Glance Location Research Articles

Exploratory Development of Algorithms for Determining Driver Attention Status.

Varying driver distraction algorithms were developed using vehicle kinematics and driver gaze data obtained from a camera-based driver monitoring system (DMS). Distracted driving characteristics can be difficult to accurately detect due to wide variation in driver behavior across driving environments. The growing availability of information about drivers and their involvement in the driving task increases the opportunity for accurately recognizing attention state. A baseline for driver distraction levels was developed using a video feed of 24 separate drivers in varying naturalistic driving conditions. This initial assessment was used to develop four buffer-based algorithms that aimed to determine a driver's real-time attentiveness, via a variety of metrics and combinations thereof. Of those tested, the optimal algorithm included ungrouped glance locations and speed. Notably, as an algorithm's performance of detecting very distracted drivers improved, its accuracy for correctly identifying attentive drivers decreased. At a minimum, drivers' gaze position and vehicle speed should be included when designing driver distraction algorithms to delineate between glance patterns observed at high and low speeds. Distraction algorithms should be designed with an understanding of their limitations, including instances in which they may fail to detect distracted drivers, or falsely notify attentive drivers. This research adds to the body of knowledge related to driver distraction and contributes to available methods to potentially address and reduce occurrences. Machine learning algorithms can build on the data elements discussed to increase distraction detection accuracy using robust artificial intelligence.

Evaluation of the Impact of Work Zone Traffic Control Devices on Change of Speed Using the SHRP 2 Naturalistic Driving Study

Speeding is a major concern in work zones and a major contributor to work zone crashes. Around 71.4% of fatal work zone crashes are speeding-related compared with 30% of fatal crashes overall. Addressing speeding in work zones is therefore critical to improving work zone safety. This study utilized data from the second Strategic Highway Research Program Naturalistic Driving Study to evaluate the impact of traffic control devices (TCDs) on reducing driver speed in work zones. Time series data assessed changes in speed for 380 drivers over 104 unique work zones on four- or multilane roadways. Speed change was measured for single-point TCDs encountered in the work zones (i.e., signing, changeable message signs [CMSs]), and estimated using a linear mixed-effect model. Results indicated speeds reduced by 4.0 mph for dynamic speed feedback signs (DSFSs), 2.3 mph for speed limit signs (both regular and work zone), 2.2 mph with trailer-mounted- and 1.2 mph for active overhead CMSs, 2.8 mph for arrow boards, and up to 2 mph for other static work zone sign types. Driver characteristics (i.e., age, gender, glance location, cell phone use) were included in initial models but were not statistically significant, probably because of sample size. For instance, simple statics indicated that drivers engaged in a cell phone task had a decrease of only 1 mph when encountering a DSFS whereas drivers not engaged in a cell phone task decreased speed by over 4 mph. However, only seven drivers were engaged in a cell phone task when encountering a DSFS—probably too small to detect statistical significance.

Driver impairment detection using decision tree based feature selection and classification

The driver's control authority plays a crucial role at commanding safely a vehicle that is the technical system. And the driver monitoring systems need to detect and identify whether the driver is impaired and able to percept and react possible hazards. In this paper, the driver's impairment detection system is presented. The procedure of fusing driving data constituted by a large set of vehicle sensors in addition to driver's eye glance location is elaborated. A batch data to train, validate and test the impairment detection system is constituted by co-existing 14 location information and 76 different sensors for trips that contain a crash or near crash instances. The procedure of aligning vehicle motion sensor data logged at fixed sampling rate with eye glance location information is presented by applying a sliding window approach. The window is slided when eye glance location is changed and mean of sensor values is used to present the batch data in this window. Each instance of the batch data is classified. A two stage detection algorithm is tested and evaluated. Each instance is classified as impair or non-impair using Extreme Gradient (xg) boosted trees and a voting mechanism for the instances is used to decide whether driver is impaired or not. The results illustrate the effectiveness of the impairment detection system.

