Accidents happen, but not all of them are inevitable. Drunk driving is one of the deadliest and most preventable causes of roadway fatalities. In 2022 alone, more than 13,000 people died in alcohol-related vehicular crashes in the United States, accounting for nearly a third of all traffic deaths, according to the National Highway Traffic Safety Administration.
Now a group of high school students in North Carolina is taking action with SoberRide, an AI-enabled device they designed to prevent intoxicated people from driving.
Breathalyzer-based ignition interlocks are already in use; they require the driver to blow into a device, proving they are sober enough to drive. However, these interlocks are not foolproof because someone other than the driver could breathe into them, trying to outsmart the device.
SoberRide uses a combination of cameras, sensors, and machine-learning algorithms to detect signs of alcohol impairment in the driver—such as pupil dilation, bloodshot eyes, and the presence of ethanol used in alcoholic beverages—before allowing a vehicle to be put into drive.
“We’ve been training our neural network to classify intoxication, refining the system’s ability to reliably sense whether someone is drunk or sober,” says Swayam Shah, chief executive officer and cofounder of SoberRide. He’s an 11th-grader at Enloe Magnet High School, in Raleigh.
The SoberRide team presented its invention at the MIT Undergraduate Research Technology Conference in October, sponsored by groups like the IEEE University Partnership Program and IEEE Women in Engineering.
The students also showcased their technology at another IEEE-supported event: the International Conference on Artificial Intelligence, Robotics, and Communication, held in December in Xiamen, China.
From tragedy to technology
The inspiration for SoberRide came from a tragedy. Shah was in eighth grade when a neighbor was killed in a collision caused by a drunk driver. The loss prompted Shah to research the magnitude of the drunk-driving problem.
“We learned that nearly 300,000 people die each year in crashes involving at least one drunk driver,” says Shaurya Mantrala, a senior at Enloe and the startup’s chief product officer.
“We don’t just want to sell a product. We want to end drunk driving—for good.” —Swayam Shah, SoberRide CEO
Motivated to develop technology to address the issue, the students took the initiative to research, design, and build SoberRide. SoberRide now consists of extremely sophisticated technology, which has been issued a U.S. patent and is based on published research presented by Shah and Mantrala at venues such as MIT.
Shah leveraged his background in coding—honed since the fourth grade—along with knowledge gained from a Harvard introduction to computer science course, which he took in seventh grade.
“I had a background in Python, Java, and C++,” he says, and his intellectual curiosity led to a growing interest in hardware. He spent countless hours learning about Arduino, Raspberry Pi, soldering, and other elements of designing and building electronics.
AI-powered detection prevents workarounds
SoberRide’s AI-driven approach sets it apart from existing ignition interlocks. Because such devices analyze the breath of the person who blows into them, the system can be bypassed by having a sober person breathe into it. SoberRide’s creators say it will leverage cameras that are already inside a car—technology that automakers are increasingly incorporating for driver-assist monitoring—to analyze the driver’s behavior. Should it detect signs of inebriation, it doesn’t allow the car to be put into drive.
The system combines ethanol sensors placed on the dashboard or driver-side B-pillar, which is the vertical roof support between the front and rear doors. Those sensors, combined with facial analysis, assess intoxication indicators such as eye redness and facial swelling. To mitigate racial bias in facial recognition, the AI model was trained using adiverse dataset curated by IIT researchers.
“The SoberRide device weighs facial analysis, which accounts for 25 percent of its decision regarding whether the person behind the wheel is impaired,” says Mantrala, who co-authored two research papers along with Shah, which were published in the IEEE Xplore Digital Library.
In addition to developing the technology, the SoberRide team has lobbied state and federal lawmakers to push for policies mandating in-vehicle DUI detection systems.
“I just got back [in March] from Washington, D.C., where I was advocating in Congress for legislation mandating passive anti-drunk systems in all vehicles,” Shah says. He did that as a side quest when he traveled to the nation’s capital to be honored as a 2025 National STEM Festival champion. The award, sponsored by EXPLR, was presented to Shah for being one of the top 106 STEM students in the country.
The team also formed a partnership with Mothers Against Drunk Driving to advocate for the HALT law, passed by Congress in 2021 as part of the Infrastructure Investment and Jobs Act.
“Under the Biden administration, there was federal action aimed at requiring passive anti-drunk-driving systems in all new vehicles by 2026,” Shah says. “But with the change in administration, the chances of this happening at the federal level have diminished. That’s why we’ve taken our advocacy to state legislators and governors.”
Shah and his team have brought this technology to North Carolina Governor Josh Stein, the state’s former Governor Roy Cooper, and Congressional Representative Deborah Ross to continue legislative advocacy.
A new business model
Although automakers have been slow to adopt the technology, the SoberRide team is targeting fleet vehicle operators such as trucking companies and delivery services, as well as parents of teenage drivers, as early adopters. In the course of their extensive market research, the SoberRide team found that more than 90 percent of teenage drivers’ parents they contacted said they would purchase this technology to serve as a berm against their kids getting behind the wheel while intoxicated.
Despite the uphill battle in securing automaker buy-in, the SoberRide team has received national recognition. Most notably, the SoberRide startup became the first high school team ever to be invited to showcase its technology at the CES event (the erstwhile Consumer Electronics Show) in Las Vegas.
“Honda, Nissan, and Toyota were among the many vehicle manufacturer representatives who visited the SoberRide booth at CES,” Mantrala says. “They showed great interest in the technology, with some of them even offering to start beta-testing our product in their vehicles.”
The team was also recently named global finalists for both the Conrad and Diamond High School Entrepreneurship Challenges, where they will compete on the international stage for further recognition, mentoring, and funding opportunities. The students were runner-ups at last year’s TiE Young Entrepreneurs (TYE) Globals pitch competition, sponsored by the Indus Entrepreneurs, a Silicon Valley nonprofit. The annual competition evaluates high school startups’ ideas, judging them on customer validation, business models, and execution. They were also recently promised US $100,000 in funding from the TiE Angels program, which they plan to utilize to perfect their technology and bring their product to market.
A mission beyond profit
Shah and his team understand widespread adoption could take years, he says, but they remain committed to their mission.
“We don’t just want to sell a product,” he says. “We want to end drunk driving—for good.”
From Your Site Articles
Related Articles Around the Web