Investigation into Effects of System Design on Metro Drivers’ Safety-Related Performance: An Eye-Tracking Study

Abstract

This paper explores performance shaping factors associated with holistic design aspects of metro systems affecting driver's behaviour based on a case study using eye-tracking techniques. Train driving is a highly visual task where the physical environment provides key visual instructions. Eye-mind theories suggest that eye movements closely follow cognitive processes when it comes to interaction with the visual world. The data for this study have been collected in a representative urban rail system serving a metropolitan area with circa 1.2 million inhabitants during 20 in-service trials. Participating drivers were asked to wear an eye-tracker while driving a train as they would normally do. The study focuses on four areas of interest at four consecutive stations. The stations have similar characteristics but differ in terms of certain design elements which are mirrors, platforms, stopping position markers and positions of a running signal. Previous studies have demonstrated the importance of these elements to metro drivers. The paper assesses the usability of the system design elements through analysis of gaze fixations. Results suggest the importance of the positions of a mirror and a signal in relation to the cab, as well as the distance between a stopping point and a signal. Such factors as openness of stations, passenger loadings and informativeness of certain elements also demonstrated influence on drivers' performance. It was also found that drivers sometimes do not check a signal before departing a station, which is a significant concern. The paper discusses factors potentially propagating such behaviour.

Eye-Tracking Calibration to Control a Cobot

“…With the aim to create safer and more advanced cars, the combination of facial recognition and eye-tracking enables information on the driver's attention, alertness or concentration on the driving task, therefore enabling the creation of different warnings and notifications. Some examples can be found in [5][6][7][8][9]. In this area, in which there is an irrefutable link to pedestrians, this groups' mobility safety has also been put in the focus of the analysis [10,11].…”

Smart Tramway Systems for Smart Cities: A Deep Learning Application in ADAS Systems

“…According to [18,22] some of the most important hazards in tram traffic are: 1) Collision between trams, 2) Tram collision with other types of vehicles, cyclists or pedestrians, 3) Running into an obstacle on the tracks. In traditional tramway systems the train driver must scan the approaching physical environment for the presence of hazards, warnings and imposed speed limits [23]. In order to reduce such hazards are required several actions both from the transportation system (operators, train drivers, infrastructure management, etc.)…”

Use of Eye-Tracking to Control a Cobot Movement: Results Coming From the Application of Tobii Pro X2-30 to an Omron Tm5-700 Robot

“…So we can create warnings and notifications in driving. Some examples can be found in Carr and Grover [5], Vetturi et al [6], Rjabovs and Palacin [7], Khan and Lee [8], and Le et al [9]. Also the safe mobility of pedestrians has been analysed [10], [11].…”