Driverless cars just got a whole lot harder. This technical paper by @amirrosenfeld raises some profound questions about the robustness of #DeepLearning as a perceptual mechanism. https://arxiv.org/abs/1808.03305
-
Correct if I am wrong, but most advanced systems currently use three types of sensors: cameras, radars, and lidars.
-
-
Right, I am just noting that lidars+vision are still not enough (although Tesla does have radars, but no lidars, which are too expensive and seem to have poor longevity).
-
But Teslas have an unexplained attraction to the backs of firetrucks... I wonder if their AI is trying to tell us something...
- 3 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.