The National Safety Council says at least nine people in the U.S. die and another 100 are injured every day in crashes caused by distracted driving.
In-vehicle technologies such as dashboard touchscreens have contributed to this enormous safety threat. But consumers are fond of these technologies and they aren’t going away.
However, there is a pantheon of other distractions that occur behind the wheel that vary greatly in form and severity. The mostly illegal use of cell phones or texting while driving tops the list. But there are so many other possibilities, such as “rubbernecking” at incidents outside the vehicle, interacting inside with children or pets, fiddling with the radio, eating while driving, etc. Unfortunately, distracted driving is a two-way street. Perfectly attentive drivers can be injured due to the distractions affecting the driver coming the other way. This is why distracted driving is quickly catching up to DUIs in terms of economic impact. It now costs society $40 million for distracted driving compared with $44 million for DUIs.
As young drivers, we were taught distracted driving is dangerous. As adults, we get bombarded with public service announcements and road signs about the dangers. Yet, most of us still do things we shouldn’t behind the wheel. A 2016 study found that nearly 50% of drivers admitted to, while driving, reading a text message, sending a text message, checking their phone for directions or using social media. Overall, nearly 60% of respondents admitted to using their cell phone at least once while driving.
Context is everything, of course, and with distracted driving, context often is malleable to fit the immediate personal needs of the driver. A large amount of cognitive dissonance is involved.
Because of the obvious safety and monetary implications, efforts to address distracted driving are being stepped up. More importantly, it is another element of human nature that can be addressed using artificial intelligence. Thanks to the mechanics of deep learning and constant improvements in computer vision technology and algorithms, there are better ways being tested to monitor and alert drivers when they slip up on safety while driving, either intentionally or unintentionally.
Generally, there are three categories of distractions that are being dealt with via artificial intelligence:
- Visual distractions that make you take your eyes off the road.
- Manual distractions that take your hands off the steering wheel.
- Cognitive distractions that prevent you from being focused on driving, perhaps because of drowsiness.
Software algorithms can address these issues using image processing and input coming from sensors that synthesize in real time selected information from the driver and interior of the vehicle. Engineers are developing these algorithms to accurately predict all possible human behavior, even though it is sometimes unpredictable and irrational.
These algorithms are critical because they serve two main purposes: to provide output to the driver, in the form of alerts or other information; and to specify the way the system should react to control the vehicle (brake, steer or other safety-related navigation commands).
Using AI and visual AI (cameras inside a sensor, for example), it is possible to ascertain quickly what’s going on inside the cabin and to continually build use cases so we can understand when something may interfere with the driving process and create new ways to alert for that.
The development of new warning systems is important because drivers can become too conditioned to certain alerts and, ultimately, will stop paying attention.
So, to keep alerts from becoming “white noise,” there is work taking place on a combination of alerts, like changing the background of the color of the dashboard in the car, changing the radio volume, or turning off the radio so an alert can come through the audio system’s speakers.
The combination of artificial intelligence and alerting will eventually provide a robust solution that will monitor and prevent most of the distractions if someone is in the car. These solutions are going to become more common and more comprehensive and ultimately could result in vehicles that will be defined and sold as “distraction cognizant” or some other descriptive moniker.
If researchers and automakers produce positive results by attacking driver distraction with artificial intelligence and visual monitoring systems, there is a good chance the auto industry will become legally mandated to provide them.
This already is the case with Advanced Driver Assistance Systems. By the end of 2020 in the U.S. and EU, all new vehicles must be equipped with two ADAS safety solutions: autonomous emergency-braking systems and forward-collision warning systems.
Reducing crashes caused by decreasing the incidence of distracted driving is a good bet right now. It’s something that should put everyone in a better mood. And, by the way, there is research on artificial intelligence being able to sense the mood of a driver which will result in cabin adjustments that will make the driver more “comfortable.” Let’s just hope that comfort doesn’t cause any more distractions.
Shmulik Shapiro is Executive Vice President-Global Business Development & Strategy at RSIP Vision. Shmulik leads RSIP’s efforts in delivering customized solutions that meet the most complex technology challenges in the hi-tech and healthcare industries. Before joining RSIP Vision, Shmulik was VP of Business Development for DiA Imaging Analysis, where he promoted use of advanced pattern recognition and machine learning technology to create automated, fast and accurate tools to analyze ultrasounds. RSIP Vision is headquartered in Jerusalem, with U.S. offices in San Jose, CA, and Boston, MA.