Each year roughly 1 million people are arrested for driving under the influence of alcohol. For the past ten years alcohol has played a role in roughly 30% of all traffic-related deaths in the United States. Concerted marketing and law enforcement efforts to reduce drunk driving through the 1990s were remarkably successful. But in the ensuing years it seems that social measures (like media campaigns and stiffer penalties) may have reached the limits of how much they can reduce impaired driving.
Recent initiatives have emphasized the possibility of using technological interventions, like traditional breathalyzer ignition locks or newer passive systems for detecting the blood alcohol level (BAC) of vehicle occupants to further curtail driving under the influence of alcohol. But these systems have obvious limitations. Ignition interlocks are both invasive and regularly bypassed when the driver under monitoring persuades a sober individual to help them “beat the system.” Newer ambient in-vehicle BAC detection technologies prevent these evasions, but often at the risk of higher false-positives (stopping both drunk drivers and designated drivers with passengers who have been drinking). Traditionally, BAC detection also does nothing to address more recently legalized or decriminalized intoxicants (like cannabis) and the increasing availability of products that include CBD (whose effect on driving is as of yet unknown).
Using Autonomous Vehicle Research to Address DUIs
In recent years Realtime Technologies simulation users have done research that could be applied to better solutions. For example, a 2017 study at Stanford, used standard RTI sims and neural monitoring hardware (including eye-tracking and fNIRS) to correlate “neural and physiological responses . . . increased cortical activation . . .[and the] relationships among cortical activation, steering control, and individual personality traits suggest that individual brain states and traits may be useful in predicting a driver’s response[s] . . . . Results such as these will be useful for informing the design of automated safety systems that facilitate safe and supportive driver–car communication.”
Some institutions, like Stanford, have specifically sought out RTI sims for their research because RTI provided “the first simulator to automatically synchronize EEG, EKG, respiration, and skin conductance with driving behavior, allowing new answers to questions about distraction and the ability of cars to take over based on the driver’s mental and physical state.”
Research like this, that explores how designers can collect and process vehicle-collected data on the driver’s actual behaviors, might one day allow the vehicle itself to detect impaired driving regardless of the source of the impairment—be it alcohol, cannabis, a mobile device, or a medical emergency.
Streamlining Autonomous Vehicle Research
According to Heather Stoner, FAAC’s General Manager for Realtime Technologies, “although this isn’t research we’ve helped anyone with yet, this is a good example of the types of things that you can do with an RTI simulator, and the caliber of research that’s possible.” This owes to the flexibility and openness of the RTI simulation platform. Researchers with limited computer programing or hardware experience can get a study up and running quickly. But those with more specific needs can get “under the hood”, coordinating input and output among monitoring devices, smartphones, and other peripherals. “If it has an API that you can send information out of it, it can definitely go into SimObserver, which will line it up with the built-in simulator data collection.”