I hope this prods Tesla to up their game. I love my Teslas but if Waymo’s approach is shown to be truly better then I’d happily switch to a car that used their tech. For now I have no choice but to stick with the self-driving that’s available for personal cars. Hopefully Waymo works on licensing their tech for other manufacturers and expanding their geographical coverage.
Tesla’s approach is smarter than Waymo. Maybe Tesla won’t win, perhaps a Chinese firm, but the winner will follow a vision based system and not a micro-mapping LIDAR system.
“Vision is all you need.”
Any evidence for this claim?
I don’t think you need evidence to understand it. I’d recommend listening to Andrej Karpathy talk about it.
But I note that human drivers do not rely on LIDAR or radar or a high res map of the road.
Human drivers don't use fixed cameras. For one thing, they can move their heads.
Fun fact, people can see light polarization.
https://pmc.ncbi.nlm.nih.gov/articles/PMC4528539/
> But I note that human drivers do not rely on LIDAR or radar or a high res map of the road.
Human drivers also have a brain that computers have struggled to replicate for decades.
Also, many of the Chinese vehicle makers already include LIDARs in their vehicles for their current ADAS
Humans are not capable of safely operating motor vehicles. For a combination of practical and psychological reasons, we accept them as safe enough, stuffing the tens of thousands of Americans who get mowed down each year into the backs of our heads. But we know what the genuinely safe version of human-operated vehicles looks like, because we do it for planes, and it involves quite a lot of complex instruments other than the human eyeball.
It would be an absolute catastrophe for the developers of autonomous vehicles to decide there's no need to do better than human drivers.