Your Interface, Your Control: Adapting Takeover Requests for Seamless Handover in Semi-Autonomous Vehicles

2025-06-02

AI Summary

Static takeover warning systems in semi-autonomous driving struggle to balance safety and user experience. Method: This study proposes a personalized, dual-dimension adaptive takeover warning mechanism that jointly considers driver state and driving context. We introduce a novel two-dimensional dynamic decision model integrating environmental complexity and event criticality, validated through eye-tracking, subjective ratings, and multi-task load experiments across rural and urban scenarios. K-means clustering uncovers systematic mappings between driver states and HUD/HDD display modalities. The framework enables real-time co-optimization of takeover time budget and display modality. Results: Optimal configurations include long time budgets with HUD for high-complexity, low-criticality scenarios, and short time budgets with HDD for low-complexity, high-criticality scenarios. The approach significantly enhances situation awareness (+27%) and takeover readiness (p < 0.01), establishing a new paradigm for dynamic human-factor adaptation in human–machine shared driving.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements

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.

Problem

• Adapting takeover requests for personalized driver safety
• Investigating display types and time budgets for situational awareness
• Designing adaptable takeover systems for varying driving environments

Innovation

• Adaptive takeover warning system for drivers
• Personalized strategies based on driver state
• Dynamic time budgets and display types