manD 1.0, short for "human dimension in automated driving," is a comprehensive multimodal dataset designed for benchmarking driver monitoring systems in automated driving contexts. It encompasses data from diverse driver monitoring sensors, collected from 50 participants (split evenly between females and males, ages 21 to 65) engaging in five different driving scenarios within a static simulator in a lab setting. The dataset spans a variety of automation levels, from manual to conditional automation, and includes environmental conditions, vehicle specifics, and detailed driver states like physiological measures, movements, gaze, and facial expressions, all synchronized. manD 1.0 facilitates research into driver behavior modeling, prediction of reactions, interaction strategy development, and motion sickness studies.
 

Dataset:

Dargahi Nobari, Khazar and Bertram, Torsten. (2023). ‘manD 1.0’. Available at: doi.org/10.7910/DVN/SG9TMD.

Experimental design and explanations:

Dargahi Nobari, K., T. Bertram: “A multimodal driver monitoring benchmark dataset for driver modeling in assisted driving automation,” Scientific Data, vol. 11, no. 1, Mar. 2024, doi: 10.1038/s41597-024-03137-y.