(TNS) — The CEO of Pittsburgh-based Argo AI, Ford's ticket to the race to develop self-driving cars, gave a peek inside the quiet artificial intelligence startup in a recent interview.
CEO Bryan Salesky is a University of Pittsburgh graduate who went on to work at Carnegie Mellon University's National Robotics Engineering Center. He was a part of the 2007 DARPA Urban Challenge-winning team and later went to work for Google's self-driving car project. He told the tech website The Verge that Ford already had a start on autonomous vehicles when it announced it was pumping $1 billion into the newly formed startup.
"There was nothing that Ford was doing that was inherently wrong or busted. They were pursuing one method and we were like, 'Hey there are a bunch of methods we can pursue and all combine to solve this problem robustly,'" Salesky told The Verge in an interview.
Ford announced in February it would invest $1 billion over five years in Argo , which Salesky had just formed with Peter Rander, a top engineer from Uber's Advanced Technology Group in Pittsburgh, to help the company produce self-driving cars by 2021. Argo based its headquarters in Pittsburgh's Strip District and will have offices in Mountain View, Calif., and Dearborn, Mich. Argo has been quiet since the February announcement. The Verge interviewed Salesky in San Francisco.
"Argo won the lottery, essentially. (Its website is still laughably sparse.) What remains to be seen is if Ford made a wise roll of the dice. Much of exactly what Argo is doing remains unknown," Kirsten Korosec wrote for The Verge.
Salesky did illuminate how Argo will use artificial intelligence. Salesky said perception is "the stickier problem" for self-driving cars because it's not enough for the car to see a car, person or bike, the car must be able to predict what that thing will do and plan accordingly.
According to The Verge:
There are two schools of thought on how to solve these problems. Startups like Drive.ai and tech giant Nvidia argue that deep neural networks — a sophisticated form of artificial intelligence algorithms that allow a computer to learn by using a series of connected networks to identify patterns in data — can be applied to everything the self-driving car does from recognizing objects to making decisions.
Proponents of deep learning say these algorithms most closely mimic how the human brain learns. But Salesky contends deep learning requires more research and computing power for it to be used in autonomous vehicles in the near term.
The other approach — and the one Argo is taking — is to train these deep nets to solve very specific problems and then surround that with machine learning algorithms that tie into the broader system.
Machine learning is a form of artificial intelligence that uses algorithms to identify and analyze patterns in data, learn from it, and then make predictions. For instance, machine learning algorithms are used to take data from cameras or lidar to teach the vehicle how to recognize a stop sign or moving car.
The Pittsburgh Business Times reported that Argo is testing Ford Fusion hybrids on Pittsburgh's streets. The cars are collecting data and being driven by a person.
©2017 The Pittsburgh Tribune-Review (Greensburg, Pa.) Distributed by Tribune Content Agency, LLC.