Welcome to Tesla Motors Club
Discuss Tesla's Model S, Model 3, Model X, Model Y, Cybertruck, Roadster and More.
Register

GM’s new Ultra Cruise: Hands-free driving on all paved roads in US/Canada

This site may earn commission on affiliate links.
How would you explain it to a non-techie? I’m open to sound explanations. I have a basic understanding of AI/NN.
And is there reason to believe Tesla will get there first? Is it the large amount of data the fleet is pumping out?
Apologies for my earlier response--upon rereading it read a little bit offensive.

Many of these things have been rehashed here and there, but there are a few reasons why GM's claim of having such functionality in 2 years is complete nonsense:

1. Supercruise requires intense 3D mapping of an entire route. Aside from the incredible cost and man-hour effort needed to 3D map and groom such vast expanses of roadway, there are also the issues of construction areas which dramatically change the roadway...anytime construction pops up (for example on an interstate where a lane is temporarily routed to an oncoming traffic lane), these areas need to be updated/maintained. Doing this for just interstates is already a costly and time-intensive task. Doing it for all paved roadways in just the U.S.? Extremely time-intensive, extremely expensive. What happens in the time after a construction project starts and GM comes out to map that section of the roadway? Do you think a construction project is going to wait for GM to come out and map their roadway changes?

2. Such a 3D map data for the US as described in (1) above would take a LOT of data. No way it can be stored onboard the vehicle. So it would have to be continually downloaded to the car as the vehicle drives around. The bandwidth needed to continually download such a high-definition map, and the cost, would be prohibitively expensive. Add this cost on top of an expensive sensor suite and lots of processing hardware. Are you ready to buy a $200,000 Chevy Impala?

3. No matter how many lidars, radars and HD radars you have in your system, you still need a fully-developed neural network for vision. Some examples why:
  1. Radar and lidar can't read signs. Yes, you could put all known signs in your mapping data. But signs change all the time. New stop signs get added and removed. Speed limits change. Detour signs get temporarily added for construction zones. New "No Turn on Red" signs get added/removed by municipalities all over the country. All Radar/Lidar sees is a flat metal plane. When a construction company puts up a detour sign, the vehicle MUST be able to read and interpret that sign with vision.

  2. Lidar and radar can't read stoplights, temporary lit signs (such as temporary speed zones/school zones...speed limit xxx when flashing, etc).

  3. Lidar and radar have limited ability to interpret hand signals or other visual cues, whereas vision has already demonstrated the ability to do this.
OK, so a vision-based neural network system is required. How do you develop it? You need several things to develop a good NN system:

a. Tons, and tons, and tons, and tons of data. How do you gather this data? GM does not have a connected fleet capable of sending images/video back to them for processing and inputting into a neural network. They have Cruise, but Cruise is a relatively small outfit and is only capable of collecting limited data in a very small geographic area.

b. The ability to cultivate the RIGHT kind of data. You can't just throw random data at it and expect it to get better. So you need to find data that addresses scenarios you're trying to solve. How does GM request specific examples of video/imagery from their fleet? They can't.

c. Tons of grooming. The data you feed into the network for training needs to be cultivated and tagged (automatically if possible for much higher productivity, as Tesla is developing with Dojo).

d. Tons of processing power to solve the NN iteratively. Does GM have supercomputers processing their networks, or an auto-labelling system like Tesla has been working on for years? Tesla has among the top 10 or 20 (depending on how you measure it) supercomputer clusters in the world. What have you heard about GM's supercomputer? (That's right, they don't have one).

There are more reasons, but this will give you a good start to be skeptical.

You are right in that Elon was overly-optimistic on the FSD timeline. I said in 2014 on this very forum (my initial post is still searchable) that it would probably take about 10 years to develop level 5 autonomy, which would bring us to 2024. Looks like my estimate is going to be maybe a year or two or three too soon, but in the ballpark.

So while you are correct that Elon thought FSD progress would be way faster than it has been, I think it's also fair to say that Tesla (and perhaps Mobileye--although their data engine is less capable) are the only people working on a true scalable system. I'm still confident Tesla will get there first, but it will take a few more years.
 
Last edited:
So will it be geofenced to particular roads? Paved road means a public or private improved street, highway, alley, public way, or easement that is covered by typical roadway materials including, but not limited to, asphalt paving or concrete.
Paved roadways fall into two categories, those surfaced with flexible pavement and those utilizing rigid pavement components. Flexible pavement roads include asphalt surfaced and/or chip seal surfaced roads
 
  • Informative
Reactions: lUtriaNt
The main reason I’m more willing to believe Barra or Waymo on FSD than Tesla is because Elon, for all his genius, is kind of crazy and doesn’t always think things through before making incredibly bold claims and commitments, which often don’t pan out. Barra on the other hand will get the boot if she gets it as wrong. GM can’t just announce such a major upcoming product without a clear roadmap for how they are going to get there. I mean the markets will slaughter them. They are answerable to investors whereas Elon seems to just do his own thing, SEC be damned! 🤣
Geniuses are often a bit eccentric. Elon is literally a rocket scientist. Have you heard him talk? He's not just a CEO...he knows intimate details of the science and physics that he works in, and uses first-principles thinking that has blown other seeming juggernauts out of the water. He started Paypal. He's the CEO of multiple massive companies changing the way the world works. Are you honestly comparing him unfavorably to Mary Barra as far as capability to get something done and move the needle is concerned? Barra, or any other automotive CEO, couldn't even keep up in a decent conversation with Musk. GM's Bolt was supposed to bury Tesla. In the end, every single one got recalled and ended up being one of the most expensive recalls in GMs history.

