Cognitive load estimation in VR flight simulator
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 estimating pilot cognitive load in virtual reality (VR) flight simulators, a critical requirement for evaluating next-generation adaptive pilot-vehicle interfaces. While traditional workload assessment relies on subjective questionnaires or performance metrics, these methods lack continuous monitoring capabilities or are task-specific. The authors propose a low-cost, modular VR simulator that integrates physiological sensing to quantify cognitive load objectively. The research aims to validate whether ocular and electroencephalogram (EEG) signals can accurately reflect perceived task difficulty during complex air-to-air combat scenarios. The experimental framework utilized a Unity-based VR simulator mimicking F-16 aerodynamics, controlled via a Thrustmaster HOTAS. Twelve Air Force test pilots participated in five distinct scenarios involving interactions with an AI-driven enemy aircraft. The AI agent employed three guidance strategies: constant velocity, augmented proportional navigation, and reinforcement learning, with some scenarios incorporating degraded radar latency to increase difficulty. Data acquisition involved an HTC Vive Pro Eye headset for eye-tracking (pupil diameter, gaze direction) and an Emotiv 32-channel EEG headset. The researchers developed specific algorithms to process this data: pupil dilation dynamics were analyzed using multi-resolution wavelet analysis to extract low-frequency variations; gaze fixation rates and nearest-neighbor indices measured visual scanning patterns; and EEG metrics included the Task Load Index (TLI), derived from frontal theta and parietal alpha power, and the Task Engagement Index (TEI), based on frontal beta, alpha, and theta bands. These physiological metrics were compared against standard pilot workload metrics derived from control input time histories, specifically duty cycle and control activity. The results demonstrated a strong association between the proposed physiological metrics and the pilots’ perceived task difficulty. The study found that low-frequency pupil diameter variations, fixation rates, and gaze distribution patterns correlated significantly with workload levels. Similarly, the EEG-based TLI and TEI provided reliable indicators of cognitive load and engagement across the different AI agent configurations. The physiological measures aligned with the baseline workload metrics derived from pilot control inputs, validating their effectiveness in distinguishing between varying levels of task complexity. The significance of this work lies in demonstrating that a low-cost, off-the-shelf VR setup combined with non-invasive physiological sensors can effectively estimate cognitive load in realistic flight simulation environments. By establishing that ocular and EEG parameters reliably track pilot workload, the study supports the use of such multimodal approaches for human-in-the-loop testing. This enables rapid prototyping and evaluation of new cockpit designs and automation systems without the high costs associated with full-motion hardware simulators, facilitating more efficient human factors engineering in aviation development.
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 | openalex | — | — | 5 | 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
- Methodological Resource: tool software, measurement protocol