Replaying real life: how the Waymo Driver avoids fatal human crashes
1–10 of 182 posts
Re: Replaying real life: how the Waymo Driver avoids fatal human crashes
#2What do you call that when you subconsciously suppress any tests or scenarios you know will break your code? Like you notice somethings kinda racey but it involves other components you don't control and so you don't do the parallel tests you probably should, that kinda thing.
Because that is exactly the bad feeling I get with Waymo never actually testing anywhere that doesn't have mm-precise maps and the all important California weather. There seems to be this implicit understanding that when you drop the thing in light snow it will just careen off the side and nobody is particularly incentivized to find that yep, that is exactly what happens.
(Even in these simulated scenarios here, you got what looks like a barren wasteland and exactly two cars)
Re: Replaying real life: how the Waymo Driver avoids fatal human crashes
#3Figure 3 has the responder slowing unusually soon. Makes me wonder if their model is overly fit to the sample. Still, if it's genuinely that good at responding and mitigating then the future looks bright.
Re: Replaying real life: how the Waymo Driver avoids fatal human crashes
#4What do you call that when you subconsciously suppress any tests or scenarios you know will break your code? Like you notice somethings kinda racey but it involves other components you don't control and so you don't do the parallel tests you probably should, that kinda thing. Because that is exactly the bad feeling I get with Waymo never actually testing anywhere that doesn't have mm-precise maps and the all importan…
Waymo is opening testing in Ohio right now, so it’s going to deal with terrible weather soon enough. https://www.limaohio.com/news/438416/waymo-to-open-ohio-test...
Re: Replaying real life: how the Waymo Driver avoids fatal human crashes
#5What do you call that when you subconsciously suppress any tests or scenarios you know will break your code? Like you notice somethings kinda racey but it involves other components you don't control and so you don't do the parallel tests you probably should, that kinda thing. Because that is exactly the bad feeling I get with Waymo never actually testing anywhere that doesn't have mm-precise maps and the all importan…
Well, devil's advocate here, but teaching a car to drive in good weather is hard enough, and has lots of applications! It doesn't seem totally unreasonable to focus on that first?
Re: Replaying real life: how the Waymo Driver avoids fatal human crashes
#6What do you call that when you subconsciously suppress any tests or scenarios you know will break your code? Like you notice somethings kinda racey but it involves other components you don't control and so you don't do the parallel tests you probably should, that kinda thing. Because that is exactly the bad feeling I get with Waymo never actually testing anywhere that doesn't have mm-precise maps and the all importan…
They have been testing in snow in Michigan, rain in Washington and a bunch of other places. You just don’t see it because they’re not operating a commercial service there yet.
Arizona is where bulk of their operations is currently and where they offer a commercial service, so it makes sense for them to focus on that area in their safety reports.
Re: Replaying real life: how the Waymo Driver avoids fatal human crashes
#7Why limit simulations to fatal crashes instead of all reported crashes?
Re: Replaying real life: how the Waymo Driver avoids fatal human crashes
#8What do you call that when you subconsciously suppress any tests or scenarios you know will break your code? Like you notice somethings kinda racey but it involves other components you don't control and so you don't do the parallel tests you probably should, that kinda thing. Because that is exactly the bad feeling I get with Waymo never actually testing anywhere that doesn't have mm-precise maps and the all importan…
Of course they're incentivized to test and implement for other areas. Their system will be worth astronomically more if it works everywhere and if it requires less precise mapping. Why would you assume otherwise? Also, small thing but it's AZ weather, not CA.
Re: Replaying real life: how the Waymo Driver avoids fatal human crashes
#9What do you call that when you subconsciously suppress any tests or scenarios you know will break your code? Like you notice somethings kinda racey but it involves other components you don't control and so you don't do the parallel tests you probably should, that kinda thing. Because that is exactly the bad feeling I get with Waymo never actually testing anywhere that doesn't have mm-precise maps and the all importan…
Well, devil's advocate here, but teaching a car to drive in good weather is hard enough, and has lots of applications! It doesn't seem totally unreasonable to focus on that first?
Yes, if basing your entire model on visible road markings that is broken by a light coating of crystallized water.
Re: Replaying real life: how the Waymo Driver avoids fatal human crashes
#10What do you call that when you subconsciously suppress any tests or scenarios you know will break your code? Like you notice somethings kinda racey but it involves other components you don't control and so you don't do the parallel tests you probably should, that kinda thing. Because that is exactly the bad feeling I get with Waymo never actually testing anywhere that doesn't have mm-precise maps and the all importan…
So long as they are intentionally constraining themselves to well mapped places with good weather, what's the problem? Summer tires don't work in the snow either, but that's fine because they aren't expected to.