A safety score for the assessment of driving style. (9th June 2021)

• Record Type: Journal Article
• Authors: Schöner, Hans-Peter; Pretto, Paolo; Sodnik, Jaka; Kaluza, Bostjan; Komavec, Mojca; Varesanovic, Damir; Chouchane, Hanna; Antona-Makoshi, Jacobo
• Is Part Of: Traffic injury prevention. Volume 22:Number 5(2021)
• Page Start: 384
• Page End: 389
• Publication Date: 2021-06-09
• Subjects: Driving style score -- safe driving index -- safety index -- cautious driving -- preventive measures; Traffic safety -- Periodicals; Traffic accidents -- Periodicals; Wounds and injuries -- Prevention -- Periodicals; 363.125
• DOI: 10.1080/15389588.2021.1904508
• Languages: English
• ISSNs: 1538-9588

Abstract

Abstract: Objective: Road traffic laws explicitly refer to a safe and cautious driving style as a means of ensuring safety. For automated vehicles to adhere to these laws, objective measurements of safe and cautious behavior in normal driving conditions are required. This paper describes the conception, implementation and initial testing of an objective scoring system that assigns safety indexes to observed driving style, and aggregates them to provide an overall safety score for a given driving session. Methods: The safety score was developed by matching safety indexes with maneuver-based parameter ranges processed from an existing highway traffic data set with a newly developed algorithm. The concept stands on the idea that safety, rather than suddenly changing from a safe to an unsafe condition at a certain parameter value, can be better modeled as a continuum of values that consider the safety margins available for interactions among multiple vehicles and that depend on present traffic conditions. A sensitivity test of the developed safety score was conducted by comparing the results of applying the algorithm to two drivers in a simulator who were instructed to drive normally and risky, respectively. Results: The evaluation of normal driving statistics provided suitable ranges for safety parameters like vehicle distances, time headways, and time to collision based on real traffic data. The sensitivity test provided preliminary evidence that the scoring method can discriminate between safe and risky drivers based on their driving style. In contrast to previous approaches, collision situations are not needed for this assessment. Conclusions: The developed safety score shows potential for assessing the level of safety of automated vehicle (AV) behavior in traffic, including AV ability to avoid exposure to collision-prone situations. Occasional bad scores may occur even for good drivers or autonomously driving vehicles. However, if the safety index becomes low during a significant part of a driving session, due to frequent or harsh safety margin violations, the corresponding driving style should not be accepted for driving in real traffic.