Re:Self-Driving Cars Have a Bicycle Problem
by Eridrus on Sunday February 26, 2017 @02:48PM
(#13739373)
Why do you think that video shows that Tesla isn't reliant on neural networks? Neural nets outputting bounding boxes is pretty normal.
Despite NVIDIA's papers, end-to-end neural nets for self-driving cars are dumb, but for the initial perception based on sensor data, neural nets are the only game in town.
I was looking at the optical flow indicators and the road-tracking. Afaik any NN solution to those are immature if they work reliably at all. Your probably right that that the bounding boxes are probably NNs.
Re:Self-Driving Cars Have a Bicycle Problem
by mathattack on Sunday February 26, 2017 @11:57AM
(#13738191)
There's a saying that neural networks are the second-best way to do everything. Don't be disappointed when their trajectory flattens out.
Outstanding quote! I'm going to reapply it.
And, as for their role in autonomous vehicles, I don't think they play a primary role (although I don't design autonomous cars so I wouldn't know for sure.) You can see in this Tesla video that a lot of the computer vision isn't even reliant on neural networks: https://www.youtube.com/watch?v=BLlwm5Dq7Is