On the forces of driver distraction: Explainable predictions for the visual demand of in-vehicle touchscreen interactions

With modern infotainment systems, drivers are increasingly tempted to engage in secondary tasks while driving. Since distracted driving is already one of the main causes of fatal accidents, in-vehicle touchscreens must be as little distracting as possible. To ensure that these systems are safe to use, they undergo elaborate and expensive empirical testing, requiring fully functional prototypes. Thus, early-stage methods informing designers about the implication their design may have on driver distraction are of great value. This paper presents a machine learning method that, based on anticipated usage scenarios, predicts the visual demand of in-vehicle touchscreen interactions and provides local and global explanations of the factors influencing drivers' visual attention allocation. The approach is based on large-scale natural driving data continuously collected from production line vehicles and employs the SHapley Additive exPlanation (SHAP) method to provide explanations leveraging informed design decisions. Our approach is more accurate than related work and identifies interactions during which long glances occur with 68% accuracy and predicts the total glance duration with a mean error of 2.4s. Our explanations replicate the results of various recent studies and provide fast and easily accessible insights into the effect of UI elements, driving automation, and vehicle speed on driver distraction. The system can not only help designers to evaluate current designs but also help them to better anticipate and understand the implications their design decisions might have on future designs.

Exploring drivers' mental workload and visual demand while using an in-vehicle HMI for eco-safe driving

Eco-safe driving is a promising approach to improve road safety while reducing transport emissions. The application of an eco-safe driving system is feasible with the support of vehicle-to-vehicle/infrastructure technologies. To guarantee system usability and safety appropriateness, a key precondition is to ensure that driver mental workload and visual demands required for using the system are reasonable. This study explored how drivers' mental workload and visual demands were affected when driving with an eco-safe driving HMI (human-machine-interface). Four in-vehicle eco-safe HMI information conditions were evaluated, including baseline, advice only, feedback only, and advice & feedback. Two traffic scenarios (stop-sign intersection with traffic vs. stop-sign intersection without traffic) were simulated using an advanced driving simulator. Behavioural variables (e.g. brake force, acceleration), visual variables (e.g. blink metrics, pupil size) and subjective workload scores were collected from 36 licensed Australian drivers. The experiment results showed that the HMI prompted drivers to apply a smooth and stable brake force when they approached the intersection and a smooth acceleration when they left the intersection. Drivers' mental workload indicated by visual measurements were consistent with their subjective reported workload levels. Drivers had a higher mental workload when they received and processed additional eco-safe information in the advice & feedback condition. An increase in mental workload induced by the in-vehicle cognitive task initiated more blink activities while the increase in visual demand caused by a complex road situation led to blink inhibition. The study shows the HMI could significantly promote eco-safe driving behaivours without causing excessive mental and visual workload of drivers.

Feel the noise: Mid-air ultrasound haptics as a novel human-vehicle interaction paradigm

Focussed ultrasound can be used to create the sensation of touch in mid-air. Combined with gestures, this can provide haptic feedback to guide users, thereby overcoming the lack of agency associated with pure gestural interfaces, and reducing the need for vision - it is therefore particularly apropos of the driving domain. In a counter-balanced 2 × 2 driving simulator study, a traditional in-vehicle touchscreen was compared with a virtual mid-air gestural interface, both with and without ultrasound haptics. Forty-eight experienced drivers (28 male, 20 female) undertook representative in-vehicle tasks - discrete target selections and continuous slider-bar manipulations - whilst driving. Results show that haptifying gestures with ultrasound was particularly effective in reducing visual demand (number of long glances and mean off-road glance time), and increasing performance (shortest interaction times, highest number of correct responses and least 'overshoots') associated with continuous tasks. In contrast, for discrete, target-selections, the touchscreen enabled the highest accuracy and quickest responses, particularly when combined with haptic feedback to guide interactions, although this also increased visual demand. Subjectively, the gesture interfaces invited higher ratings of arousal compared to the more familiar touch-surface technology, and participants indicated the lowest levels of workload (highest performance, lowest frustration) associated with the gesture-haptics interface. In addition, gestures were preferred by participants for continuous tasks. The study shows practical utility and clear potential for the use of haptified gestures in the automotive domain.

Evaluating secondary input devices to support an automotive touchscreen HMI: A cross-cultural simulator study conducted in the UK and China

Touchscreen Human-Machine Interfaces (HMIs) are a well-established and popular choice to provide the primary control interface between driver and vehicle, yet inherently demand some visual attention. Employing a secondary device with the touchscreen may reduce the demand but there is some debate about which device is most suitable, with current manufacturers favouring different solutions and applying these internationally. We present an empirical driving simulator study, conducted in the UK and China, in which 48 participants undertook typical in-vehicle tasks utilising either a touchscreen, rotary-controller, steering-wheel-controls or touchpad. In both the UK and China, the touchscreen was the most preferred/least demanding to use, and the touchpad least preferred/most demanding, whereas the rotary-controller was generally favoured by UK drivers and steering-wheel-controls were more popular in China. Chinese drivers were more excited by the novelty of the technology, and spent more time attending to the devices while driving, leading to an increase in off-road glance time and a corresponding detriment to vehicle control. Even so, Chinese drivers rated devices as easier-to-use while driving, and felt that they interfered less with their driving performance, compared to their UK counterparts. Results suggest that the most effective solution (to maximise performance/acceptance, while minimising visual demand) is to maintain the touchscreen as the primary control interface (e.g. for top-level tasks), and supplement this with a secondary device that is only enabled for certain actions; moreover, different devices may be employed in different cultural markets. Further work is required to explore these recommendations in greater depth (e.g. during extended or real-world testing), and to validate the findings and approach in other cultural contexts.

Assessing the visual and cognitive demands of in-vehicle information systems

BACKGROUND

New automobiles provide a variety of features that allow motorists to perform a plethora of secondary tasks unrelated to the primary task of driving. Despite their ubiquity, surprisingly little is known about how these complex multimodal in-vehicle information systems (IVIS) interactions impact a driver's workload.

RESULTS

The current research sought to address three interrelated questions concerning this knowledge gap: (1) Are some task types more impairing than others? (2) Are some modes of interaction more distracting than others? (3) Are IVIS interactions easier to perform in some vehicles than others? Depending on the availability of the IVIS features in each vehicle, our testing involved an assessment of up to four task types (audio entertainment, calling and dialing, text messaging, and navigation) and up to three modes of interaction (e.g., center stack, auditory vocal, and the center console). The data collected from each participant provided a measure of cognitive demand, a measure of visual/manual demand, a subjective workload measure, and a measure of the time it took to complete the different tasks. The research provides empirical evidence that the workload experienced by drivers systematically varied as a function of the different tasks, modes of interaction, and vehicles that we evaluated.

CONCLUSIONS

This objective assessment suggests that many of these IVIS features are too distracting to be enabled while the vehicle is in motion. Greater consideration should be given to what interactions should be available to the driver when the vehicle is in motion rather than to what IVIS features and functions could be available to motorists.