There can be a lot of technical challenges to face during the development of autonomous vehicles, but one of the hardest is knowing and preventing accidents with pedestrians and other objects that might end up in the street.
As many bicycle riders know, there is a lot of intense eye contact between bike riders and drivers when bikers are attempting to keep themselves safe from inattentive drivers - especially with so many smartphones to distract people. That usual interaction between drivers and bike riders is something that computers can't easily learn.
Derq, a Techstars Mobility alumni based in Dubai and Detroit, is going through a year long project within Detroit to help that pedestrian/vehicle problem and the risks that are involved, especially around intersections.
“We’re concentrating on road safety for regular cars as well as autonomous vehicles,” says Georges Aoude, Derq’s co-founder and CEO. “Our two main applications are intersection safety—predicting red light violations and sending warnings to a vehicle—and pedestrian safety, which involves leveraging cameras from smart cities to predict pedestrian intent.”
Derq's software currently pays attention to the interactions between the vehicle and pedestrians and general infrastructure to predict and avoid any accidents. They are using a patented AI supported algorithm, which was developed by Aoude while he was attending MIT, to have another two extra seconds of time for both cars and their drivers.
“If you think of the Uber accident [which resulted in a fatality], they had the best sensors but the car still couldn’t see, or they didn’t work,” he notes. “We observe for a long time—on day one, we can’t make predictions. So we collect data and teach the vehicles what pedestrians are doing. The model is smart enough to adapt and predict intent, and we’re able to show we can do it with a high rate of accuracy and a low rate of false warnings.”
Aoude states that Derq has purposefully chosen the Randolph-Jefferson intersection in Detroit because it's congested and busy. It's a major intersection downtown that connects to nearby highways and access to the Detroit-Windsor tunnel.
Apart of their Detroit project, Derq is working with the Michigan Department of Transportation to install their sensors around the intersection. These sensors give data feedback that allows Derq to run their software, create predictions, and communicate any possible threats straight away.
“MDOT, the Michigan Economic Development Corporation, Techstars, and PlanetM made it possible for a startup like us to build our technology in Dubai and test it in Detroit,” he adds.
Derq started up in 2016 and has already fund raised $1.5 million through an investment round. They are in the process of running another round of fundraising in hopes to scale their software and move into new markets.
The pilot in Detroit, which began in May, will go on for one year, and Derq hopes to expand into other MDOT controlled intersections within Michigan. They have also talked about testing more with the American Center for Mobility, located outside of Ann Arbor, MI.
“Our goal is to grow our presence to many other Michigan locations and grow our partnerships with players in the ecosystem,” Aoude says, adding that Derq already has signed 15 non-disclosure agreements with partners in the mobility industry as well as a memorandum of understanding and joint development agreement with Dubai’s government. “What we’re doing today can help [cars function better] now—we don’t have to wait for autonomous vehicles to be on the road.”
Join us in Madrid from the 13th to the 16th of November for the Property Portal Watch Conference.