Humans and Control System Models need feedback to operate, and worse still... when any input into the vehicle's controls produce zero results, you will spin out.
My concern with a model in these conditions is that it wouldn't recoginize the fact that other cars were in the ditch and that it should probably slow down
The main limitation is still sensors in the snow, but it seems to not be that big of a deal to build sensor packages that are better at seeing in the snow than a human is.
Being able to plot a series of inputs that can more efficiently use available traction than a human doesn't prevent you from blundering your way into a dumb situation where the laws of physics dictate that the only possible outcomes are various flavors of bad ones.
It's not clear how often the software will chose poorly and need to brute force its way out with traction/handling. The fact that they seem to be hedging against this by putting the hardware on particularly performant cars indicates it must happen enough to matter or be rare but bad enough to matter when it does happen.
Waymo will probably also rack up a ton of technically not at fault accidents by being obtuse in traffic since there's when there's snow there's a lot less margin for the "two people trying to pass each other in a hallway" type missteps that behavior tends to create.
No, this is not a "works in a textbook" take. The path planner is aware of surface conditions on the road. This is already a big deal because otherwise the AV would not be safe to operate in the rain.
Waymo will not be touched in most of those accidents. I've been driving in snow long enough to know that there are always going to be idiots who drive too fast for conditions and lose control of their car; I'm sure some of them will blame Waymo because it's nearby. I once watched a guy with a TX license plate spin out on a perfectly empty, perfectly straight freeway. Waymo doesn't really need to do anything for human drivers to crash.
You couldn't see anything. As soon as there wasn't a car 20 yards in front of you, it was a complete whiteout. Ice built up on the wiper as quickly as you could possibly reach out of your window and clear it. Radar would probably be nice, but I don't think it'd be enough to keep driving. The cameras and lidar would be an absolute wreck.
I'm sure we'll get there eventually, but that is really the final frontier for AI driving I think. Waymos aren't even allowed to drive in a snowstorm right now. I suspect that you'll be dealing with Caltrans closing the pass for the rest of your life.
Disclosure: My grad student advisor.
Even if you also have good winter tires on, if your level of "caution" could be best measured as normal to high, sometimes it's a judgment call on when you want to pull off to the shoulder for 45 seconds to let a bunch of vehicles behind you pass. I'm not sure this is something any automated driver has been configured for. Or just generally to deal with driving when the road condition could best be described as "two only partially visible ruts in the snow where the tires of previous vehicles have driven, with snow in the centre".
Same thing in somewhere with a climate like upper Michigan or in Maine.
I love Waymo in other cities, but it'd be especially helpful here during the 1 day every other year that we actually get any snow ... if we ever get snow here again.