The company’s tech is apparently based around fully autonomous, exit-to-exit commercial truck transportation on freeways — with the idea apparently being that this is where self-driving tech stands to be the most useful, and also the most effective. Human drivers handle all of the city driving, but have free time in between city stops to rest, and therefore to increase transportation/shipping efficiency — with such a system, drivers could be on the road for very long shifts. It would seem so anyways.
The CEO and co-founder of Embark, Alex Rodrigues, commented: “Embark’s truck uses a combination of radars, cameras and LiDARs to perceive the world around it. The millions of data points from these sensors are processed using a form of Artificial Intelligence known as Deep Neural Nets (or DNNs) that allow the truck to learn from its own experience.” Note that Tesla uses essentially the same approach.
“Analyzing terabyte upon terabyte of real-world data, Embark’s DNNs have learned how to see through glare, fog, and darkness on their own. We’ve programmed them with a set of rules to help safely navigate most situations, how to safely learn from the unexpected, and how to apply that experience to new situations going forward.”
Notably, the startup is currently home to employees who previously worked at SpaceX, Audi’s self-driving vehicle program, and Stanford AI. Maven Ventures is currently the primary backer.