This startup’s AI is smart enough to drive different types of vehicles



Mountain View, Calif.-based Ghost’s Jay Gierak is impressed with Wayve’s demos and agrees with the company’s overall take. “The robotic approach is not the right way to do this,” says Gierak.

But he’s not convinced by Wayve’s total commitment to deep learning. Instead of one large model, Ghost trains several hundred smaller models, each with a specialty. It then passes simple rules that tell the self-driving system which models to use in which situations. (Ghost’s approach is similar to that taken by another Israel-based AV2.0 company, Autobrains. But Autobrains uses yet another layer of neural networks to learn the rules.)

According to Volkmar Uhlig, co-founder and CTO of Ghost, dividing AI into smaller pieces, each with specific functions, makes it easier to establish that an autonomous vehicle is safe. “At some point, something will happen,” he said. “And a judge will ask you to point to the code that says, ‘If there’s a person in front of you, you have to brake.’ That piece of code has to exist. The code can still be learned, but in a large model like Wayve’s, it would be hard to find, Uhlig says.

Yet the two companies pursue complementary goals: Ghost wants to make consumer vehicles capable of driving on the highways; Wayve wants to be the first company to put driverless cars in 100 cities. Wayve is now working with UK grocery giants Asda and Ocado, collecting data from their urban delivery vehicles.

Yet in many ways both companies are far behind the market leaders. Cruise and Waymo have clocked up hundreds of hours of human-free driving in their cars and already offer robotaxi services to the public in a small number of locations.

“I don’t want to diminish the magnitude of the challenge ahead of us,” Hawke said. “The audiovisual industry teaches you humility.”

Source link


Comments are closed.