Citation

Török. IEEE Trans. Intel. Transp. Syst. 2023; 24(1): 718-727.

Copyright

(Copyright © 2023, IEEE (Institute of Electrical and Electronics Engineers))

DOI

10.1109/TITS.2022.3212280

PMID

unavailable

Abstract

In the future, the role of the human factor in the driving processes is expected to decrease continuously. At the same time, based on the global trends, the role of computer-supported decision systems and artificial intelligence (AI)-based control solutions increases in relation to driving processes, which carries a significant safety-enhancing potential. To assess the possible social benefits of automated vehicle systems objectively, it is necessary to analyze the possible negative effects in detail as well. Accordingly, the aim of this article is to present a statistical survey of crashes involving automated vehicles today in order to identify and evaluate the factors that are relevant in the crashes. The analyzed data showed that when the autopilot mode was turned off and the human driver made the control decisions, the severity of crashes on straight roads was greater at $\alpha \,\,=0.1$ significance level than when the vehicle was in autopilot mode and the vehicle system made the control decisions. In addition, if the $\alpha $ significance level is 0.2, then crashes on plain terrain, during the day, or in the speed range of 80-100 km/h are generally less serious for vehicles driven in autopilot mode than for vehicles with autopilot mode turned off. In light of the considerations above, it is also important to emphasize that this paper only investigates crash severity given occurrence but not the probability of occurrence itself.

Language: en

Keywords

Accidents; Automated vehicles; Autopilot; collision causes of highly automated vehicles; crash severity of highly automated vehicles; Databases; Human factors; Reliability; risk factors; Safety; statistical data analysis; Vehicles