| 1. |
- Tivesten, Emma, 1968, et al.
(författare)
-
Out-of-the-loop crash prediction: The Automation Expectation Mismatch (AEM) algorithm
- 2019
-
Ingår i: IET Intelligent Transport Systems. - : Institution of Engineering and Technology (IET). - 1751-9578 .- 1751-956X. ; 13:8, s. 1231-1240
-
Tidskriftsartikel (refereegranskat)abstract
- This study uses behavioural data from the complete drive for a subset of 54 participants from the automation expectation mismatch set of test track experiments and aims to develop an algorithm that can predict which drivers are likely to crash. Participants experienced 30 min of highly reliable supervised automation and were required to intervene to avoid crashing with a stationary object at the end of the drive. Many of them still crashed, despite having their eyes on the conflict object. They were informed about their role as supervisors, automation limitations, and received attention reminders if visually distracted. Three pre-conflict behavioural patterns were found to be associated with increased risk of crash involvement: low levels of visual attention to the forward path, high per cent road centre (i.e. gaze concentration), and long visual response times to attention reminders. One algorithm showed very high performance in classifying crashers when combining metrics related to all three behaviours. This algorithm is possible to implement as a real-time function in eye-tracker equipped vehicles. The algorithm can detect drivers that are not sufficiently engaged in the driving task, and provide feedback (e.g. reduce function performance, turn off function) to increase their engagement.
|
|
| 2. |
- Tivesten, Emma, 1968, et al.
(författare)
-
The timecourse of driver visual attention in naturalistic driving with Adaptive Cruise Control and Forward Collision Warning
- 2015
-
Ingår i: International Conference on Driver Distraction and Inattention, 4th, 2015, Sydney, New South Wales, Australia.
-
Konferensbidrag (refereegranskat)abstract
- Adaptive Cruise Control (ACC) and Forward Collision Warning (FCW) have been shown to have a positive effect on safety-related measures despite a general increase in secondary task involvement. To understand this effect, this study examined the relationship between drivers glance locations and ACC hard braking or FCW events when ACC is active. The study analyzed naturalistic driving on motorways where the car remained in the same lane. Four subsets of driving segments were included: ACC braking (peak deceleration ≥ 3 m/s2), FCW+ACC (driving with ACC when a forward collision warning was issued) ACC maintaining speed, and Driver braking without ACC or FCW. The results indicate that although drivers do take their eyes off path more when using ACC, this conclusion seems to be valid only in non-critical (baseline-similar) situations. Drivers showed a steady increase in %EyesOnPath well before critical situations, resulting in 95% EyesOnPath both at the onset of ACC braking and at the onset of driver braking, and 98% when FCW were issued. At braking onset, headway was significantly longer when ACC braked compared to when the driver braked.
|
|
| 3. |
- Victor, Trent, 1968, et al.
(författare)
-
Automation Expectation Mismatch: Incorrect Prediction Despite Eyes on Threat and Hands on Wheel
- 2018
-
Ingår i: Human Factors. - : SAGE Publications. - 1547-8181 .- 0018-7208. ; 60:8, s. 1095-1116
-
Tidskriftsartikel (refereegranskat)abstract
- Objective: The aim of this study was to understand how to secure driver supervision engagement and conflict intervention performance while using highly reliable (but not perfect) automation. Background: Securing driver engagement—by mitigating irony of automation (i.e., the better the automation, the less attention drivers will pay to traffic and the system, and the less capable they will be to resume control) and by communicating system limitations to avoid mental model misconceptions—is a major challenge in the human factors literature. Method: One hundred six drivers participated in three test-track experiments in which we studied driver intervention response to conflicts after driving highly reliable but supervised automation. After 30 min, a conflict occurred wherein the lead vehicle cut out of lane to reveal a conflict object in the form of either a stationary car or a garbage bag. Results: Supervision reminders effectively maintained drivers’ eyes on path and hands on wheel. However, neither these reminders nor explicit instructions on system limitations and supervision responsibilities prevented 28% (21/76) of drivers from crashing with their eyes on the conflict object (car or bag). Conclusion: The results uncover the important role of expectation mismatches, showing that a key component of driver engagement is cognitive (understanding the need for action), rather than purely visual (looking at the threat), or having hands on wheel. Application: Automation needs to be designed either so that it does not rely on the driver or so that the driver unmistakably understands that it is an assistance system that needs an active driver to lead and share control.
|
|
| 4. |
- Bärgman, Jonas, 1972, et al.
