Detecting Drunk Driving Using Off-the-Shelf Smartwatches

2026-05-22

AI Summary

This study addresses the challenge of detecting alcohol-impaired driving, a behavior often unrecognized by drivers themselves and a leading cause of preventable traffic accidents. The authors propose a method leveraging commercially available smartwatches to capture physiological signals—specifically wrist acceleration and heart rate variability—and employ both logistic regression and a dual-tower one-dimensional convolutional neural network (CNN) for classification. Notably, this work presents the first real-vehicle implementation of alcohol impairment detection using consumer-grade wearable devices and demonstrates the model’s generalization capability to unseen users through closed-course validation. Experimental results show that the proposed CNN achieves average AUROC scores of 0.88 and 0.86 in detecting any alcohol consumption and blood alcohol concentration exceeding the legal limit of 0.05 g/dL, respectively.

Abstract

Alcohol-impaired driving remains a major yet preventable cause of road traffic injury and death, with many drivers underestimating their level of intoxication. Compared to in-vehicle systems, mobile drunk-driving detection using consumer smartwatches offers a scalable way to trigger preventive interventions and increase awareness without additional in-vehicle hardware. We introduce a system that leverages wrist accelerometer data and heart rate variability-derived physiological signals to detect alcohol-related driving impairment. We collected data in a randomized, controlled three-arm test-track study (n=54) and trained both logistic regression models with window-aggregated features and a two-tower 1D convolutional neural network (CNN), to detect alcohol-impaired driving. The CNN achieved a participant-averaged area under the receiver operating characteristic (AUROC) of 0.88 for detecting any alcohol intoxication and 0.86 for detecting driving above the WHO-recommended limit of 0.05 g/dL. To the best of our knowledge, this is the first work to (1) demonstrate drunk-driving detection using consumer smartwatches, (2) develop and evaluate such a system in a real vehicle on a closed test track, and (3) rigorously assess generalization to unseen participants. Together, these findings highlight the potential of wearable-based sensing to support scalable, measurement-driven prevention of alcohol-related traffic harm.

Problem

• drunk driving detection
• smartwatches
• alcohol impairment
• wearable sensing
• traffic safety

Innovation

• smartwatch-based detection
• alcohol-impaired driving
• heart rate variability
• 1D CNN
• generalization to unseen participants