Hacker News Reader

Comment by modeless | Hacker News Reader

They just announced 500k driverless miles in Phoenix. Over several years that sounds laughably small to me. For comparison, motor vehicle fatalities in the US are around 1.5 per 100 million miles. We're several orders of magnitude away from even being able to convincingly demonstrate that these reduce (or at least do not increase) fatalities in the real world.

I'm glad that Cruise beat Waymo to driverless in SF because they are providing the swift kick in the butt that Waymo seems to require to actually make progress in a reasonable amount of time.

View on HN

>500k driverless miles in Phoenix

Waymo has 20 million miles IRL driverless, and 15 billion miles in simulated driving.

Fatalaties are not the only metric. Accidents are much more frequent and driverless cars have already proven they're safer in that regard.

Fatalities are the metric Waymo uses every time they give a presentation. They always start off by telling us how many people die on the roads and how they can help. And it's true! I think it's a very important metric and they are right to focus on it.

Simulated miles are not convincing. Miles with a safety driver are better but still ultimately different. Also the type of miles matters too, and Waymo has been focusing on the easiest miles possible until Cruise forced them to up their game and try something a little more valuable.

>Fatalities are the metric Waymo uses every time they give a presentation.

Source? Because since 2020 Waymo has been primarily touting their "contact events" metric, which is what most people consider to be accidents.

Simulated miles are still better than no miles. Given the better accident rate it seems to contribute to a degree.

The point is that it's an argument from ignorance to narrowly focus on one metric and say we don't have enough information on whether autonomous vehicles are safe. We do have a range of metrics and information already that point to them being safer.

> Simulated miles are still better than no miles.

Provided your starting point is AV software with some ability to drive, this isn't necessarily true. Tuning on simulated miles can lead towards over-optimization for the conditions of the simulation.

https://youtu.be/qJiFKxvJlhY?t=66

https://youtu.be/gW6Wt2WQotY?t=232

https://youtu.be/o8rCOKSDMcg?t=60

There are countless other examples. It's one of the first things they bring up in almost every presentation to the general public. It's how they present themselves to the world, as the answer to traffic fatalities.

You may think it "ignorant" but the fact is that fatalities are going to be the single most important metric that the public and journalists and governments are going to focus on, and that's why it matters. The first few driverless car fatalities are going to be a huge, huge deal and are likely to result in action from all three branches of government. There will be court cases, there will be regulatory action, and there will be a lot of noise from politicians about laws and maybe even some laws passed about it. The first one already forced Uber out of the game.

> They just announced 500k driverless miles in Phoenix.

Not with one version of the software. They are cheating: they should reset the mileage whenever they update the software.

500K miles does not tell much. It depends on how well those miles cover all possible (observed / not observed) edge cases, i.e. the famous long tail.

Motorbike riders:

Rider 1: I have 20 years experience riding a motorbike.

Rider 2: 20 years experience or 1 years "experience" repeated 20 times?

Tesla's FSD traveled billions of miles (2 years ago they had over 3 billion miles).

Their crash rate is 1 in 4.4 billion miles. That's crash, not a fatality. And it's getting better.

https://cleantechnica.com/2021/12/07/tesla-1-crash-per-4-41-...

yeah because every time it's about to crash it slags it off onto the driver

Your link says Autopilot, not FSD. Autopilot is highway autonomy, which is vastly easier and you can rack up many more miles very quickly. This is not at all a relevant comparison.

Any Google search on this shows your stats are wildly incorrect.

Reply on news.ycombinator.com