Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

Measuring and Managing Mind Wandering in Automated Vehicles

Project description

Tackling mind-wandering in automated vehicles

Autonomous cars can help reduce accidents caused by risky driver behaviours, but they can also introduce a new risk. When the car takes care of the driving, the driver is likely to stop paying attention to the road. This may elicit mind-wandering, reflecting a lapse in situation awareness that can delay critical responses and increase accidents. Supported by the Marie Sklodowska-Curie Actions programme, the MindWandAV project is investigating the relationship between trust, risk perception and mind-wandering in automated driving. High-fidelity simulators and real-world road tests will be used to model driver states through physiological markers such as eye-tracking and heart rate. The findings will pave the way for safer human-automation collaboration.

Objective

Automated vehicles (AVs) are expected to reduce accidents and congestion by mitigating human error and enabling more efficient use of travel time. However, at SAE Level 2—where the system manages both steering and speed while drivers are still required to monitor the environment—a challenge emerges: drivers must remain vigilant without continuous control, which increases the risk of disengagement. A central factor in this challenge is mind-wandering (MW), defined in the driving context as a shift of attention away from processing task-relevant information (e.g. road conditions, vehicle control) toward internally generated, task-unrelated thoughts. Intentional MW may arise from overtrust in automation, while underload induced by automation facilitates disengagement more generally. Both forms undermine situational awareness and delay responses, thereby threatening safety. Despite its importance, the relationship between MW, trust, and perceived risk in automated driving remains largely unexplored.
This project addresses this gap through three objectives. O1 will operationalize and computationally model MW in high-fidelity simulators, integrating subjective ratings, behavioral metrics, physiological indices (eye tracking, electrocardiography), and driving performance, to distinguish intentional and unintentional MW. O2 will validate simulator-derived models in naturalistic on-road studies with commercial and experimental vehicles, testing how contextual variability modulates MW and its links to trust calibration and risk perception. O3 will design and evaluate adaptive human–machine interfaces (HMIs) that dynamically mitigate MW by integrating Driver State Monitoring (DSM) informed by predictive models from O1–O2, using multimodal feedback and user-centered design methods. By combining cognitive psychology, human factors, mechanical engineering, and computational modeling, the project advances theoretical accounts of attentional states in automated driving.

Fields of science (EuroSciVoc)

Keywords

Programme(s)

Topic(s)

Funding Scheme

HORIZON-TMA-MSCA-PF-EF - HORIZON TMA MSCA Postdoctoral Fellowships - European Fellowships

See all projects funded under this funding scheme

Call for proposal

(opens in new window) HORIZON-MSCA-2025-PF

See all projects funded under this call

Coordinator

TECHNISCHE UNIVERSITEIT DELFT
Net EU contribution
€ 217 076,16
Total cost
No data