Comment by cronix | Hacker News Reader

Comment by cronix | Hacker News Reader

I think the whole dream/goal of building a self driving car on top of a system completely designed for manual human interpretation and input is asinine, and that's before you even consider the complexity of adding other humans manually driving or suddenly walking in front of your car from a blind spot. Instead of building a digital system from the ground up, we are forcing manufacturers to come up with tech to read speed signs meant for human eyes and accurately interpret them under a myriad of conditions. What if it's covered in mud, or snow? Wouldn't coming up with national/international standards and a digital system work better for digital cars, like broadcasting speed limits instead of only relying on interpreting visual inputs, etc? Or standardizing the charging interface so you don't end up in a mac-like dongle hell and can just know no matter what car charging station you pull up to it will just work, like gas stations and standardized fueling systems work for all brand of ICE vehicles? I can go to any branded gas station and there isn't a station specific for just Ford cars. It just seems like a mish mash system of cludges hobbled together instead of a solid, well thought out system from the ground up. Due to that, we are making it 10x harder (and more dangerous) than it really needs to be. It's like saying you have to build all modern OS's on top of DOS made for 8 bit cpu's.

>> What if it's covered in mud, or snow?

That's the entire problem. These systems don't understand anything about the world. If you see a sign covered in snow you're going to recognize it as such and make your best guess as to what it says and weather you care. You probably don't need that information to drive safely because you have a lot of knowledge to fall back on. These things dont, so some folks want to improve GPS accuracy and maps and signage. That's not a viable solution on so many levels.

General AI is the only way forward for fully autonomous cars.

Right now, the TSLAs with FSD will disable it in snow+rain, so I assume that even if TSLA achieves L4, it will be only under ideal conditions until they have enough data to resolve these edge cases.

>Right now, the TSLAs with FSD will disable it in snow+rain

What about that instant before it figures out it's bad enough weather to shut itself off? What is the threshold?

It seems like currently the minute it detects rain it shuts it down. (wipers are automatic also)

On the other hand, there are a lot of videos of FSD Beta on youtube that show the car driving into the sun where it's almost impossible for a human to see, but the cameras detect all of it.

Musk said after winter 2019 they would have all the data they need for all human drivable ice and snow conditions:

https://www.youtube.com/watch?v=Ucp0TTmvqOE

I keep seeing people incorrectly call less than perfect driving conditions "edge cases." That term refers to rare conditions. Rain, snow, pedestrians, and support pillars are not rare.

You're right, they are not really edge cases, but the original poster mentioned a sign covered in snow. In that case, a human would probably just do the same thing the TSLA would: blow the stop sign or continue at the current speed limit until they get pulled over.

> If you see a sign covered in snow you're going to recognize it as such and make your best guess as to what it says and weather you care.

The first winter after I got my license, I was driving around at night on a road I hadn't been to before.. kind of in the middle of nowhere, unpaved unlit back roads.

I saw a sign, partially covered in snow, and had a hard time making sense of it. Why this odd shaped sign in the middle of nowhere? I really wanted to figure it out and fixated on it a bit too much.. only right after making it past the sign, I realized it's warning about a tight bend in the road right ahead. Almost made it into the ditch. Thanks, sign, I would have seen the curve just fine if I had just focused on the road ahead.

Agree with your points but one thing to note, electric car world has indeed settled on a universal fast charging standard. Its also just as ubiquitous, thankfully.

Every new EV from Rivian to GM to BMW uses the “Combined Charging System.” Tesla, chooses to continue to use their own proprietary design in the U.S. despite having CCS technology available. (and the implementation completed already - European Tesla models ship CCS - required by law.)

Tesla will sell you $10K beta software that wants to steer into pedestrians, that most choose to pay for because after delivery, the price doubles (so act fast!) Most who fork that kind of cash are not able to access all parts of this beta software, this software license cannot sold/transferred to the next owner regardless of what the maroney sticker says, but don’t worry, FSD is being launched next month.

If thats excusable, surely then everyone’s ok with vendor lock in for DC Fast charging unless one wants to shell out $450 for a slower “old school” Chademo adapter, the fact one cannot buy replacement parts for their car, and cannot repair their own vehicle.

Tesla - America’s Beta Test Success Story.

When your technology starts working only when the entire world changes dramatically, you probably don't have a great technology idea.

In particular, road maintenance is already expensive and often left to rot. Still, current driving is relatively robust - even if a few signs are damaged or go missing, no major issues will occur. Road signs keep working even during storms, even if there is no power, even if something has hacked national electronic systems, even if the GPS is not accessible.

Replacing all this with brittle, finicky, expensive, easy to attack en masse digital systems is not a great idea.

>When your technology starts working only when the entire world changes dramatically, you probably don't have a great technology idea.

Exactly! No wonder those pesky horseless carriages never caught on!

Cars had value without the need for major changes in the world. Road signs were codified and universally implemented only after cars proved their worth. Roads were not invented for cars, road-ready cars had existed for a good few thousand years before the first actual car.

Yeah, everyone remembers the famous 8 lane interstates built by the Romans, cutting through Europe, with gas stations every 16 miles. The only thing we needed to adapt were the road signs!

So you see no qualitative difference between a couple of horse carriage crossing the North American plains, and an Interstate system (that requires no stopping) with gas stations, motels, parking lots, malls, suburbs?

Have you looked at maps of cities with roads and parking lots? Cities in north America are literally built / rebuilt around cars, cities in Europe heavily modified.

Or, conversely, that means you find any advance towards autonomy in cars, in their current form, such as lane assistants, or working well in good weather on interstates, etc. is completely worthless?

There is a huge difference between a technology that is useful in the current world, as cars were at their inception, but can be significantly be improved by infrastructure; and a technology that requires a huge change in the world's infrastructure before it becomes useful.

That is, if autonomous cars can improve safety or convenience on current infrastructure, they will prevail, and new infrastructure will develop with them in mind. But if they are only useful after such changes, they will likely linger for decades before any adoption.

You did not answer: Do you find any advance towards autonomy in cars, in their current form, such as lane assistants, or working well in good weather on interstates, etc. is completely worthless?

Autonomy today is in the same situation that cars once were; even the current state of 'autonomy' has obvious advantages already and will only become more in the future.

Edit: How do you think cars were useful at their inception? Slow, with a range of a few miles, needed to be rebuilt every few miles, gas to be bought in pharmacies. Quite a bit had to change before cars became something practically useful beyond showing 'I am rich'.

> we are forcing manufacturers to come up with tech ...

No one is forcing manufacturers to do anything. They a perceive a business opportunity and take it.

Couldn’t agree more.

There are way too many edge cases in real world driving conditions because road traffic and signage changes from instant to instant.

As a driver I don’t know what’s round the next bend, could be road works or a vehicle collision.

There’s no technical reason a computer based driving system shouldn’t be more aware, it’s an implementation failure.

Reply on news.ycombinator.com