Driver response and recovery following automation initiated disengagement in real-world hands-free driving

Objective Advanced driver assistance systems are increasingly available in consumer vehicles, making the study of drivers’ behavioral adaptation and the impact of automation beneficial for driving safety. Concerns over driver’s being out-of-the-loop, coupled with known limitations of automation, has led research to focus on time-critical, system-initiated disengagements. This study used real-world data to assess drivers’ response to, and recovery from, automation-initiated disengagements by quantifying changes in visual attention, vehicle control, and time to steady-state behaviors. Methods Fourteen drivers drove for one month each a Cadillac CT6 equipped with Super Cruise (SC), a partial automation system that, when engaged, enables hands-free driving. The vehicles were instrumented with data acquisition systems recording driving kinematics, automation use, GPS, and video. The dataset included 265 SC-initiated disengagements identified across 5,514 miles driven with SC. Results Linear quantile mixed-effects models of glance behavior indicated that following SC-initiated disengagement, the proportions of glances to the Road decreased (Q50Before=0.91, Q50After=0.69; Q85Before=1.0, Q85After=0.79), the proportions of glances to the Instrument Cluster increased (Q50Before=0.14, Q50After=0.25; Q85Before=0.34, Q85After=0.45), and mean glance duration to the Road decreased by 4.86 sec in Q85. Multinomial logistic regression mixed-models of glance distributions indicated that the number of transitions between glance locations following disengagement increased by 43% and that glances were distributed across fewer locations. When driving hands-free, take over time was significantly longer (2.4 sec) compared to when driving with at least one hand on the steering wheel (1.8 sec). Analysis of moment-to-moment distributional properties of visual attention and steering wheel control following disengagement indicated that on average it took drivers 6.1 sec to start the recovery of glance behavior to the Road and 1.5 sec for trend-stationary proportions of at least one hand on the steering wheel. Conclusions Automation-initiated disengagements triggered substantial changes in driver glance behavior including shorter on-road glances and frequent transitions between Road and Instrument Cluster glance locations. This information seeking behavior may capture drivers’ search for information related to the disengagement or the automation state and is likely shaped by the automation design. The study findings can inform the design of more effective driver-centric information displays for smoother transitions and faster recovery.

Design and evaluation of visual guiding facilities along urban road tunnel horizontal curves based on vision and speed perception

With continuous increase in the number and length of urban road tunnels, traffic safety in the road tunnels has attracted ever greater attention. In particular, driver’s sight distance and sight zone along urban tunnel curves are constrained, and potential safety hazards are prominent. Herein, from the perspectives of active guidance, using visual guiding facilities to enable drivers to accurately perceive the orientation of the tunnel curve alignment and to control the speed reasonably have become a key research point with theoretical significance and practical application value. In this study, four types of schemes for urban road tunnel horizontal curves were constructed and evaluated by simulation experiments. Scene a was a rare scene without any visual guiding facility in practice, ordinary Scene b was a common scene in an urban road tunnel, Scene c included chevron alignment signs (additional to Scene b), and Scene d included LED arches (additional to Scene b). Glance location occupancy, mean glance duration, accuracy of speed perception and reaction time were used as driver performance indicators, in which the four types of scenes were analyzed and evaluated by visual test, speed perception test and subjective evaluation. The results showed that compared with Scenes a and b, Scene c with chevron alignment signs can improve alignment guidance along road tunnel horizontal curve, while the test results of Scene d with LED arches as proposed in this study had the best performance in all aspects. The research scheme and test results can provide reference for visual guiding facility design and traffic safety improvement along urban road tunnel horizontal curves.

Capturing Driver Status Using Naturalistic Driving Study Data: Implications for Assessing Health and Safety

The design of advanced driver-assistance systems (ADASs) and driving monitoring systems can be improved with a better understanding of on-road driving behavior. Information on traffic environment, health, engagement in secondary tasks, and corresponding eye glance locations can provide important insights into driver’s in-vehicle movements and status. This study examines the in-vehicle head movement of the driver and the factors affecting it using data from a naturalistic driving study. Linear mixed models were used to examine head position at a given point in time, and hierarchical clustering with dynamic time warping (DTW) was used to explore the trajectories of the head position. The findings show that some health conditions (e.g., limited flexibility, cancer) were correlated to restrictive head position during driving, and vehicle acceleration and traffic environment factors contributed to the variation in head positions.

