Google, who's just down the road
from Stanford, seems to understand this, and they've turned their
autonomous cars up to "aggressive" in this driving demo that they gave
to some lucky sods in a parking lot at the TED conference in Long Beach.
It's pretty impressive: This might seem dangerous, but arguably, this
demo is likely safer than a human driving around the parking area at
normal speeds, if we assume that the car's sensors are all switched on
and it's not just playing back a preset path. The fact is that a car
equipped with radar and LIDAR and such can take in much more
information, process it much more quickly and reliably, make a correct
decision about a complex situation, and then implement that decision far
better than a human can.
This is especially true if we
consider the type of research that is being done with Shelley to teach
cars how to make extreme maneuvers, safely. So why aren't we all driving
autonomous cars already? It's not a technical ; there are several cars
on the road right now with lane sensing, blind spot detection and
adaptive cruise control, which could be combined to allow for autonomous
highway driving. Largely, the reasons seem to be legal: there's no real
framework or precedent for yielding control of a vehicle to an
autonomous system, and nobody knows exactly who to blame or sue if
something goes wrong.
And furthermore, the first
time something does go wrong, it's going to be like a baseball bat to
the face of the entire robotics industry. Anyway, enough of the
depressing stuff, here's an outside view of Google's robot car squealing
around that parking lot: For what it's worth, "aggressive" is
apparently one of four different driving personalities that you have the
option of choosing from every time to start up one of their robot cars.