(författare)
-
How does glance behavior influence crash and injury risk? A ‘what-if’ counterfactual simulation using crashes and near-crashes from SHRP2
- 2015
-
Ingår i: Transportation Research Part F: Traffic Psychology and Behaviour. - : Elsevier BV. - 1369-8478. ; 35, s. 152-169
-
Tidskriftsartikel (refereegranskat)abstract
- As naturalistic driving data become increasingly available, new analyses are revealing the significance of drivers’ glance behavior in traffic crashes. Due to the rarity of crashes, even in the largest naturalistic datasets, near-crashes are often included in the analyses and used as surrogates for crashes. However, to date we lack a method to assess the extent to which driver glance behavior influences crash and injury risk across both crashes and near-crashes. This paper presents a novel method for estimating crash and injury risk from off-road glance behavior for crashes and near-crashes alike; this method can also be used to evaluate the safety impact of secondary tasks (such as tuning the radio). We apply a ‘what-if’ (counterfactual) simulation to 37 lead-vehicle crashes and 186 lead-vehicle near-crashes from lead-vehicle scenarios identified in the SHRP2 naturalistic driving data. The simulation combines the kinematics of the two conflicting vehicles with a model of driver glance behavior to estimate two probabilities: (1) that each event becomes a crash, and (2) that each event causes a specific level of injury. The usefulness of the method is demonstrated by comparing the crash and injury risk of normal driving with the risks of driving while performing one of three secondary tasks: the Rockwell radio-tuning task and two hypothetical tasks. Alternative applications of the method and its metrics are also discussed. The method presented in this paper can guide the design of safer driver–vehicle interfaces by showing the best tradeoff between the percent of glances that are on-road, the distribution of off-road glances, and the total task time for different tasks.
|
|
| 5. |
- Engström, Johan A Skifs, 1973, et al.
(författare)
-
Great expectations: A predictive processing account of automobile driving
- 2018
-
Ingår i: Theoretical Issues in Ergonomics Science. - 1464-536X .- 1463-922X. ; 19:2, s. 156-194
-
Tidskriftsartikel (refereegranskat)abstract
- Predictive processing has been proposed as a unifying framework for understanding brain function, suggesting that cognition and behaviour can be fundamentally understood based on the single principle of prediction error minimisation. According to predictive processing, the brain is a statistical organ that continuously attempts get a grip on states in the world by predicting how these states cause sensory input and minimising the deviations between the predicted and actual input. While these ideas have had a strong influence in neuroscience and cognitive science, they have so far not been adopted in applied human factors research. The present paper represents a first attempt to do so, exploring how predictive processing concepts can be used to understand automobile driving. It is shown how a framework based on predictive processing may provide a novel perspective on a range of driving phenomena and offer a unifying framework for traditionally disparate human factors models.
|
|
| 6. |
- Fridman, L., et al.
(författare)
-
"Owl' and "Lizard': patterns of head pose and eye pose in driver gaze classification
- 2016
-
Ingår i: IET Computer Vision. - : Institution of Engineering and Technology (IET). - 1751-9640 .- 1751-9632. ; 10:4, s. 308-314
-
Tidskriftsartikel (refereegranskat)abstract
- Accurate, robust, inexpensive gaze tracking in the car can help keep a driver safe by facilitating the more effective study of how to improve (i) vehicle interfaces and (ii) the design of future advanced driver assistance systems. In this study, the authors estimate head pose and eye pose from monocular video using methods developed extensively in prior work and ask two new interesting questions. First, how much better can they classify driver gaze using head and eye pose versus just using head pose? Second, are there individual-specific gaze strategies that strongly correlate with how much gaze classification improves with the addition of eye pose information? The authors answer these questions by evaluating data drawn from an on-road study of 40 drivers. The main insight of the study is conveyed through the analogy of an owl' and lizard' which describes the degree to which the eyes and the head move when shifting gaze. When the head moves a lot (owl'), not much classification improvement is attained by estimating eye pose on top of head pose. On the other hand, when the head stays still and only the eyes move (lizard'), classification accuracy increases significantly from adding in eye pose. The authors characterise how that accuracy varies between people, gaze strategies, and gaze regions.
|
|
| 7. |
- Jakobsson, Lotta, 1967, et al.
(författare)
-
Rear-End impact-Crash prevention and occupant protection
- 2015
-
Ingår i: 2015 IRCOBI Conference Proceedings - International Research Council on the Biomechanics of Injury. ; , s. 803-813
-
Konferensbidrag (refereegranskat)abstract
- This study presents the enhancements of knowledge as well as countermeasures addressing crash prevention and occupant protection in rear-end impact situations. It includes the second-generation Whiplash Protection System (WHIPS) together with occupant pre-positioning by tightening the electrical reversible safety belts, acceleration reduction by applying the brakes when the car is at a standstill and rearward flashing lights triggered by sensors identifying a potential rear-end impact. Significant steps towards whiplash injury reduction through rear-end impact crash prevention and occupant protection are taken by integrating pre-crash sensing and crash performance to address real-world safety needs. The pre-crash sensing information, with safety belt tightening, addresses some of the main high-risk situations in rear-end impacts, such as extensive head to head-restraint distance. By adjusting the occupants to sit closer to the seat at time of impact, the full benefit of the seat protection can be achieved. The WHIPS has been further improved by focusing energy absorption together with even and close support, and by addressing small and large occupants, both male and female, thus adding to overall occupant protection potential. Through the use of pre-crash sensing, opponent warning system and a braking functionality, additional injury reductions can be achieved and some crashes avoided altogether. Further studies are needed to quantify these effects.
|
|
| 8. |
- Lee, Joonbum, et al.
