New GM Cruise Self-Driving Video Shows More Mastery of SF Roads

Re:New GM Cruise Self-Driving Video Shows More Mastery of SF... by jrlocke on Wednesday February 08, 2017 @05:05PM (#13602619)

The system is likely capable of distinguishing a lit green light from a sign painted like one. If you're simply asking "would the system be fooled if someone nefariously hung an always green light where a red one should be" surely that is a circumstance that would fool a human as well.

[ Parent | on HN ]

Re:New GM Cruise Self-Driving Video Shows More Mastery of SF... by semi-extrinsic on Wednesday February 08, 2017 @06:08PM (#13603077)

I'm not convinced it would distinguish the two.

Perhaps the most concerning thing is that someone could create a nefarious image that's not obviously nefarious to humans. I mean, we've all seen the very slight adjustments required to trick state-of-the-art image classification systems into thinking a cat is really a crocodile.

[ Parent | on HN ]

Re:New GM Cruise Self-Driving Video Shows More Mastery of SF... by zardo on Wednesday February 08, 2017 @05:12PM (#13602678)

>The system is likely capable of distinguishing a lit green light from a sign painted like one.

I doubt it. It's not even clear that it shouldn't treat a painted green dot like a green light.

[ Parent | on HN ]