The appeal of self-driving vehicles is the promise that drivers will be able to do other tasks on the road or simply enjoy the ride as automation technology takes the task of driving out of human hands. However, the technology is not at the point yet where automated functions can be relied upon for a driver to take their eyes off the road, according to researchers from the University of Toronto Engineering.
The researchers recently used an automated vehicle driving simulator and eye-tracking equipment to study two types of in-vehicle displays and their impact on the driving behavior of 48 participants. The team found that drivers become over-reliant on the automated technology, especially in vehicles that have in-vehicle displays with takeover request and automation capability (TORAC).
This request asks the driver to take vehicle control when the automation is not able to handle the situation.
"Drivers find themselves in situations where, although they are not actively driving, they are still part of the driving task — they must be monitoring the vehicle and step in if the vehicle fails," said Birsen Donmez, professor at the University of Toronto Engineering. "And these vehicles fail, it's just guaranteed. The technology on the market right now is not mature enough to the point where we can just let the car drive and we go to sleep. We are not at that stage yet."
Even though some cars are advertised as self-driving, they are still just Level 2, or partially automated, meaning drivers should not rely on these types of vehicle automation. Tesla’s automated system warns drivers every 30 seconds or less when their hands are not detected on the wheel. When the automation fails, driver attention and anticipation are key factors to whether a traffic accident happens or not.
In the university test’s, one scenario involved participants receiving a non-driving, self-paced task such as reading a text message when the takeover prompt was turned on.
"Their monitoring of the road went way down compared to the condition where these features were turned off," Donmez said. "Automated vehicles and takeover requests can give people a false sense of security, especially if they work most of the time. People are going to end up looking away and doing something non-driving related."
Another test involved a second in-vehicle display system that added information about traffic to the data provided by the TORAC system, called STTORAC. This system informs drivers about the surrounding driving environment such as potential traffic or conflicts on the road. This type of display shortened the reaction time in scenarios where drivers had to take over control of the car, a significant improvement. This type of display helps to keep drivers better engaged in monitoring and anticipating traffic conflicts.
The next steps involve testing non-driving behaviors such as drowsiness while operating an automated vehicle.
The full research can be found in the journal ScienceDirect.