Influence of different visual guiding facilities in urban road tunnel on driver’s spatial right-of-way perception

Urban road tunnel construction is becoming ever more prevalent, and traffic safety in tunnel operation is even more important. This study evaluates the influence of different visual guiding facilities on drivers’ spatial right-of-way perception by combining quantitative and qualitative methods in order to provide a basis for traffic safety optimization in the tunnel. Simulation scenes were designed for six common types of visual guiding facilities as comprising no facility (baseline), horizontal strips, edge markers, LED arch, vertical stripes, and combination (multiple) facilities. An eye tracker was used to obtain eye movement data of subject drivers exposed to various scenes. After each driving test, psychological feeling of the subjects in tunnel driving, and their ratings of alignment and contour guidance of various facilities were obtained by questionnaires. The research results showed that setting locations and facility types have a great impact on drivers’ glance location and glance duration. When horizontal stripes, edge markers, LED arch and vertical stripes were set separately, alignment guidance and contour guidance performance were found to vary in inverse proportion. Horizontal stripes and edge markers are the preferred and necessary facilities, which are conducive to ensuring longitudinal and horizontal rights-of-way. LED arch and vertical stripes are also good supplements to spatial right-of-way. The combination of these 4 types of facilities can provide multi-level alignment guidance and contour guidance functions, which is beneficial to traffic safety in the tunnel.

Visual attention and steering wheel control: From engagement to disengagement of Tesla Autopilot

Previous research indicates that drivers may forgo their supervisory role with partial-automation. We investigated if this behavior change is the result of the time automation was active. Naturalistic data was collected from 16 Tesla owners driving under free-flow highway conditions. We coded glance location and steering-wheel control level around Tesla Autopilot (AP) engagements, driver-initiated AP disengagements, and AP steady-state use in-between engagement and disengagement. Results indicated that immediately after AP engagement, glances downwards and to the center-stack increased above 18% and there was a 32% increase in the proportion of hands-free driving. The decrease in driver engagement in driving was not gradual over-time but occurred immediately after engaging AP. These behaviors were maintained throughout the drive with AP until drivers approached AP disengagement. In conclusion, drivers may not be using AP as recommended (intentionally or not), reinforcing the call for improved ways to ensure drivers’ supervisory role when using partial-automation.

Users’ Response to Critical Situations in Automated Driving: Rear-Ends, Sideswipes, and False Warnings

Although an automated vehicle may operate for an extended time, it may suddenly request a user’s intervention in critical situations (i.e., beyond the system’s operational design domain). Despite the proliferation of studies to understand how users resume control in such critical situations, a systematic analysis of the whole response process is necessary. We analyzed the visual-motor response process of distracted users to front and lateral vehicle conflicts. We also investigated the effect of false warnings and expectations. In a driving simulator experiment (high fidelity, fixed-based, within-subject design), 45 participants performed a visual-manual distracting task until an audio warning was issued. The response process was modeled with Bayesian generalized linear mixed effects models. The models incorporate the carryover effect (up to the 2nd order), typical side effect of within-subjects experiments. Reaction times were modeled with a shifted-Wald distribution; response choices with a softmax regression. The warning was effective at capturing visual attention and prompting the resumption of control, but it did not directly initiate an intervention. Glance location and the choice and timing of evasive maneuver depended on driving context and on previous experience. Analysis of the whole response process yields more relevant information on the effect of warnings for transition of control than a single measure of intervention time. Furthermore, the carryover effect should not be discounted, because trial randomization can only partially alleviate the problem. We provided results in a format that can be used as a reference for future studies and for computational models of driver behavior.

