Forward Collision Warning Systems: Validating Driving Simulator Results with Field Data
This work addresses the need to validate driving simulator results for ADAS evaluation, but it is incremental as it applies existing methods to new data.
The study tackled evaluating driver braking behavior with a forward collision warning system in a driving simulator and validated the results with field data, finding a statistically significant mean speed reduction of 15.07 mph post-FCW.
With the advent of Advanced Driver Assistance Systems (ADAS), there is an increasing need to evaluate driver behavior while using such technology. In this unique study, a forward collision warning (FCW) system using connected vehicle technology, was introduced in a driving simulator environment, to evaluate driver braking behavior and then the results are validated using data from field tests. A total of 93 participants were recruited for this study, for which a virtual network of South Baltimore was created. A one sample t-test was conducted, and it was found that the mean reduction in speed of 15.07 mph post FCW, is statistically significant. A random forest, machine learning algorithm was found to be the best fit for ranking the most important variables in the dataset by order of importance. Field data obtained from the University of Michigan Transportation Research Institute (UMTRI), substantiated the FCW findings from this driving simulator study.