Criticality Metrics Study for Safety Evaluation of Merge Driving Scenarios, Using Near-miss Video Data

In autonomous driving vehicles with an automation level greater than three, the autonomous system is responsible for safe driving, instead of the human driver. Hence, the driving safety of autonomous driving vehicles must be ensured before they are used on the road. Because it is not realistic to evaluate all test conditions in real traffic, computer simulation methods can be used. Since driving safety performance can be evaluated by simulating different driving scenarios and calculating the criticality metrics that represent dangerous collision risks, it is necessary to study and define the criticality metrics for the type of driving scenarios. This study focused on the risk of collisions in the confluence area because it was known that the accident rate in the confluence area is much higher than on the main roadway. There have been several experimental studies on safe driving behaviors in the confluence area; however, there has been little study logically exploring the merging actions with mathematical metrics. In light of this, this study introduces a criticality metric representing the risk of a collision in a junction area. The metric calculates the reaction level required to avoid a predicted collision risk; therefore, a safety evaluation can be performed by assessing the reaction effort to prevent such collisions in a driving scenario. The near-miss video data from the database is used to validate the proposed metric for the merging scenario. The database contains various real merging scenarios experienced by human drivers. The proposed metric was validated to identify a critical situation with collision risks and a safe driving situation that can prevent collisions easily, using sample data of merging scenarios from the database. Moreover, an example application for safety assessment was investigated. In summary, the safety performance of autonomous driving vehicles in merging can be evaluated through simulations using the criticality metric. In the future, the results of this study could be applied to develop an on-board risk detection function in the confluence area.