Lockheed Martin and Boeing? NASA itself? The European Space Agency? SpaceX has blown them ALL away in cost, capability, and timelines. Ask Jeff Bezos if he thinks Elon is a formidable business leader. The CEO of Amazon himself is getting his ass handed to him on a plate by SpaceX. SpaceX is the ONLY private company in the world that can take people to orbit. Even the U.S. government can't claim that capability anymore. SpaceX is the only company reusing orbital-class rockets--and they're doing it frequently. Tesla's EVs outperform all the other "big car company" offerings and at a far lower cost. Only Tesla has been agile enough to navigate the chip shortage by implementing their own custom chip software. VW, GM, et. all don't have that expertise.

I just can't for the life of me understand how you think Elon's claims don't pan out. Everyone knows they usually don't pan out in his given timeline, but they DO pan out...and at a lower cost and sooner than his competitors. You should read this book to get a better idea of how Elon's mind works and a better appreciation about why he is so successful.
 
GM promised and delivered with Super Cruise functionality and are testing Cruise autonomous ridesharing.

Of course time will tell what GM has on the market in 2022/23 and who gets to FSD first. The sooner it comes, the more lives we can save and more convenience/comfort we can provide to people.
That’s a curious way to phrase it.

Cruise could do super cruise when they bought Cruise. There was no “promise and deliver” of any sort. It was already done.

It’s actually revealing that years later they’ve made so little progress.
 
Not quite. Yes, Waymo and Cruise need cameras but Waymo and Cruise also use 360 lidar to detect, track and classify cars, pedestrians, cyclists etc... Lidar is used for a lot more than just localization on a HD map. They use lidar as a complement to camera vision because there are cases where lidar is better than cameras, for example, driving into the sun where cameras can get blinded or driving at night in pitch darkness where cameras may see poorly but in both these cases, lidar will still work great.

In the top part of the video, we see what the new Waymo lidar sees. We see that the Waymo lidar is able to see objects like cars and pedestrians with great accuracy even at night:


Note around the 1 mn mark, lidar sees an occluded worker who comes out from behind a parked car at night.
Sure adding Lidar for localization doesn't preclude using it for other purposes but I'm just saying that the localization requirements were the impetus to put Velodyne Lidar (a very esoteric sensor back in 2005) on the roof of cars in the DARPA Grand Challenge. It was the key addition that allowed them to win. There was just no other way to do it at the time. And Waymo and Cruise are both descendants of the same contest, in terms of the codebase, hardware setup, and people.
 
Geniuses are often a bit eccentric. Elon is literally a rocket scientist. Have you heard him talk? He's not just a CEO...he knows intimate details of the science and physics that he works in, and uses first-principles thinking that has blown other seeming juggernauts out of the water. He started Paypal. He's the CEO of multiple massive companies changing the way the world works. Are you honestly comparing him unfavorably to Mary Barra as far as capability to get something done and move the needle is concerned? Barra, or any other automotive CEO, couldn't even keep up in a decent conversation with Musk. GM's Bolt was supposed to bury Tesla. In the end, every single one got recalled and ended up being one of the most expensive recalls in GMs history.

Lockheed Martin and Boeing? NASA itself? The European Space Agency? SpaceX has blown them ALL away in cost, capability, and timelines. Ask Jeff Bezos if he thinks Elon is a formidable business leader. The CEO of Amazon himself is getting his ass handed to him on a plate by SpaceX. SpaceX is the ONLY private company in the world that can take people to orbit. Even the U.S. government can't claim that capability anymore. SpaceX is the only company reusing orbital-class rockets--and they're doing it frequently. Tesla's EVs outperform all the other "big car company" offerings and at a far lower cost. Only Tesla has been agile enough to navigate the chip shortage by implementing their own custom chip software. VW, GM, et. all don't have that expertise.

I just can't for the life of me understand how you think Elon's claims don't pan out. Everyone knows they usually don't pan out in his given timeline, but they DO pan out...and at a lower cost and sooner than his competitors. You should read this book to get a better idea of how Elon's mind works and a better appreciation about why he is so successful.
Elon can say things that totally correct and obvious, and then the next moment have some incredibly dumb take. Like his insistence that Tesla not have vision-based driver monitoring for years, like jerking on the steering wheel is somehow an acceptable solution.
 
