A Simulator Dataset to Support the Study of Impaired Driving

John Gideon; Kimimasa Tamura; Emily Sumner; Laporsha Dees; Patricio Reyes Gomez; Bassamul Haq; Todd Rowell; Avinash Balachandran; Simon Stent; Guy Rosman · 2025 · arXiv

DOI: arXiv:2507.02867

URL: http://arxiv.org/abs/2507.02867v1

archive: archived pipeline: cataloged verified

Abstract

Despite recent advances in automated driving technology, impaired driving continues to incur a high cost to society. In this paper, we present a driving dataset designed to support the study of two common forms of driver impairment: alcohol intoxication and cognitive distraction. Our dataset spans 23.7 hours of simulated urban driving, with 52 human subjects under normal and impaired conditions, and includes both vehicle data (ground truth perception, vehicle pose, controls) and driver-facing data (gaze, audio, surveys). It supports analysis of changes in driver behavior due to alcohol intoxication (0.10\% blood alcohol content), two forms of cognitive distraction (audio n-back and sentence parsing tasks), and combinations thereof, as well as responses to a set of eight controlled road hazards, such as vehicle cut-ins. The dataset will be made available at https://toyotaresearchinstitute.github.io/IDD/.

Summary

Toyota Research Institute technical report (arXiv 2507.02867) introducing the Impaired Driving Dataset (IDD): a public driving simulator dataset spanning ~25 hours of urban driving with 52 human subjects under normal and impaired conditions. The dataset captures vehicle data (ground-truth perception, vehicle pose, controls) and driver-facing data (gaze, audio, surveys), covering alcohol intoxication (target 0.10% BAC), two cognitive-distraction tasks (audio n-back and sentence parsing), their combinations, and responses to eight controlled road hazards such as vehicle cut-ins. The authors demonstrate that fixations and saccades decrease under both impairment states and argue that joint modeling of impairment types improves detection.

Key finding

Releases the first publicly available driving-simulator dataset combining alcohol intoxication and cognitive distraction with controlled hazard responses, and shows that gaze-based features (fixation/saccade rates) decline under both impairment types with additive effects when impairments co-occur.

Methodology

Driving-simulator study (52 participants across two cohorts: v1 TRI employees who underwent the intoxication protocol; v2 externally recruited via User Interviews). Five-component protocol: gaze calibration, pre-driving visuomotor tasks, driving practice, cognitive-distraction task practice, and driving with hazards. Conditions include baseline, alcohol intoxication (0.10% BAC), audio n-back, sentence parsing, and combinations. Eight controlled hazard scenarios (e.g., vehicle cut-ins) were embedded. WCG IRB approved (Protocol #20241945).

Sample size: N=52 (v1 + v2 cohorts); ~25 hours of simulated urban driving

Quality score: 5 / 5

Topics