Adaptive Automation Triggered by EEG-Based Mental Workload Index: A Passive Brain-Computer Interface Application in Realistic Air Traffic Control Environment
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This study addresses the challenge of maintaining optimal operator performance in high-stakes environments by implementing Adaptive Automation (AA) triggered by real-time mental workload assessment. The authors argue that static automation often leads to operator underload or overload, degrading safety and performance. To solve this, they developed a passive Brain-Computer Interface (pBCI) system that uses electroencephalogram (EEG) signals to detect mental workload levels and dynamically adjust automation support in a realistic Air Traffic Control (ATC) environment. The primary goal was to demonstrate that EEG-based indices could reliably trigger AA solutions to reduce workload during high-demand periods while preventing automation during low-demand periods to avoid underload. The experiment involved twelve Air Traffic Controller students at the École Nationale de l’Aviation Civile in Toulouse, France. Participants performed ATC scenarios in a high-fidelity simulator under two conditions: one where AA was triggered by an online EEG-based workload index (AA On) and a control condition where the index was computed but not used to trigger automation (AA Off). EEG signals were recorded from nine scalp electrodes and processed using a StepWise Linear Discriminant Analysis (SWLDA) algorithm, calibrated on individual frontal theta and parietal alpha band features. The AA system implemented four specific interventions: filtering non-critical alerts, highlighting calling stations, modifying collision avoidance alert graphics, and reducing visual clutter by hiding non-relevant aircraft. These interventions were activated only when the EEG-derived workload index exceeded a threshold established during a calibration phase. The results demonstrated the effectiveness of the pBCI system in triggering AA primarily during high-demand conditions. The system successfully reduced the mental workload experienced by the controllers during overload situations. Conversely, the AA solutions were not activated when workload levels remained below the threshold, thereby preventing potentially dangerous underload conditions. Subjective assessments using the NASA-TLX questionnaire confirmed that the adaptive support helped maintain workload within appropriate limits. The study validates the feasibility of using continuous, non-invasive neurophysiological monitoring to drive adaptive automation in complex operational settings. The significance of this work lies in its demonstration of a closed-loop human-machine interaction system in a realistic, high-fidelity environment, moving beyond previous laboratory-based studies. By successfully integrating EEG-based mental workload estimation with dynamic automation adjustments, the study provides evidence that pBCI technologies can enhance safety and performance in critical domains like aviation. This approach offers a robust method for mitigating both overload and underload, preserving operator situational awareness and skill levels while optimizing task allocation between human and machine.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-08-09 |
| archive | success | canonical_url | — | — | 1 | 2026-08-09 |
| extract | success | cached | — | — | 3 | 2026-08-10 |
| clean | success | clean | — | — | 1 | 2026-08-09 |
| chunk | success | chunk | — | — | 1 | 2026-08-09 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-08-09 |
| promote | success | — | — | — | 1 | 2026-08-09 |
| summarize | success | llm | qwen3.6-27b-nvidia | summ-v5 | 2 | 2026-08-10 |
| tag | success | vector_similarity | — | — | 11 | 2026-08-11 |
| verify | success | — | — | — | 2 | 2026-08-10 |
Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: physiological data, self report data