Decoding Driver Takeover Behaviour in Conditional Automation with Immersive Virtual Reality
URL: http://arxiv.org/abs/2402.16046v1
archive: archived pipeline: cataloged verified
Abstract
The safe transition from conditional automation to manual driving control is significantly intertwined with the vehicle's lateral and longitudinal dynamics. The transition may occur as a result of a system-initiated mandatory takeover (MTOR) or as a driver-initiated discretionary takeover (DTOR). In either condition, the takeover process entails differing cognitive demands and may affect the driving behaviour differently. This study analyzes driving stability and perceived mental workload in 304 takeover attempts recorded from 104 participants within virtual and immersive reality environments. Adopting an exploratory approach, this dynamic simulator study employs a mixed factorial design. Utilizing a deep neural network-based survival analysis with SHAP interpretability, the study investigated the influence of covariates on perception-reaction time (PRT), distinguishing between safe and unsafe control transition and offering insights into the temporal dynamics of these shifts. The distributions of key parameters in experimental groups were analyzed and factors influencing the perceived mental workload were estimated using multivariate linear regression. The findings indicate a notable decrease in the risk of unsafe takeovers (described by a longer PRT) when drivers have prior control-transition experience and familiarity with Automated Vehicles (AVs). However, driver's prior familiarity and experience with AVs only decreased the perceived mental workload associated with DTOR, with an insignificant impact on the cognitive demand of MTOR. Furthermore, multitasking during automated driving significantly elevated the cognitive demand linked to DTOR and led to longer PRT in MTOR situations.
Summary
Ansar and Farooq analyzed 304 takeover attempts from 104 participants in an immersive VR driving simulator to compare mandatory (system-initiated, MTOR) and discretionary (driver-initiated, DTOR) control transitions in conditional automation. They used a deep-neural-network survival model with SHAP interpretability to estimate covariate effects on perception-reaction time (PRT) and a multivariate linear regression for perceived mental workload. Prior AV familiarity and takeover experience reduced unsafe-takeover risk and lowered DTOR workload but did not affect MTOR workload; multitasking during automation increased DTOR cognitive demand and lengthened MTOR PRTs. The authors argue DTOR has been understudied relative to MTOR despite distinct cognitive profiles.
Key finding
Driver-initiated (discretionary) takeovers carry different cognitive and reaction-time profiles than system-initiated mandatory takeovers, and prior AV experience reduces unsafe-takeover risk and DTOR workload but not MTOR workload.
Methodology
Mixed factorial driving-simulator study using virtual immersive reality and digital twins, with 104 participants completing 304 takeover events split between mandatory (MTOR) and discretionary (DTOR) conditions. Deep neural network survival analysis with SHAP interpretability modeled perception-reaction time as a function of kinematic, stability, perceptual, attitudinal, demographic, and environmental covariates; multivariate linear regression estimated perceived mental workload.
Sample size: N=104 participants, 304 takeover attempts
Quality score: 5 / 5