Objective: A driving simulator study was conducted to evaluate the longitudinal effects of an intervention and withdrawal of a lane keeping system on driving performance and cognitive workload. Background: Autonomous vehicle systems are being implemented into the vehicle fleet. However, limited research exists in understanding the carryover effects of long-term exposure. Methods: Forty-eight participants (30 treatment, 18 control) completed eight drives across three separate days in a driving simulator. The treatment group had an intervention and withdrawal of a lane keeping system. Changes in driving performance (standard deviation of lateral position [SDLP] and mean time to collision [TTC]) and cognitive workload (response time and miss rate to a detection response task) were modeled using mixed effects linear and negative binomial regression. Results: Drivers exposed to the lane keeping system had an increase in SDLP after the system was withdrawn relative to their baseline. Drivers with lane keeping had decreased mean TTC during and after system withdrawal compared with manual drivers. There was an increase in cognitive workload when the lane keeping system was withdrawn relative to when the system was engaged. Conclusion: Behavioral adaptations in driving performance and cognitive workload were present during automation and persisted after the automation was withdrawn. Application: The findings of this research emphasize the importance to consider the effects of skill atrophy and misplaced trust due to semi-autonomous vehicle systems. Designers and policymakers can utilize this for system alerts and training.

A Hidden Markov Model framework is introduced to formalize the beliefs that humans may have about the mode in which a semi-automated vehicle is operating. Previous research has identified various "levels of automation," which serve to clarify the different degrees of a vehicle's automation capabilities and expected operator involvement. However, a vehicle that is designed to perform at a certain level of automation can actually operate across different modes of automation within its designated level, and its operational mode might also change over time. Confusion can arise when the user fails to understand the mode of automation that is in operation at any given time, and this potential for confusion is not captured in models that simply identify levels of automation. In contrast, the Hidden Markov Model framework provides a systematic and formal specification of mode confusion due to incorrect user beliefs. The framework aligns with theory and practice in various interdisciplinary approaches to the field of vehicle automation. Therefore, it contributes to the principled design and evaluation of automated systems and future transportation systems.

No abstract

No abstract

No abstract