Quantifying Virtual Control Tower Decision Making using Visual Discrimination of Aircraft Maneuvers
Bibliographic record
Abstract
The new Virtual and Remote Control Tower paradigm (RTO) [1] requires verification of technical parameters and extensive validation of the performance with simulation and field experiments. Of central importance for tower controllers are visual cues obtained from the out-of-windows view [2] which is replaced by a high resolution video panorama with pan-tilt zoom function. Here we present results of a remote tower simulation and analysis of dual choice decision errors obtained with 13 domain experts who had to observe and predict the outcome of aircraft landing under different braking conditions. High deceleration leads to stop on the runway whereas low deceleration results in runway overshoot. Bayes inference, discriminability, and subjective decision bias, derived from the response matrix data (hit rate H (correct prediction of stop stimulus), misses, correct rejections and false alarm rate FA (false “stop” prediction of no-stop stimulus) are used for deriving video frame rate requirements for minimizing decision errors [3]. Results are presented in ROC space (receiver operating characteristic) displaying (H, FA)-data together with isosensitivity (d’ or nonparametric A) and isobias curves according to detection theory. Preliminary data analysis of decision error-decrease with increasing framerate FR (6 – 24 Hz) is based based on the hypothesis of an exponentially decaying visual short term memory with sample and hold delay. Exponential and linear approximations and extrapolations of the d’ (or A) vs. FR data indicate a minimum FR-requirement of at least 35 Hz. The result is confirmed with Bayes inference and is supported by shooter game experiments [4]. These methods are presently used also for quantifying RTO performance and usability under field testing conditions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".