The Neuroergonomics of Aircraft Cockpits: The Four Stages of Eye-Tracking Integration to Enhance Flight Safety

Abstract

Abstract:Commercial aviation is currently one of the safest modes of transportation; however, human error is still one major contributing cause of aeronautical accidents and incidents. One promising avenue to further enhance flight safety is Neuroergonomics, an approach at the intersection of neuroscience, cognitive engineering and human factors, which aims to create better human-system interaction. Eye-tracking technology allows users to "monitor the monitoring" by providing insights into both pilots' attentional distribution and underlying decisional processes. In this position paper, we identify and define a framework of four stages of step-by-step integration of eye-tracking systems in modern cockpits. Stage I concerns Pilot Training and Flight Performance Analysis on-ground; stage II proposes On-board Gaze Recordings as extra data for the "black box" recorders; stage III describes Gaze-Based Flight Deck Adaptation including warning and alerting systems, and, eventually, stage IV prophesies Gaze-Based Aircraft Adaptation including authority taking by the aircraft. We illustrate the potential of these four steps with a description of incidents or accidents that we could certainly have avoided thanks to eye-tracking. Estimated milestones for the integration of each stage are also proposed together with a list of some implementation limitations. We believe that the research institutions and industrial actors of the domain will all benefit from the integration of the framework of the eye-tracking systems into cockpits.

A Neuroergonomics Approach to Mental Workload, Engagement and Human Performance

“…A crucial step is to design cognitive countermeasures to prevent the occurrence of these phenomena. The formal framework that we proposed (see Table 1) paves the way to design neuro-adaptive technology for augmented cognition and enhanced human-machine teaming (Peysakhovich et al, 2018;Krol et al, 2019;Stamp et al, 2019). The implementation of such neuro-adaptive technology relies on a pipeline that consists of a signal acquisition step, a preprocessing step to improve the signal-to-noise ratio, a feature extraction step, a classification step to diagnose the current mental states, and lastly an adaptation step (Zander and Kothe, 2011;Roy and Frey, 2016).…”

Intelligent cockpit

“…A promising way to do so, the core of the current thesis project, is to integrate eye tracker on board in order to monitor pilots eye movements [Peysakhovich et al 2016]. These data can be further used to deduce the crew attentional state, the breakdown of which can be detected early and prevented [Dehais et al 2017[Dehais et al , 2015Lefrancois et al 2016;Liu et al 2016;Peysakhovich et al 2018].…”

The interplay of eye movements and attention in a continuous flight related task

“…Rather than assuming where and what they were paying attention to, by examining the recorded eye movements, they can have a clear read out of exactly where the pilot was attending at any one time. Peysakhovich et al (2018) claim that the technology already available today would be sufficient for capturing this information, but delays at a higher level have prevented this from happening so far. However, as suggested in Chapter 3, where one is visually fixating is not necessarily where they are paying attention to -i.e.…”

“…In a laboratory setting, this may be possible, however in a real cockpit, the eye tracker would need to be robust enough to deal with lots of changes in luminance, distance from eyes, etc. Further, public acceptance of this type of technology may also hinder its progress, and as such, it is proposed that it may be more than 20 years before this could be integrated into the cockpit (Peysakhovich et al, 2018).…”

“…• Despite being interesting, there is no inherent use for a majority of the results found in aviation unless it is applied into evidence-based training. Peysakhovich, Lefrançois, Dehais, and Causse (2018) suggest that eye tracking should already be incorporated into standard aviation training and propose different ways it could be used: debriefing, accident reports, as well as being integrated into actual aviation systems, and pilot training.…”