Re:Alphabet’s Waymo Cuts Cost of Key Self-Driving Sensor by 90%
by sjwright on Sunday January 08, 2017 @11:43PM
(#13354070)
You seriously think driving through one Taco Bell in a mule at low speed is even remotely comparable to driving real streets at real speeds for extended distances with 100% final production hardware?
[ Parent
| on HN ]
Re:Alphabet’s Waymo Cuts Cost of Key Self-Driving Sensor by 90%
by stuckagain on Monday January 09, 2017 @02:04AM
(#13354575)
So you didn't watch the video, then.
Re:Alphabet’s Waymo Cuts Cost of Key Self-Driving Sensor by 90%
by sjwright on Monday January 09, 2017 @04:34AM
(#13355147)
Yes, I watched the video. And to jog my memory I just watched it again now. Excatly as I described earlier: "a hacked-together mule loaded up with a pile of sensors on a roof rack."
That video has exceptionally high production values indicative of a carefully stage-managed performance on near-empty streets with exotic hardware that's never going to be used in any consumer car. I don't mean to diminish Google's achievement, but it's hardly the same as actually shipping hardware to customers.
Re:Alphabet’s Waymo Cuts Cost of Key Self-Driving Sensor by 90%
by Fricken on Monday January 09, 2017 @07:53AM
(#13355973)
I do not believe that Google was being disingenuous with their blind driver goes to taco bell video. But that's besides the point, demo videos don't mean shit. Getting a car to noodle around the neighbourhood under supervised conditions is a far cry from having a vehicle that can do that reliably all the time.
Waymo is down to 1 emergency disengage for every 5000 miles of driving, and that's a far more suitable metric for progress.