(författare)
-
Investigating the correspondence between driver head position and glance location
- 2018
-
Ingår i: PeerJ Computer Science. - : PeerJ. - 2376-5992.
-
Tidskriftsartikel (refereegranskat)abstract
- The relationship between a driver's glance orientation and corresponding head rotation is highly complex due to its nonlinear dependence on the individual, task, and driving context. This paper presents expanded analytic detail and findings from an effort that explored the ability of head pose to serve as an estimator for driver gaze by connecting head rotation data with manually coded gaze region data using both a statistical analysis approach and a predictive (i.e., machine learning) approach. For the latter, classification accuracy increased as visual angles between two glance locations increased. In other words, the greater the shift in gaze, the higher the accuracy of classification. This is an intuitive but important concept that we make explicit through our analysis. The highest accuracy achieved was 83% using the method of Hidden Markov Models (HMM) for the binary gaze classification problem of (a) glances to the forward roadway versus (b) glances to the center stack. Results suggest that although there are individual differences in head-glance correspondence while driving, classifier models based on head-rotation data may be robust to these differences and therefore can serve as reasonable estimators for glance location. The results suggest that driver head pose can be used as a surrogate for eye gaze in several key conditions including the identification of high-eccentricity glances. Inexpensive driver head pose tracking may be a key element in detection systems developed to mitigate driver distraction and inattention.
|
|
| 9. |
- Markkula, Gustav M, 1978, et al.
(författare)
-
A farewell to brake reaction times? Kinematics-dependent brake response in naturalistic rear-end emergencies
- 2016
-
Ingår i: Accident Analysis and Prevention. - : Elsevier BV. - 0001-4575. ; 95, s. 209-226
-
Tidskriftsartikel (refereegranskat)abstract
- Driver braking behavior was analyzed using time-series recordings from naturalistic rear-end conflicts (116 crashes and 241 near-crashes), including events with and without visual distraction among drivers of cars, heavy trucks, and buses. A simple piecewise linear model could be successfully fitted, per event, to the observed driver decelerations, allowing a detailed elucidation of when drivers initiated braking and how they controlled it. Most notably, it was found that, across vehicle types, driver braking behavior was strongly dependent on the urgency of the given rear-end scenario's kinematics, quantified in terms of visual looming of the lead vehicle on the driver's retina. In contrast with previous suggestions of brake reaction times (BRTs) of 1.5 s or more after onset of an unexpected hazard (e.g., brake light onset), it was found here that braking could be described as typically starting less than a second after the kinematic urgency reached certain threshold levels, with even faster reactions at higher urgencies. The rate at which drivers then increased their deceleration (towards a maximum) was also highly dependent on urgency. Probability distributions are provided that quantitatively capture these various patterns of kinematics-dependent behavioral response. Possible underlying mechanisms are suggested, including looming response thresholds and neural evidence accumulation. These accounts argue that a naturalistic braking response should not be thought of as a slow reaction to some single, researcher-defined "hazard onset", but instead as a relatively fast response to the visual looming cues that build up later on in the evolving traffic scenario.
|
|
| 10. |
- Morando, Alberto, 1988, et al.
(författare)
-
A Reference Model for Driver Attention in Automation: Glance Behavior Changes During Lateral and Longitudinal Assistance
- 2019
-
Ingår i: IEEE Transactions on Intelligent Transportation Systems. - 1524-9050 .- 1558-0016. ; 20:8, s. 2999-3009
-
Tidskriftsartikel (refereegranskat)abstract
- This paper introduces a reference model of glance behavior for driving safety assessment. This model can improve the design of automated and assistive systems. Technological limitations have previously hindered the use of unobtrusive eye trackers to measure glance behavior in naturalistic conditions. This paper presents a comprehensive analysis of eye-tracking data collected in a naturalistic field operation test, using an eye tracker that proved to be robust in real-world driving scenarios. We describe a post-processing technique to enhance the quality of naturalistic eye-tracker data, propose a data-analysis procedure that captures the important features of glance behavior, and develop a model of glance behavior (based on distribution fitting), which was lacking in the literature. The model and its metrics capture key defining characteristics of, and differences between, on- and off-path glance distributions, and during manual driving and driving with adaptive cruise control and lane keeping aid active. The results show that drivers' visual response is tightly coupled to the driving context (vehicle automation, car-following, and illumination).
|
|
