NATURALISTIC DRIVING BEHAVIOR
The goal of this project is to define and validate values for the parameters in the set of safety assessment metrics developed in Phase I of the Driving Safety Performance Metrics for ADS-Equipped Vehicles project. IAM will determine the best representative values from existing US naturalistic driving datasets.
IAM member Mobileye originated a mathematical model for automated vehicle safety based on human behaviors that works to inform IAM’s naturalistic driving behavior project. The technology-neutral model with five human driver-inspired safety rules: don’t hit the car in front of you, don’t cut in recklessly, right of way is given—not taken, be cautious in areas with limited visibility, and if you can avoid a crash without causing another one—you must.