Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

GAZELOAD A Multimodal Eye-Tracking Dataset for Mental Workload in Industrial Human-Robot Collaboration

Bsher Karbouj, Baha Eddin Gaaloul, Jorg Kruger

TL;DR

GAZELOAD provides an open, domain-specific multimodal eye-tracking dataset for mental workload estimation in industrial human–robot collaboration. It synchronizes ocular metrics from Meta ARIA glasses with environmental illumination and rich task/robot context across three workload levels and induced faults, using 250 ms aggregation windows to enable real-time MWL analysis. The dataset is organized for cross-modal alignment (eye metrics, lux, and event logs) and released under CC BY 4.0 with accompanying processing scripts, supporting benchmarking of MWL estimation, feature extraction, and temporal modeling in realistic HRC settings. This resource facilitates exploration of environmental factors, such as lighting, on eye-based workload markers and promotes reproducible research in industrial automation contexts.

Abstract

This article describes GAZELOAD, a multimodal dataset for mental workload estimation in industrial human-robot collaboration. The data were collected in a laboratory assembly testbed where 26 participants interacted with two collaborative robots (UR5 and Franka Emika Panda) while wearing Meta ARIA smart glasses. The dataset time-synchronizes eye-tracking signals (pupil diameter, fixations, saccades, eye gaze, gaze transition entropy, fixation dispersion index) with environmental real-time and continuous measurements (illuminance) and task and robot context (bench, task block, induced faults), under controlled manipulations of task difficulty and ambient conditions. For each participant and workload-graded task block, we provide CSV files with ocular metrics aggregated into 250 ms windows, environmental logs, and self-reported mental workload ratings on a 1-10 Likert scale, organized in participant-specific folders alongside documentation. These data can be used to develop and benchmark algorithms for mental workload estimation, feature extraction, and temporal modeling in realistic industrial HRC scenarios, and to investigate the influence of environmental factors such as lighting on eye-based workload markers.

GAZELOAD A Multimodal Eye-Tracking Dataset for Mental Workload in Industrial Human-Robot Collaboration

TL;DR

GAZELOAD provides an open, domain-specific multimodal eye-tracking dataset for mental workload estimation in industrial human–robot collaboration. It synchronizes ocular metrics from Meta ARIA glasses with environmental illumination and rich task/robot context across three workload levels and induced faults, using 250 ms aggregation windows to enable real-time MWL analysis. The dataset is organized for cross-modal alignment (eye metrics, lux, and event logs) and released under CC BY 4.0 with accompanying processing scripts, supporting benchmarking of MWL estimation, feature extraction, and temporal modeling in realistic HRC settings. This resource facilitates exploration of environmental factors, such as lighting, on eye-based workload markers and promotes reproducible research in industrial automation contexts.

Abstract

This article describes GAZELOAD, a multimodal dataset for mental workload estimation in industrial human-robot collaboration. The data were collected in a laboratory assembly testbed where 26 participants interacted with two collaborative robots (UR5 and Franka Emika Panda) while wearing Meta ARIA smart glasses. The dataset time-synchronizes eye-tracking signals (pupil diameter, fixations, saccades, eye gaze, gaze transition entropy, fixation dispersion index) with environmental real-time and continuous measurements (illuminance) and task and robot context (bench, task block, induced faults), under controlled manipulations of task difficulty and ambient conditions. For each participant and workload-graded task block, we provide CSV files with ocular metrics aggregated into 250 ms windows, environmental logs, and self-reported mental workload ratings on a 1-10 Likert scale, organized in participant-specific folders alongside documentation. These data can be used to develop and benchmark algorithms for mental workload estimation, feature extraction, and temporal modeling in realistic industrial HRC scenarios, and to investigate the influence of environmental factors such as lighting on eye-based workload markers.
Paper Structure (10 sections, 3 figures, 1 table)

This paper contains 10 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Data Collection
  4. Experimental Setup
  5. participant
  6. Experimental Tasks
  7. Dataset
  8. Data availability & Licensing
  9. Ethics & Anonymization
  10. Limitations

Figures (3)

  • Figure 1: Experimental setup: participant wearing ARIA smart glasses interacting with the UR5 robot (left); Franka Emika Panda station with assembly parts (right)
  • Figure 2: Example summaries from the dataset: (left) self-reported MWL (1–10) per task block T1–T5 aggregated across participant; (right) saccade count per 250 ms window per task block.
  • Figure 3: Preprocessing pipeline for deriving eye-tracking metrics from raw ARIA smart-glasses recordings.