Your Interface, Your Control: Adapting Takeover Requests for Seamless Handover in Semi-Autonomous Vehicles
URL: http://arxiv.org/abs/2506.01836v1
archive: archived pipeline: cataloged verified
Abstract
With the automotive industry transitioning towards conditionally automated driving, takeover warning systems are crucial for ensuring safe collaborative driving between users and semi-automated vehicles. However, previous work has focused on static warning systems that do not accommodate different driver states. Therefore, we propose an adaptive takeover warning system that is personalised to drivers, enhancing their experience and safety. We conducted two user studies investigating semi-autonomous driving scenarios in rural and urban environments while participants performed non-driving-related tasks such as text entry and visual search. We investigated the effects of varying time budgets and head-up versus head-down displays for takeover requests on drivers' situational awareness and mental state. Through our statistical and clustering analyses, we propose strategies for designing adaptable takeover systems, e.g., using longer time budgets and head-up displays for non-hazardous takeover events in high-complexity environments while using shorter time budgets and head-down displays for hazardous events in low-complexity environments.
Summary
Two simulator user studies on adaptive takeover-request (TOR) design for SAE L3 semi-automated driving. Participants drove rural and urban scenarios while performing non-driving tasks (text entry, visual search). Study 1 (Display Type) compared head-up vs head-down TOR displays; Study 2 (Time Budget) varied lead time before a hazardous obstacle. Statistical and clustering analyses produced design recommendations for personalised, context-adaptive TOR strategies.
Key finding
Optimal takeover-warning design depends jointly on environment complexity and event hazard: longer time budgets and head-up displays suit non-hazardous events in high-complexity environments, while shorter time budgets with head-down displays better serve hazardous events in low-complexity environments.
Methodology
Two-study driving-simulator experiment with rural and urban scenarios and concurrent non-driving tasks (text entry, visual search). Study 1 manipulated display type (head-up vs head-down); Study 2 manipulated time-budget length, with TOR fixed at 7 s before collision in the Display Type Study. Outcome measures included reaction time, gaze behaviour, manoeuvre quality, situational awareness, and self-reported mental state. Clustering analysis used to derive driver-state-conditioned design rules.
Sample size: Two simulator studies; specific N per study not extracted
Quality score: 5 / 5