
Drivers who are already on the wrong side of existing driver monitoring systems know their warnings and wails can be annoying, and they sometimes yell wolf. Automotive engineers must strike a delicate balance when choosing when and how a system beeps or beeps.
The key to building a great driver monitoring system, experts say, is creating software that not only tells drivers when they’re doing something wrong, but also supports their attention. “It’s about defensive driving and avoiding conflict altogether, not avoiding a crash once a conflict occurs,” said Greg Fitch, director of safety research for Google’s in-car app Android Auto. That could mean it emits a quiet but escalating tone rather than a high-pitched beep when it sees you looking aside — when you might be paying attention to a pedestrian. Maybe when you use the steering wheel to hug one side of the lane, the system doesn’t fully disengage from automatic lane keeping, but instead shares control.
Driver monitoring systems are too new to have exhaustively proven effective rules. Regulators, automakers and academia are still debating how best to support impaired, easily distracted people while driving. Answers may vary by person, company or culture. “Especially in Asian countries, they’re less inclined to announce loudly because you might be driving and someone else is in the car,” Smart Eye’s Zijderveld said. “If the siren goes off, other people will hear it and they will think you are a bad driver.”
Some safety experts believe that much of what automakers are rolling out so far is not good enough. Last year, U.S. safety group Consumer Reports began offering an extra safety point to vehicles with partially autonomous features and active driver monitoring systems.
CR’s tests found that some automakers’ systems allow vehicles to travel for as long as 30 seconds — half a mile at 60 mph — without the driver’s hands touching the wheel. (Its recent tests brought top honors to Ford’s BlueCruise, which the company says can change lanes, reposition cars within lanes and drive hands-free on 130,000 miles of North American highways, and includes an eye-tracking camera , when the driver stops paying attention to the road for a few seconds.)
The U.S.-based Insurance Institute for Highway Safety last year created a “checklist” of technologies to include in driver monitoring systems, including monitoring the driver’s gaze and hand position and using rapidly escalating alerts if the driver is not paying attention to regain the driver’s attention in response to the initial warning. (The group has yet to release its first set of ratings.) How a system interacts with drivers may be more important—and more difficult—than how it monitors them. “You have the vehicle monitor the driver and verify that they’re doing what they’re supposed to do. But so what?” said Alexandra Mueller, the group’s senior research scientist. “It’s about how the vehicle responds to the information. “
Still, those who study how new car technology interacts with humans say these small, driver-facing cameras have huge potential to help improve safety for all drivers. “A lot of people don’t know they’re bad drivers unless they’re likely to get honked, get a ticket, or get into a crash,” says Greg Neiswander, Android Auto’s head of research and testing. With the right feedback — which has proven to be a tall order — “you could theoretically make people better drivers, better drivers,” he said.
In the future, “The question is not, can we monitor drivers? But we can support Are they more efficient? Bryan Reimer, a research scientist at MIT who leads the Advanced Vehicle Technology Consortium, which brings together industry experts and academics to study how people interact with autonomous driving features, said. If implemented in the right way, these systems can not only stop people from doing bad things behind the wheel, but also help them actively do good things.