Towards Context-Aware Modeling of Situation Awareness in Conditionally Automated Driving

TL;DR

This paper presents a real-time, multimodal data-driven model to assess driver situation awareness in conditionally automated vehicles, enhancing safety during takeover events.

Contribution

It introduces a predictive model using multimodal physiological and behavioral data, trained with LightGBM and SHAP for improved SA assessment in automated driving.

Findings

Achieved RMSE=0.89, MAE=0.71, and correlation=0.78 in SA prediction.

Identified top predictors for driver SA using SHAP analysis.

Demonstrated the model's potential for safer driver-AV interactions.

Abstract

Maintaining adequate situation awareness (SA) is crucial for the safe operation of conditionally automated vehicles (AVs), which requires drivers to regain control during takeover (TOR) events. This study developed a predictive model for real-time assessment of driver SA using multimodal data (e.g., galvanic skin response, heart rate and eye tracking data, and driver characteristics) collected in a simulated driving environment. Sixty-seven participants experienced automated driving scenarios with TORs, with conditions varying in risk perception and the presence of automation errors. A LightGBM (Light Gradient Boosting Machine) model trained on the top 12 predictors identified by SHAP (SHapley Additive exPlanations) achieved promising performance with RMSE=0.89, MAE=0.71, and Corr=0.78. These findings have implications towards context-aware modeling of SA in conditionally automated driving, paving the way for safer and more seamless driver-AV interactions.