Predicting Drivers’ Eyes-Off-Road Duration in Different Driving Scenarios

Drivers consecutively direct their gaze to various areas to select relevant information from the traffic environment. The rate of crash risk increases with different off-road glance durations in different driving scenarios. This paper proposed an approach to identify current driving scenarios and predict driver’s eyes-off-road durations using Hidden Markov Model (HMM). A moving base driving simulator study with 26 participants driving in three driving scenarios (urban, rural, and motorway) was conducted. Three different fixed occlusion durations (0-s, 1-s, and 2-s) were applied to quantify eyes-off-road durations. Participants could initiate each occlusion for certain duration by pressing a microswitch on a finger. They were instructed to occlude their vision as often as possible while still driving safely. Drivers’ visual behavior and occlusion behavior were captured and analyzed based on manually frame by frame coding. Visual behaviors in terms of glance duration and glance location in time series were used as input to train HMMs. The results showed that current driving scenarios could be identified ideally using glance location sequences, the accuracy achieving up to 89.3%. And motorway was relatively distinguishable easily with over 90% accuracy. Moreover, HMM-based algorithms that fed up with both glance duration and glance location sequences resulted in a highest accuracy of 92.7% in driver’s eyes-off-road durations prediction. And higher accuracy achieved in longer eyes-off-road durations prediction. It indicates that time series of glance allocations could be used to predict driving behavior and indentify driving environment. The developed models in this study could contribute to the development of scenario sensitive visual inattention prewarning system.

Investigating the correspondence between driver head position and glance location.

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.

Examining drivers' eye glance patterns during distracted driving: Insights from scanning randomness and glance transition matrix

IntroductionVisual attention to the driving environment is of great importance for road safety. Eye glance behavior has been used as an indicator of distracted driving. This study examined and quantified drivers' glance patterns and features during distracted driving. MethodData from an existing naturalistic driving study were used. Entropy rate was calculated and used to assess the randomness associated with drivers' scanning patterns. A glance-transition proportion matrix was defined to quantity visual search patterns transitioning among four main eye glance locations while driving (i.e., forward on-road, phone, mirrors and others). All measurements were calculated within a 5s time window under both cell phone and non-cell phone use conditions. ResultsResults of the glance data analyses showed different patterns between distracted and non-distracted driving, featured by a higher entropy rate value and highly biased attention transferring between forward and phone locations during distracted driving. Drivers in general had higher number of glance transitions, and their on-road glance duration was significantly shorter during distracted driving when compared to non-distracted driving. ConclusionsResults suggest that drivers have a higher scanning randomness/disorder level and shift their main attention from surrounding areas towards phone area when engaging in visual-manual tasks. Practical applicationsDrivers' visual search patterns during visual-manual distraction with a high scanning randomness and a high proportion of eye glance transitions towards the location of the phone provide insight into driver distraction detection. This will help to inform the design of in-vehicle human-machine interface/systems.

Glass half-full: On-road glance metrics differentiate crashes from near-crashes in the 100-Car data

BackgroundMuch of the driver distraction and inattention work to date has focused on concerns over drivers removing their eyes from the forward roadway to perform non-driving-related tasks, and its demonstrable link to safety consequences when these glances are timed at inopportune moments. This extensive literature has established, through the analyses of glance from naturalistic datasets, a clear relationship between eyes-off-road, lead vehicle closing kinematics, and near-crash/crash involvement. ObjectiveThis paper looks at the role of driver expectation in influencing drivers’ decisions about when and for how long to remove their eyes from the forward roadway in an analysis that consider the combined role of on- and off-road glances. MethodUsing glance data collected in the 100-Car Naturalistic Driving Study (NDS), near-crashes were examined separately from crashes to examine how momentary differences in glance allocation over the 25-s prior to a precipitating event can differentiate between these two distinct outcomes. Individual glance metrics of mean single glance duration (MSGD), total glance time (TGT), and glance count for off-road and on-road glance locations were analyzed. Output from the AttenD algorithm (Kircher and Ahlström, 2009) was also analyzed as a hybrid measure; in threading together on- and off-road glances over time, its output produces a pattern of glance behavior meaningful for examining attentional effects. ResultsIndividual glance metrics calculated at the epoch-level and binned by 10-s units of time across the available epoch lengths revealed that drivers in near-crashes have significantly longer on-road glances, and look less frequently between on- and off- road locations in the moments preceding a precipitating event as compared to crashes. During on-road glances, drivers in near-crashes were found to more frequently sample peripheral regions of the roadway than drivers in crashes. Output from the AttenD algorithm affirmed the cumulative net benefit of longer on-road glances and of improved attention management between on- and off-road locations. ConclusionThe finding of longer on-road glances differentiating between safety-critical outcomes in the 100-Car NDS data underscores the importance of attention management in how drivers look both on and off the road. It is in the pattern of glances to and from the forward roadway that drivers obtained critical information necessary to inform their expectation of hazard potential to avoid a crash. ApplicationThis work may have important implications for attention management in the context of the increasing prevalence of in-vehicle demands as well as of vehicle automation.

