HADRIAN-LAS: A multimodal psychological, physiological, and behavioral dataset for Low Arousal and Sleepiness [LAS] states detection in long monotonous driving simulated tasks

Version 2 2024-03-23, 10:55
Version 1 2024-03-23, 10:25
Posted on 2024-03-23 - 10:55 authored by Leandro L. Di Stasi
The HADRIAN-LAS dataset consists of a wide range of neurobehavioral data collected during an approximately 180-min long monotonous simulated driving. We aimed to build a multimodal psychological, physiological, and behavioral dataset to track low arousal and sleepiness (LAS) states while driving. To do so, we carried out a 2x2 within-subjects experiment with time-on-driving (2 levels: TOD1 [0-90 min], TOD2 [91-180 min]) and driving modality (2 levels: manual [MD] vs. automated [AD] driving) as the main factors. During the whole driving simulation, we implemented a multimodal data collection system – that included remote and wearable sensors – to monitor drivers’ states. We recorded physiological (i.e., eye movements, facial temperature, electrodermal and electrocardiogram activity, blood volume pulse, and respiration rate), behavioral (i.e., vehicle-based data and mannerisms), as well as subjective (i.e., driving style, chronotype, sleepiness, and fatigue) data. Twenty-one professional drivers (mean ± standard deviation [SD]; age = 44.43 ± 7.26 years; body mass index = 26.29 ± 3.62 kg/m2; driving experience [Spanish type B driving license] = 26.00 ± 7.70 years; annual car driving mileage = 47,251.90 ± 43,832.82 km/year; 20 men) underwent an early-morning, 180 min-long, simulated driving session. Participants drove a semi-dynamic (four-degree-of-freedom motion platform) driving simulator (Nervtech™, Ljubljana, Slovenia) that recreates a middle-sized electric automatic car. It is also equipped with autopilot and full self-driving capability features. The driving session consisted of two 90-min blocks of either MD or AD. After the first 90 minutes, without resting, the driving modality changed from MD to AD or vice-versa (the order was counterbalanced across participants). During AD, the drivers were asked to supervise the automation system. At the end of the second 90-min block, a final take-over signal was presented, and drivers engaged into a 5-min driving/supervising (depending on initial driving modality) period under adverse meteorological conditions. The overall dataset comprises 77 video (.MP4 and .AVI) and 132 .CSV files, for an amount of 277 GB. For each file, we adopted a consistent file naming (i.e., ID_Number_“type of recorded data”). A customized Matlab code (Mathworks Inc., Natick, MA, USA) was used to synchronize the overall data set. We used two external triggers to mark the beginning of the driving session (i.e., data acquisition): a handheld trigger switch (PLUX Wireless Biosignals, Lisbon, Portugal) and the simulator blinker lever. Before starting the driving session, we asked participants to pull the lever down (with their left hand) while simultaneously pushing the button trigger switch (with their right hand making the gesture clearly visible on cameras). Both digital markers were sent to the simulator. For quality control, flexibility and synchronization, data presented in all directories – except for the “Subjective ratings” directory – were divided into thirty-nine chunks. Therefore each .CSV file contains an extra column called chunks (i.e., first column). The column chunks includes the following labels: “Start” (delay time before the driving session started, up to 25 seconds for synchronization purposes); Chunk-1 to Chunk-36 (thirty-six 5-min of driving, 180 minutes of session); “Adverse Meteorological Event” (last 5-min driving); “End” (extra time once the driving session finished).


3 Biotech
3D Printing in Medicine
3D Research
3D-Printed Materials and Systems
AAPG Bulletin
AAPS PharmSciTech
Abhandlungen aus dem Mathematischen Seminar der Universität Hamburg
ABI Technik (German)
Academic Medicine
Academic Pediatrics
Academic Psychiatry
Academic Questions
Academy of Management Discoveries
Academy of Management Journal
Academy of Management Learning and Education
Academy of Management Perspectives
Academy of Management Proceedings
Academy of Management Review
Select your citation style and then place your mouse over the citation text to select it.


The Neuroergonomics & Operator Performance Laboratory has been funded by the HADRIAN (Holistic Approach for Driver Role Integration and Automation Allocation for European Mobility Needs) project. HADRIAN has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 875597. This document reflects only the authors' view. The European Climate, Infrastructure and Environment Executive Agency (CINEA) is not responsible for any use that may be made of the information it contains.

Research Institution(s)

Neuroergonomics and Operator Performance Lab - University of Granada

Contact email



Usage metrics



Francesco Angioi
Marcelo A. Costa Fernandes
María Jesús Caurcel-Cara
Christophe Prat
Jaka Sodnik
Carolina Diaz-Piedra
need help?