Ford studies how driverless cars signal intentions

Display uses light combinations to simulate human driver nods or waves

Published: September 14, 2017, 5:50 PM
Updated: November 21, 2021, 3:07 PM

Ford VTTI Research vehicle yielding at crosswalk

Just about everybody is familiar the need for autonomous vehicles to get information from other road users and road infrastructure, but now Ford is testing a way for autonomous vehicles to relay information to other road users.

In partnership with the Virginia Tech Transportation Institute (VTTI), the company is testing its lighting method that signals intent to pedestrians, bicyclists and other (human) drivers, much like a human driver signals intention with a nod or hand wave.

“Understanding how self-driving vehicles impact the world as we know it today is critical to ensuring we’re creating the right experience for tomorrow,” said John Shutko, Ford’s human factors technical specialist. “We need to solve for the challenges presented by not having a human driver, so designing a way to replace the head nod or hand wave is fundamental to ensuring safe and efficient operation of self-driving vehicles in our communities.”

Ford and the VTTI created a user experience study that involved a human driver wearing a seat suit to simulate a driverless vehicle and gauge human reactions to a vehicle’s external lighting signals indicating the car is yielding the right of way or about to accelerate from a stop.

Printing out driving intentions wasn’t considered an option because not everybody might understand the language, and symbols might be too ambiguous (based on historical studies on symbol recognition by consumers). Because signals for braking and direction indicators are already widely used and acknowledged, the companies decided to expand on their usage.

Ford placed a light bar on the windshield of a Transit Connect minivan to indicate if the vehicle was yielding (two white lights moving side to side), driving autonomously (a solid white light) or starting to accelerate (rapidly blinking white light). Six high-definition cameras mounted around the minivan captured the behaviour of other road users that may not have been seen by the disguised driver.

The vehicle operated around Arlington, Virginia during August 2017, driving more than 150 hours and covering some 2,900 km. The driver activated the signal bar more than 1,650 times at intersections, parking lots and garages, and airport roadways.

“This work is of value not only to vehicle users and manufacturers, but to anyone who walks, rides or drives alongside an autonomous vehicle in the future,” said Andy Schaudt, project director, Center for Automated Vehicle Systems, Virginia Tech Transportation Institute.

Researchers will analyze the data on how other road users reacted to the signals to push for an industry standard for a form of visual communication understood by most people in any country where autonomous vehicles will operate. The next step will be to adapt the communications protocol to interact with the visually impaired.

“Preparing for a self-driving future is going to take all of us working together,” concluded Shutko. “That’s why we’re developing and advocating for a standard solution so it can be adopted by the industry and applied to all self-driving vehicles.”