Drivers anticipate lead-vehicle conflicts during automated longitudinal control: Sensory cues capture driver attention and promote appropriate and timely responses

Adaptive Cruise Control (ACC) has been shown to reduce the exposure to critical situations by maintaining a safe speed and headway. It has also been shown that drivers adapt their visual behavior in response to the driving task demand with ACC, anticipating an impending lead vehicle conflict by directing their eyes to the forward path before a situation becomes critical. The purpose of this paper is to identify the causes related to this anticipatory mechanism, by investigating drivers’ visual behavior while driving with ACC when a potential critical situation is encountered, identified as a forward collision warning (FCW) onset (including false positive warnings). This paper discusses how sensory cues capture attention to the forward path in anticipation of the FCW onset. The analysis used the naturalistic database EuroFOT to examine visual behavior with respect to two manually-coded metrics, glance location and glance eccentricity, and then related the findings to vehicle data (such as speed, acceleration, and radar information). Three sensory cues (longitudinal deceleration, looming, and brake lights) were found to be relevant for capturing driver attention and increase glances to the forward path in anticipation of the threat; the deceleration cue seems to be dominant. The results also show that the FCW acts as an effective attention-orienting mechanism when no threat anticipation is present. These findings, relevant to the study of automation, provide additional information about drivers’ response to potential lead-vehicle conflicts when longitudinal control is automated. Moreover, these results suggest that sensory cues are important for alerting drivers to an impending critical situation, allowing for a prompt reaction.

Differences in glance behavior between drivers using a rearview camera, parking sensor system, both technologies, or no technology during low-speed parking maneuvers

This study characterized the use of various fields of view during low-speed parking maneuvers by drivers with a rearview camera, a sensor system, a camera and sensor system combined, or neither technology. Participants performed four different low-speed parking maneuvers five times. Glances to different fields of view the second time through the four maneuvers were coded along with the glance locations at the onset of the audible warning from the sensor system and immediately after the warning for participants in the sensor and camera-plus-sensor conditions. Overall, the results suggest that information from cameras and/or sensor systems is used in place of mirrors and shoulder glances. Participants with a camera, sensor system, or both technologies looked over their shoulders significantly less than participants without technology. Participants with cameras (camera and camera-plus-sensor conditions) used their mirrors significantly less compared with participants without cameras (no-technology and sensor conditions). Participants in the camera-plus-sensor condition looked at the center console/camera display for a smaller percentage of the time during the low-speed maneuvers than participants in the camera condition and glanced more frequently to the center console/camera display immediately after the warning from the sensor system compared with the frequency of glances to this location at warning onset. Although this increase was not statistically significant, the pattern suggests that participants in the camera-plus-sensor condition may have used the warning as a cue to look at the camera display. The observed differences in glance behavior between study groups were illustrated by relating it to the visibility of a 12–15-month-old child-size object. These findings provide evidence that drivers adapt their glance behavior during low-speed parking maneuvers following extended use of rearview cameras and parking sensors, and suggest that other technologies which augment the driving task may do the same.

Evaluation of driving behavior on rural 2-lane curves using the SHRP 2 naturalistic driving study data

IntroductionOver half of motor vehicle fatalities are roadway departures, with rural horizontal curves being of particular interest because they make up only a small share of the system mileage but have a crash rate that is significantly higher than tangent sections. However the interaction between the driver and roadway environment is not well understood, and, as a result, it is difficult to select appropriate countermeasures. MethodIn order to address this knowledge gap, data from the SHRP 2 naturalistic driving study were used to develop relationships between driver, roadway, and environmental characteristics and risk of a road departure on rural curves. The SHRP 2 NDS collected data from over 3,000 male and female volunteer passenger vehicle drivers, ages 16–98, during a three year period, with most drivers participating between one to two years. A Roadway Information Database was collected in parallel and contains detailed roadway data collected on more than 12,500 centerline miles of highways in and around the study sites. ResultsRoadway data were reduced for rural 2-lane curves and included factors such as geometry, shoulder type, presence of rumble strips, etc. Environmental and traffic characteristics, such as time of day, ambient conditions, or whether the subject vehicle was following another vehicle, were reduced from the forward roadway video view. Driver characteristics, such as glance location and distraction were reduced from the driver and over the shoulder videos. ConclusionsLogistic regression models were developed to assess the probability (odds) of a given type of encroachment based on driver, roadway, and environmental characteristics. At the point this study was undertaken, crashes and near crashes were not yet available and only around 1/3 of the full SHRP NDS dataset could be queried. As a result, the likelihood of crossing the right or left lane line (encroachments) and speeding were used as dependent variables.

