Analyzing driver gaze behavior and consistency of decision making during automated driving

Miyajima, Chiyomi; Yamazaki, Suguru; Bando, Takashi; Hitomi, Kentarou; Terai, Hitoshi; Okuda, Hiroyuki; Hirayama, Takatsugu; Egawa, Masumi; Suzuki, Tatsuya

doi:10.1109/ivs.2015.7225894

Cited by 16 publications

(7 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It appears that the lack of a need for vehicle control during this automation condition reduces the probability of drivers' gaze back to the road center, after attending to other AoIs. These results are in line with that of others who have shown a more dispersed gaze during automation, compared to when manual control is in place (Miyajima et al, 2015;Louw & Merat, 2017).…”

Section: Resultssupporting

confidence: 92%

“…To our knowledge, this, and other research in the lane-change context (e.g. Miyajima at al., 2015), have only analyzed mean gaze fixations to different areas of interest, and drivers' average horizontal and vertical gaze dispersion. However, we argue that there is value in understanding how, and when, drivers shift their attention across the different information sources, to understand what information is used during the decision-making process required for a lane-change maneuver (Mourant & Rockwell, 1971;Underwood, Chapman, Brockelhurst, Underwood, & Crundall 2003).…”

Section: Introductionmentioning

confidence: 50%

“…The results of this study also support our previous findings (Gonçalves et al, submitted), that by removing physical control and decision-making responsibility from drivers, automation reduces drivers' propensity to efficiently scan the environment and look for information that might be relevant for task execution. Therefore, removal of manual vehicle control may cause drivers to be more reliant on good system performance and suitable HMI, which, if absent, makes them less capable of responding to automation failures (Parasuraman & Riley, 1997;Miyajima et al, 2015). This induced reliance on timely and suitable information reinforces the fact that poorly designed automated systems and related interfaces may bring with them additional and unforeseen risks to the road environment, reinforcing the ironies of automation (Bainbridge, 1981).…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Using Markov Chains to Understand the Sequence of Drivers' Gaze Transitions During Lane-Changes in Automated Driving

Gonçalves

Louw

Madigan

et al. 2019

Proceedings of the 10th International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design: Dri

View full text Add to dashboard Cite

This paper reports the results of a driving simulator study, which analyzed differences in drivers' raw gaze transition patterns during different stages of a lane-change maneuver, measured during manual, partially and conditionally automated driving. To understand whether the different levels of automation affected behaviour, and particularly how visual attention was distributed during a lane-change maneuver, a Markov chains approach was used to compare gaze transitions between the different information sources available in the surrounding road and cockpit environment, for each of the three drives. Results showed that drivers initiated fewer safety-related inspections (for example to the wing mirrors) during partial automation, throughout the whole lane change maneuver, possibly because they were focusing on how to the transition of control from automation. Drivers in this condition also had a higher probability of checking the system's HMI, to verify the automation's status. In contrast, during conditional automation, the lack of a need for vehicle control by the driver resulted in more gaze transitions between information sources, and fewer gazes to locations where a potential hazard could be present, when compared to manual. Finally, drivers generally only deviated their gaze towards information related to aspects of vehicle control they were responsible for, which we conclude could make them susceptible to missing hazards during both routine and safety-critical takeovers .

show abstract

Section: Resultssupporting

confidence: 92%

Section: Introductionmentioning

confidence: 50%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Using Markov Chains to Understand the Sequence of Drivers' Gaze Transitions During Lane-Changes in Automated Driving

Gonçalves

Louw

Madigan

et al. 2019

Proceedings of the 10th International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design: Dri

View full text Add to dashboard Cite

show abstract

“…The amount of visual attention allocated to the road during automated driving is known to be a predictor of driver performance when regaining manual control (Miyajima et al, 2015). Thus, our second hypothesis was that drivers who glance at the road more often would also be able to perform better when the automation fails unexpectedly.…”

Section: Discussionmentioning

confidence: 99%

The Effects of Continuous Driving-Related Feedback on Drivers’ Response to Automation Failures

Cohen-Lazry

Borowsky

Oron-Gilad

2017

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

During prolonged periods of autonomous driving, drivers tend to shift their attention away from the driving task. As a result, they require more time to regain awareness of the driving situation and to react to it. This study examined the use of informative automation that during Level-3 autonomous driving provided drivers with continuous feedback regarding the vehicle’s actions and surroundings. It was hypothesized that the operation of informative automation will trigger drivers to allocate more attention to the driving task and will improve their reaction times when resuming control of the vehicle. Sixteen participants drove manual and autonomous driving segments in a driving simulator equipped with Level-3 automation. For half of the participants, the informative automation issued alerts and messages while for the other half no messages were issued (control). The number of on-road glances served as a proxy for drivers’ attention. Drivers’ performance on handling an unexpected automation failure event was measured using their time-to-brake and time-to-steer. Results showed that drivers using the informative automation made more frequent on-road glances than drivers in the control group. Yet, there were no significant differences in reaction times to the automation failure event between the groups. Explanations and implications of these results are discussed.

show abstract

“…The quality of this prediction depended essentially on gaze dynamics, although the optimal prediction was achieved by examining a combination of static and dynamic characteristics. This study helps to pave the way for developing algorithms to estimate the driver's state in an autonomous vehicle based on oculometric data (Gonçalves et al, 2019;Miyajima et al, 2015). Driver monitoring is a challenge in the development of new generations of these vehicles as it may be essential to assess whether the driver is in the loop or out of it, in terms of vehicle control and environmental supervision (Louw & Merat, 2017).…”

Section: Discussionmentioning

confidence: 99%

Model-based estimation of the state of vehicle automation as derived from the driver’s spontaneous visual strategies

Schnebelen¹,

Charron²,

Mars³

2021

JEMR

View full text Add to dashboard Cite

When manually steering a car, the driver’s visual perception of the driving scene and his or her motor actions to control the vehicle are closely linked. Since motor behaviour is no longer required in an automated vehicle, the sampling of the visual scene is affected. Autonomous driving typically results in less gaze being directed towards the road centre and a broader exploration of the driving scene, compared to manual driving. To examine the corollary of this situation, this study estimated the state of automation (manual or automated) on the basis of gaze behaviour. To do so, models based on partial least square regressions were computed by considering the gaze behaviour in multiple ways, using static indicators (percentage of time spent gazing at 13 areas of interests), dynamic indicators (transition matrices between areas) or both together. Analysis of the quality of predictions for the different models showed that the best result was obtained by considering both static and dynamic indicators. However, gaze dynamics played the most important role in distinguishing between manual and automated driving. This study may be relevant to the issue of driver monitoring in autonomous vehicles.

show abstract

Analyzing driver gaze behavior and consistency of decision making during automated driving

Cited by 16 publications

References 3 publications

Using Markov Chains to Understand the Sequence of Drivers' Gaze Transitions During Lane-Changes in Automated Driving

Using Markov Chains to Understand the Sequence of Drivers' Gaze Transitions During Lane-Changes in Automated Driving

The Effects of Continuous Driving-Related Feedback on Drivers’ Response to Automation Failures

Model-based estimation of the state of vehicle automation as derived from the driver’s spontaneous visual strategies

Contact Info

Product

Resources

About