AutoX Has Built a Self-Driving Car That Navigates with a Bunch of $50 Webcams

While companies like Uber and Google build self-driving cars replete with pricey sensors, Jianxiong Xiao is doing the same thing with some $50 webcams.

Previously an assistant professor of computer science at Princeton, Xiao is the founder and CEO of AutoX, a startup working to make autonomous transportation accessible to everyone. Speaking at MIT Technology Review’s EmTech Digital conference in San Francisco this week, Xiao credited his past with inspiring the startup’s goal: as a child growing up poor in a small town in China, he wasn’t able to visit the ocean until he was 18, despite the fact that it was just 20 miles away.

Now, Xiao said, he imagines a future where kids don’t have to depend on their parents to drive them around, for instance, and can instead summon a self-driving ride.

“Autonomous driving should not be a luxury,” he said.

To make this happen in a way that’s economical, AutoX is eschewing the standard self-driving car sensors like inertial measurement units, lidar, and differential GPS, which can add up to hundreds of thousands of dollars. Instead, over the past six months the company built software—the brains of a self-driving car, essentially—that harnesses seven Logitech webcams that are mounted on the front of a car, arranged to get a 360-degree view.

At EmTech, Xiao showed off some videos of the technology at work, letting a car navigate city streets on its own during the day, in light rain on a winding road, on a cloudy night, and at night on the highway. Another video showed how it can drive in varying lighting conditions, too—such as when going under a freeway overpass in San Jose. These kinds of conditions are still tricky even for self-driving cars bristling with state-of-the-art sensors.

Xiao says AutoX hopes to work with carmakers as well as companies, like Lyft and Uber, that are already helping people get rides.