I think the Rivian approach is the best. They're basically copying the Tesla model of having their fleet send the sensor recordings back and then using them as training data. While they're far behind right now, they'll catch up quickly, as they can copy a lot of the basic technology that's now established instead of having to invent everything from scratch and make wrong decisions along the way. The difference is Rivian is including lidar, so they just include the matched video and lidar recordings as a larger training data set. I'm convinced that if the price of lidar was more like it is today back when Tesla started selling FSD in 2016, then that's exactly what Tesla would have done, but Tesla is now stuck with their solution with ten million cars already on the road.

But in clear weather conditions, I don't think lidar really helps that much. Most human accidents would be avoided if drivers had better situational awareness and didn't have gaps in paying attention, and the cameras solve that.

...coding models? Are they comparable to the expensive ones?

I want a refund on my See Instant Crater event tickets! They costed me half a bitcoin, dammit!

Musk: "Stupid woke moon, eh, should be locked up or given correctional therapy to, eh, put it into a business-friendly orbit. It's in a socialist orbit right now. Put the socialists in orbit instead, heh heh heh."

Snow, rain, fog, changes in roads, construction, flooding.

Humans fuck those up also. It's just that traffic fortunately tends to be light during bad weather so that our screwups have limited impact. During the last heavy rain I drove in at night I probably made 10+ traffic violations because I couldn't see the damned lines. Fortunately there weren't a lot of other cars around to be co-confused with: the wise stayed home.

And if there is traffic in bad weather, such as work commutes, one just typically follows the person in front of them. If they by chance drove off a cliff I'd probably follow them down. So we have rules-of-thumb that mostly save us, but are highly imperfect.

I believe the goal has to be "better than humans" because humans seem to have a double standard for bots per screwups. Bots F-ing up spread like wildfire on social media.

Maybe we are collectively bigoted against automation, but being bots probably won't lobby to correct that or fight for their (alleged) rights, that's probably the way it will stay (at least until true sentience). Thus, I agree with the premise the driving system must be better than a human driver to be accepted.

In the worst case, they'll add interior walls (and maybe add some windows to the exterior walls), and resell it as office space, residential space, factory space, retail distribution space, or even a community library. After all, floors built to support racks of equipment should handle the weight and distribution of stacks of books without breaking a sweat.

So the construction might be overkill for what they eventually get used for, but it's not like a newly built, solid building isn't going to find a use. Maybe a quarter of the effort is wasted? Just guessing.

We don't even have a permanent colony on Antarctica, just scientific expeditions manned part-time.

To be a multi-planet species, we would need at least one permanent colony on a second planet (Mars, presumably).

Mars is a LOT harder than Antarctica.

I would say the non-litterer is preferable to the person who even litters on the moon.

It's the same reasons that CEOs who wreck multiple companies one after the other seem top find a golden parachute and a new job waiting for them.

Reminds me of the Robot Operating System https://www.ros.org/

It's really a bunch of utilities that let you route sensor data through pipes and sockets.

Just wait until they get that massive ticket for littering...

then it's considered beatified behavior.

Direct result of letting AT&T buy them.

T-Mobile is on one hell of a downward spiral. It's actually impressive.