AVT Consortium Research
Assistive/automated driving support, human-centered considerations in user engagement
“Driver response and recovery following automation initiated disengagement in real-world hands-free driving”
Pnina Gershon, Bruce Mehler, and Bryan Reimer
This research aims to better understand how advanced driver assistance systems (ADAS), which are increasingly available in consumer vehicles, changes driver behavior. The study looks specifically at 14 drivers over a one-month period, each driving a Cadillac CT6 equipped with Super Cruise—a partial automation system that, when engaged, enables hands-free driving—as well as data acquisition systems that records driver behavior. This real-world data illustrates drivers’ response to, and recovery from, automation-initiated disengagements by quantifying changes in visual attention, vehicle control, and time to return to steady-state behaviors. The study found that automation-initiated disengagements triggered substantial changes in driver glance behavior, including shorter on-road glances and frequent transitions between looking at the road and the driving instruments and overall differences in reaction times based upon the presence of hands on the wheel prior to disengagement. This work aims to help vehicle designers enhance future systems.
Assistive/automated driving support, human-centered considerations in user engagement
“Visual attention and steering wheel control: From engagement to disengagement of Tesla Autopilot”
Alberto Morando, Pnina Gershon, Bruce Mehler, and Bryan Reimer
Previous research indicates that drivers may forgo their supervisory role with partial-automation. This research investigates whether this behavior is the result of the time that automation was active. The study collected naturalistic data from 16 Tesla owners driving under free-flow highway conditions. Researchers 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. Drivers may not be using AP as recommended, reinforcing the call for improved ways to ensure drivers’ supervisory role when using partial-automation.
Assistive/automated driving support, human-centered considerations in user engagement
“Characterizing driver speeding behavior when using partial-automation in real-world driving”
Samantha H. Haus, Pnina Gershon, Bruce Mehler & Bryan Reimer
Understanding how drivers speed is important for developing countermeasures, especially as new automation features emerge. This study used a combination of supervised and unsupervised data analysis techniques to assess relevant factors in real-world speeding epochs—defined as traveling at least five miles per hour over the speed limit for a minimum duration of three seconds. Vehicle speed-exceedance profiles were characterized over time using Dynamic Time Warping and were included in multivariate models that evaluated the associations between different features of the speeding epochs, such as speeding duration and magnitude. This work highlights the variability in speeding behavior between and within partially-automated and manual driving. The results suggest that the design of systems intended to mitigate risky speeding behaviors should consider targeting divergent behaviors observed between manual and automated driving.
Safety of vulnerable road users, driving behavior across technologies and context
“Interdependence of driver and pedestrian behavior in naturalistic roadway negotiations”
Zach Noonan, Pnina Gershon, Josh Domeyer, Bruce Mehler & Bryan Reimer
Negotiating right-of-way between drivers and pedestrians can be a complex social dilemma, and misjudgment on either side can potentially lead to dangerous outcomes. This research examines the interdependence of pedestrians and drivers across different intersection types, capturing other external factors, such as other vehicles or pedestrians. A vehicle-pedestrian interaction dataset was extracted from a large naturalistic driving data collection effort, which included vehicle, pedestrian, and contextual information. The study found that interactions in undesignated crossings (i.e., jaywalking) were associated with interdependent behavior, whereas interactions in designated crossings (i.e., crosswalks and parking lots) showed an effect on the driver’s wait time, but no significant corresponding partner effect on the pedestrian. Protected intersection interactions (i.e., traffic lights and stop signs) demonstrated no significant partner effects. These findings can inform how context and driver-pedestrian interactions should be incorporated into future modeling efforts, which may support the design of automated systems that are able to interact more safely, efficiently, and socially.
Consumer attitudes and understanding of new technologies
“Consumer Knowledge and Acceptance of Driving Automation: Changes Over Time and Across Age Groups”
Chaiwoo Lee, Pnina Gershon, Bryan Reimer, Bruce Mehler, Joseph F. Coughlin
This study presents a five-year series of large-scale surveys on consumer knowledge, perception, and acceptance of vehicle automation in the U.S. The results suggest a continued hesitance toward use of self-driving vehicles, with willingness to use them increasing sharply under hypothetical conditions around inability to drive and added safety assurance. Drivers of all ages were most comfortable with driver-assist level automation, but acceptance of automation overall decreased with age. The findings also indicate that the public may have inaccurate beliefs about the overall availability of self-driving vehicles.
Consumer attitudes and understanding of new technologies, human-centered considerations in user engagement
“Evaluating and rating the safety benefits of advanced vehicle technologies: Developing a transparent approach and consumer messaging to maximize benefit”
Bruce Mehler, Pnina Gershon, and Bryan Reimer
The AVT Consortium launched in 2015, following a project in 2012 in which the MIT AgeLab worked with a major traffic safety organization to develop a data-driven system for rating the effectiveness of new technologies intended to improve safety. Drawing from this initial work, as well as newer sources of data, AVT researchers argue that the evaluation and rating of safety and driver assistance technologies for informing consumers should consider both the theoretical and existing demonstrated benefit of specific technologies. Ratings based on observed benefit for actual drivers under real-world conditions are proposed to be complementary, rather than competing with, ratings focused largely on controlled, test-track evaluations of engineered capability. This approach aims to help consumers in considering the extent to which a technology is or is not relevant to their particular driving needs. Topics also addressed include the opportunities and challenges of automotive technology software updates, standardization of the naming of technologies, branding and capability confusion, issues associated with obtaining accurate information and training at dealerships, and how consumer input might better be leveraged to everyone’s benefit.