ITSC 2025 Paper Abstract

Paper WE-EA-T14.6

Göbel, Jan-Philipp (CARIAD SE, Johannes Kepler University (JKU), Technische Hochschu), Mertens, Jan Cedric (CARIAD SE), Kundinger, Thomas (AUDI AG), Riener, Andreas (Technische Hochschule Ingolstadt)

Multimodal Detection of Alcohol-Impaired Driving Using Time-Series Classification in a High-Fidelity Simulator

Scheduled for presentation during the Regular Session "S14b-Human Factors and Human Machine Interaction in Automated Driving" (WE-EA-T14), Wednesday, November 19, 2025, 14:50−15:30, Currumbin

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 19, 2025

Keywords Human-Machine Interaction Systems for Enhanced Driver Assistance and Safety, Driver Behavior Monitoring and Feedback Systems for Semi-autonomous Vehicles

Abstract

This study introduces a novel machine learning framework for detecting alcohol-induced driving impairment based on multimodal behavioral signals collected in a high-fidelity driving simulator. With 120 participants—the largest sample size in this field to date—the experiment captured both vehicle dynamics and eye-tracking data under sober and intoxicated conditions. To preserve temporal dependencies, a MiniRocket time-series classifier was employed, outperforming conventional feature-based models. A systematic signal-wise analysis identified steering behavior and drowsiness as the most informative indicators. Signal combinations further enhanced classification performance, achieving up to 85.2 % accuracy on unseen test data. While scenario-specific models (urban, rural, highway) provided only marginal improvements, a time window analysis revealed that just three minutes of driving data were sufficient for reliable detection. As the first study to integrate gaze and driving behavior in a scalable, signal-based approach, this work demonstrates the practical potential of multimodal time-series classification for real-time, in-vehicle driver monitoring.