How Dangerous Is Looking Away From the Road? Algorithms Predict Crash Risk From Glance Patterns in Naturalistic Driving

In this study, the authors used algorithms to estimate driver distraction and predict crash and near-crash risk on the basis of driver glance behavior using the data set of the 100-Car Naturalistic Driving Study. Driver distraction has been a leading cause of motor vehicle crashes, but the relationship between distractions and crash risk lacks detailed quantification. The authors compared 24 algorithms that varied according to how they incorporated three potential contributors to distraction--glance duration, glance history, and glance location--on how well the algorithms predicted crash risk. Distraction estimated from driver eye-glance patterns was positively associated with crash risk. The algorithms incorporating ongoing off-road glance duration predicted crash risk better than did the algorithms incorporating glance history.Augmenting glance duration with other elements of glance behavior--1.5th power of duration and duration weighted by glance location--produced similar prediction performance as glance duration alone. The distraction level estimated by the algorithms that include current glance duration provides the most sensitive indicator of crash risk. The results inform the design of algorithms to monitor driver state that support real-time distraction mitigation systems.

Methodology for Capturing Driver Eye Glance Behavior during In-Vehicle Secondary Tasks

Driving is a visual task; any driver behavior that takes the driver's visual attention from the driving environment is likely to increase the risk of a crash. Many new intelligent transportation systems telematics applications are now being installed in cars, and some of these may result in substantial degradation of visual attention. Accurately capturing driver eye glance behavior during the evaluation of these devices is critical to assessing the safety impact of engaging in secondary tasks while driving. The development of a methodology is reported; it reliably determines on-road and off-road eye glance duration by using video data collected during highway driving evaluation trials while drivers were engaged with secondary tasks. Human raters determined glance location and duration by detailed coding of the driver's eye movements on the videos. The raters agreed most of the time, but sufficient disagreement suggested that using the consensus of multiple raters significantly improved the reliability of the resulting eye glance data.

Methodology for Capturing Driver Eye Glance Behavior During In-Vehicle Secondary Tasks

Driving is a visual task; any driver behavior that takes the driver's visual attention from the driving environment is likely to increase the risk of a crash. Many new intelligent transportation systems telematics applications are now being installed in cars, and some of these may result in substantial degradation of visual attention. Accurately capturing driver eye glance behavior during the evaluation of these devices is critical to assessing the safety impact of engaging in secondary tasks while driving. The development of a methodology is reported; it reliably determines on-road and off-road eye glance duration by using video data collected during highway driving evaluation trials while drivers were engaged with secondary tasks. Human raters determined glance location and duration by detailed coding of the driver's eye movements on the videos. The raters agreed most of the time, but sufficient disagreement suggested that using the consensus of multiple raters significantly improved the reliability of ...

Investigating the Effect of Performing Voice Recognition Tasks on the Detection of Forward and Peripheral Events

This research investigates the ability of a driver to detect forward and peripheral events while driving and interacting with a voice recognition system. Thirty-seven participants took part in a driving experiment on a closed highway. Participants performed phone dialing tasks using either a voice recognition system simulation or a manual cell phone while driving. Participants also monitored two lights: one mounted on the hood of the vehicle and one on the left side mirror. Participants were instructed to press a foot pedal when a light appeared (i.e., event). Data were collected on drivers' glance locations as well as their responses to events. Results suggested that voice recognition dialing generally resulted in better visual scanning of the environment and response time to events than manual dialing. In addition, for younger participants, performance using the voice recognition system was similar to baseline driving, while older participants showed performance decrements for all tasks relative to baseline driving.