Vigilance Decrement During On-Road Partially Automated Driving Across Four Systems

Abstract

Objective This study uses a detection task to measure changes in driver vigilance when operating four different partially automated systems. Background Research show temporal declines in detection task performance during manual and fully automated driving, but the accuracy of using this approach for measuring changes in driver vigilance during on-road partially automated driving is yet unproven. Method Participants drove four different vehicles (Tesla Model 3, Cadillac CT6, Volvo XC90, and Nissan Rogue) equipped with level-2 systems in manual and partially automated modes. Response times to a detection task were recorded over eight consecutive time periods. Results Bayesian analysis revealed a main effect of time period and an interaction between mode and time period. A main effect of vehicle and a time period x vehicle interaction were also found. Conclusion Results indicated that the reduction in detection task performance over time was worse during partially automated driving. Vehicle-specific analysis also revealed that detection task performance changed across vehicles, with slowest response time found for the Volvo. Application The greater decline in detection performance found in automated mode suggests that operating level-2 systems incurred in a greater vigilance decrement, a phenomenon that is of interest for Human Factors practitioners and regulators. We also argue that the observed vehicle-related differences are attributable to the unique design of their in-vehicle interfaces.