The future of automobile autonomy isn't going to involve cars covered in cameras and radar and lasers. It's going to be all invisible, and CMU is already there.
The 2011 Cadillac SRX in the picture above is an autonomous car. Carnegie Mellon University had it drive itself 33 miles last week on public roads, from from Cranberry, Pa. to Pittsburgh International Airport. At first glance, you probably wouldn't be able to tell that the car is self-driving, because self-driving cars looked like this just five years ago:
That's CMU's BOSS competing in the DARPA Urban Challenge in 2007, with who knows how many sensors mounted all over it. And even Google's autonomous cars have that signature Velodyne LIDAR mounted on top of them:
By contrast, CMU's SRX relies entirely on automotive-grade radars, lidars, and cameras. You can see them if you look closely in the picture at the top of this article (there's one above the windshield, for example), but you do have to look closely. Inside, there are some extra buttons and screens, but all of the computers are stuffed under the floor in the trunk. And despite the lack of giant and complicated and expensive sensor systems, the car is still able to achieve the level of autonomy that we all want it to, as CMU's Raj Rajkumar explains:
"This car is the holy grail of autonomous driving because it can do it all — from changing lanes on highways, driving in congested suburban traffic and navigating traffic lights."
In addition to controlling the steering, speed and braking, the autonomous systems also detect and avoid obstacles in the road, including traffic cones and barrels, as well as pedestrians and bicyclists, pausing until they are safely out of the way. The systems provide audible warnings of obstacles and communicate vehicle status to its passengers using a human-like voice.
It's unfortunate that while the technology for all of this is arguably mostly ready, society (socially and legally) just isn't yet. You can buy cars with adaptive cruise control and lane departure warnings, which could hypothetically let the car drive itself, at least under some specific circumstances. And despite the fact that even a bad autonomous (or semi-autonomous) car would still save lives overall, there's no legal infrastructure in place to make it possible for manufacturers to implement such technology without undue risk of being sued into oblivion the first time something goes wrong.
Via [ CMU ]
Evan Ackerman is a senior editor at IEEE Spectrum. Since 2007, he has written over 6,000 articles on robotics and technology. He has a degree in Martian geology and is excellent at playing bagpipes.