How to keep drivers engaged while supervising driving automation? A literature survey and categorisation of six solution areas

Abstract

This work aimed to organise recommendations for keeping people engaged during human supervision of driving automation, encouraging a safe and acceptable introduction of automated driving systems. First, heuristic knowledge of human factors, ergonomics, and psychological theory was used to propose solution areas to human supervisory control problems of sustained attention. Driving and non-driving research examples were drawn to substantiate the solution areas. Automotive manufacturers might (1) avoid this supervisory role altogether, (2) reduce it in objective ways or (3) alter its subjective experiences, (4) utilize conditioning learning principles such as with gamification and/or selection/ training techniques, (5) support internal driver cognitive processes and mental models and/or (6) leverage externally situated information regarding relations between the driver, the driving task, and the driving environment. Second, a cross-domain literature survey of influential human-automation interaction research was conducted for how to keep engagement/attention in supervisory control. The solution areas (via numeric theme codes) were found to be reliably applied from independent rater categorisations of research recommendations. Areas (5) and (6) were addressed by around 70% or more of the studies, areas (2) and (4) in around 50% of the studies, and areas (3) and (1) in less than around 20% and 5%, respectively. The present contribution offers a guiding organisational framework towards improving human attention while supervising driving automation. Relevance to human factors/Relevance to ergonomics theory A good amount of human factors research has already previously been devoted to examining human vigilance in supervising automated process (both by experimental investigation and literature review synthesis). However, given recent advances and accidents with humans ARTICLE HISTORY

Addressing Driver Disengagement and Proper System Use: Human Factors Recommendations for Level 2 Driving Automation Design

“…Numerous proactive strategies have been recommended to keep drivers engaged by increasing situational awareness of present traffic conditions and staying in loop in the physical task of driving, while also minimizing in-vehicle opportunities for distraction. However, some strategies that have been suggested are unrealistic for modern production vehicles and real-world driving conditions, such as imposing secondary tasks through gamification to maintain cognitive arousal (Cabrall et al, 2019), which could add unsafe cognitive burden in certain situations, or using adaptive automation that tailors system functionality to individual driver characteristics, such as experience or age (Saffarian et al, 2012), which goes beyond current in-vehicle driver recognition software capabilities and also introduces privacy concerns for operators.…”

“…Our paper does not make recommendations about vehicle interface characteristics, which is thoroughly covered in the guidance from the National Highway Traffic Safety Administration (Campbell et al, 2018; National Highway Traffic Safety Administration [NHTSA], 2017), except for where it applies to strategies for managing a driver’s attention to the driving task. Other important papers have made human factors recommendations on the design and implementation of Level 2 driving automation (e.g., Banks et al, 2018; Cabrall et al, 2019; Consumer Reports, 2018; Endsley, 2017a, 2017b, 2018; Eriksson & Stanton, 2017; Seppelt & Victor, 2016); however, they were more theoretical than concrete, covered some but not all of our areas of interest, and/or made recommendations without citing empirical data. This paper seeks to build upon that body of work and is organized as follows.…”

Drivers use active gaze to monitor waypoints during automated driving

“…In order to be useful for controlling a driver’s trajectory, guiding fixations need to support reliable estimates of self-motion 17 , 69 . Additionally, estimating the motion of the vehicle with respect to the environment is a core function of the monitoring task during automation, since executing the appropriate steering commands upon manual takeover (and detecting any automation errors) requires an accurate estimate of the current vehicle motion 8 , 70 , 71 . Estimating the vehicle’s trajectory, therefore, could be the task that is producing similar gaze behaviours across both driving modes.…”

Dynamic scan paths investigations under manual and highly automated driving

“…The currently available highest form of automation, referred as Highly Automated Driving (HAD), is able to manage both lateral and longitudinal control of the vehicle see 38 for a review. However, in case of automation malfunction, or driving situations automation is not able to handle, take-over requests are required 39 , 40 . Here, dynamic scan paths analysis was carried out to refine the understanding of the impact of HAD on visual exploration.…”