Waymo One is now open to everyone in San Francisco

Waymo and similar companies all use HD Mapping. Ignoring the specifics, it can be thought of as a centimeter-level perfect reconstruction of the environment, including additional metadata such as slopes, exact lane positions, road markings, barriers, traffic signs, and much more.

HD Mapping is great when it's accurate and available. But it requires a ton of data and constant updating, or the car will get "lost," and realistically will never be implemented in general, at best in certain cities.

Reliance on HD Mapping gets you to "robotaxis" quicker and easier, but it doesn't and likely cannot scale.

It remains to be seen if Tesla can generalize FSD enough to reach the same level as HD Mapping everywhere. Still, they have shown that the current limiting factor is not what the car sees or knows but what it does with that information. It is unclear how or why HD mapping would help them at that point.

Eh, I'd say we're a decade out from an L5 vehicle. It'll officially be L4, on road only. But that matches a good fraction of American drivers' capabilities.

Waymo has shown they can make robotaxis work, but the big catch so far is that it takes them a long time to open in a new city. They have several phases before they open fully, from what I've seen it seems to be: safety driver no passenger testing, safety drivers with employee passengers, driverless with employee passengers, limited rollout to paid passengers under NDA, wider rollout but with waitlist, and finally getting rid of the waitlist.

This means that hitting even all the major metro areas in just the US is going to take them a long time, let alone the rest of the world (or at least developed world). That does give Tesla some time to potentially catch up, since they don't seem to be bounded by geography in the same way.

Now, that said, I personally don't think Tesla's strategy is workable except maybe the very long term. Doing this with only vision seems like taking something that was already enormously challenging and making it nearly impossible instead. Their slow progress and inability to get their cars to avoid even basic errors frequently, despite near a decade of development now, I think points to this strategy just being bad.

If you can make the unit economics work for a large quantity of individual cars, mapping is a small fixed cost.

I agree that it's not economical to map every city and road in the US, since you need to generate revenue from every mapped road and city. So you can think of HD maps as amounting to building roads. They will be built in lucrative places. Cruise and Waymo won't make money from putting taxis in nowhere Arkansas, so they don't need to map it.

> the current limiting factor is not what the car sees or knows but what it does with that information. It is unclear how or why HD mapping would help them at that point.

That's simply untrue. All the hard stuff continues to be reliability and sensor gated. Cruise and Waymo have amazing sensors and even they struggle with sensor range, sensor reliability, model performance on tail cases, etc. For example, at night these cars typically do not have IR or Thermal sensing. They are relying on the limited dynamic range of their cameras + active illumination + hoping laser gets enough points / your object is reflective enough. Laser perception also hits limits when lasers shine on small objects (think: skinny railroad arm). Cars also have limits with regard to interpreting written signs, which is a big part of driving.

Occlusions are still public enemy #1. Waymo killed a dog. Cruise crashed into a fire truck coming out of a blind intersection even though their sensors saw the truck within 100ms.

LiDAR and HD mapping together are supremely useful, even if you don't drive with it, for enabling you to simulate accurately. You cannot simulate reliably while guessing at distances and locations. HD maps let you use visual odometry to localize, and distance measurements grounded in physics backstop the realism of your simulation at least in terms of the world's shape.

Tesla lacks the ability to resim counterfactuals with confidence since they don't have HD ground truth. There are believers at the company that maybe you could make "good enough" ground truth from imagery alone but that in and of itself is a huge risk, and it's what skipping steps looks like. Most in the industry agree that barring a major change in strategy they just have no way to regression test their software to the level of reliability required for L4 / no human supervision.