Aurora Flight Sciences, under contract to the Federal Railroad Administration (FRA), studied the feasibility of autonomously monitoring and combating train engineer fatigue. This program is called Monitoring Engineer Fatigue (MEFA). Research and testing at the FRA's Cab Technology Integration Laboratory confirmed that identifying fatigue through physiological cues through a variety of detection sensors is plausible. RGBD (color + depth) cameras were used to detect facial features for key points of interest - mainly eye and mouth movements. Researchers parsed an activity within the general code of operating rules (GCOR) into a logical step-by-step procedure, which could then be presented to Aurora's procedure execution module. The biggest area for improvement is the method by which fatigued engineers are analyzed. Researchers recommend future work include an analysis of engineers who are actively fatigued. Relying instead on actors would increase the risk of developing a brittle algorithm.
In the future, operators of complex equipment will spend more time monitoring computer controlled devices rather than having hands on control of such ...
Links with this icon indicate that you are leaving a Bureau of Transportation
Statistics (BTS)/National Transportation Library (NTL)
Web-based service.
Thank you for visiting.
You are about to access a non-government link outside of
the U.S. Department of Transportation's National
Transportation Library.
Please note: While links to Web sites outside of DOT are
offered for your convenience, when you exit DOT Web sites,
Federal privacy policy and Section 508 of the Rehabilitation
Act (accessibility requirements) no longer apply. In
addition, DOT does not attest to the accuracy, relevance,
timeliness or completeness of information provided by linked
sites. Linking to a Web site does not constitute an
endorsement by DOT of the sponsors of the site or the
products presented on the site. For more information, please
view DOT's Web site linking policy.
To get back to the page you were previously viewing, click
your Cancel button.