|
|Unnamed Dataset 3|
|Unnamed Dataset 4|
|Unnamed Dataset 5|
|Unnamed Dataset 6|
- Automotive Industry Standards (AIS), AIS-100 Requirements for the Protection of Pedestrian and Other Vulnerable Road Users in the Event of a Collision with a Motor Vehicle
- Osamu , I.J. , Imura, S.K. Prediction of Pedestrian Protection Performance using Machine Learning ESV Conference
- du Boisberranger , J. , Van den Bossche , J. Random Forest Regression https://scikitlearn.org/stable/modules/generated/sklearn.ensemble.RandomForestRegressor.html