Tagged With nvidia drive px2

When I was a kid, self-driving cars were the sci-fi future. They were the stuff of Isaac Asimov's Sally and the Johnny Cab from Total Recall. I didn't actually think that they'd ever happen -- the concept itself was a long way from reality, a lot more fi than sci. But smarter brains than mine, with the help of some surprisingly old-school tech, have built cars that can drive on everyday roads.

I took a short trip in one, and it was normal. Normal to the point of being bland -- which is what you want from a self-driving car.

Video: I don't think anyone would argue that artificial intelligence in any of its current forms is past infancy, meaning that humans are still smarter. For now. But this car, with no driver inside, pays attention to every other meatbag-filled car on the road -- and learns from them.

Predicting the future is near impossible -- but that doesn‘t stop us all from having a red hot go. Human beings have been predicting the future since the beginning of history and the results range from the hilarious to the downright uncanny.

One thing all future predictions have in common: they‘re rooted in our current understanding of how the world works. It‘s difficult to escape that mindset. We have no idea how technology will evolve, so our ideas are connected to the technology of today.

Driverless cars are very cool, but the technology that enables their self-driving smarts requires a novel mix of raw computational and deep learning power, using both general-purpose CPUs and GPUs to crunch real-time data and match it to a massive catalogue of imagery and vehicle profiles. A brand new Nvidia processor, the company says, has the power to finally make it happen.