  • Like
Reactions: stcptl
Geniuses are often a bit eccentric. Elon is literally a rocket scientist. Have you heard him talk? He's not just a CEO...he knows intimate details of the science and physics that he works in, and uses first-principles thinking that has blown other seeming juggernauts out of the water. He started Paypal. He's the CEO of multiple massive companies changing the way the world works. Are you honestly comparing him unfavorably to Mary Barra as far as capability to get something done and move the needle is concerned? Barra, or any other automotive CEO, couldn't even keep up in a decent conversation with Musk. GM's Bolt was supposed to bury Tesla. In the end, every single one got recalled and ended up being one of the most expensive recalls in GMs history.

Lockheed Martin and Boeing? NASA itself? The European Space Agency? SpaceX has blown them ALL away in cost, capability, and timelines. Ask Jeff Bezos if he thinks Elon is a formidable business leader. The CEO of Amazon himself is getting his ass handed to him on a plate by SpaceX. SpaceX is the ONLY private company in the world that can take people to orbit. Even the U.S. government can't claim that capability anymore. SpaceX is the only company reusing orbital-class rockets--and they're doing it frequently. Tesla's EVs outperform all the other "big car company" offerings and at a far lower cost. Only Tesla has been agile enough to navigate the chip shortage by implementing their own custom chip software. VW, GM, et. all don't have that expertise.

I just can't for the life of me understand how you think Elon's claims don't pan out. Everyone knows they usually don't pan out in his given timeline, but they DO pan out...and at a lower cost and sooner than his competitors. You should read this book to get a better idea of how Elon's mind works and a better appreciation about why he is so successful.

There is no doubt that Elon is one of the most consequential innovators of our time. No auto CEO even comes close. But often times he says/does things that are downright idiotic. And it’s not just his timelines, especially with regards to FSD. He’s had to walk back claims on hardware capability and update hardware so many times. And what’s with the Tesla robot? Is Tesla really going to pursue that? Otherwise what was the point of showing that? And he is Elon so he can get away with it. A traditional CEO such as Barra doesn’t have that luxury and would lose her job. So I’d be very surprised if they made such public commitments and claims without a clear path to getting there. Surely they aren’t pulling this out of thin air? Cuz 2023 isn’t far away. I’m not a techie so I’m making inferences based on things I do understand. Time will tell of course!
 
Just found this online on maps:

“GM relied on lidar-scanned high-definition maps for Super Cruise, but Ditman said it wasn’t practical to map all 2 million miles of road for Ultra Cruise. “We do rely on similar map data,” he said. “However, we have a larger number of sensors that also observe the roads so when we combine the map accuracy with what our sensors see of the road geometry and the road markings, we’re still able to accurately place ourselves and drive the right nominal path.”

So - it is going to be totally new autonomous driving - with entirely different maps ?

All in 2 years ?

I’m not a techie so I’m making inferences based on things I do understand.
That explains your confidence.

You are totally basing your confidence on one thing.

Barra on the other hand will get the boot if she gets it as wrong. GM can’t just announce such a major upcoming product without a clear roadmap for how they are going to get there. I mean the markets will slaughter them. They are answerable to investors whereas Elon seems to just do his own thing, SEC be damned!
Since you are not a techie, probably you understand this.

How many CEOs have promised stuff, haven't been able to deliver and yet went home with golden parachutes ? Do CEOs really care ? Every auto major in the world has had multiple CEOs in the time Tesla has had one CEO. Why do you think this happened ?

Industry is littered with a LOT of promise by every legacy auto maker that there would be self-driving cars in "5 years". You can go back and look at the statements through out 2010s - from Nissan to Toyota to Volvo to BMW to ... though, none of the CEOs lost their jobs because of this. They lost because they couldn't understand how the industry is changing. Berra is no different.
 
Last edited:
There is new HD radar now that has much higher resolution than normal radar. This new radar has high enough resolution that it can be used as a back up to vision in bad weather. In fact, Waymo recently published a blog on how they are using HD radar to help see in poor visibility like fog:


any word on relative cost compared to low-def radar?
 
I get the skepticism regarding GM given their track record. But at least they are trying. And competition probably will cause Tesla to speed up development of FSD. The only major issue that I can see with the Tesla approach is the lack of side facing cameras in each headlight. This hardware change should take care of ULTs and possibly also roundabouts.

The present version of FSD beta still makes dumb mistakes, but it's not that far away from a driver supervised approach that can basically go anywhere on paved roads in good weather.
 
And competition probably will cause Tesla to speed up development of FSD.
Not sure about that. There is a limit to what Tesla can do - it is limited by engineers (& compute). They are working on DoJo for the compute part - and had AI day to speed up recruitment. There simply aren't that many good AI engineers around for Tesla to be able to hire a lot of them quickly. If they could - they would have. Many companies have the policy of no head count limit per se - just a matter of finding the right talent.
 
Sure adding Lidar for localization doesn't preclude using it for other purposes but I'm just saying that the localization requirements were the impetus to put Velodyne Lidar (a very esoteric sensor back in 2005) on the roof of cars in the DARPA Grand Challenge. It was the key addition that allowed them to win. There was just no other way to do it at the time.
No object detection and avoidance was the primary job of Lidar in the Grand challenge. You are pushing misinformation.
And Waymo and Cruise are both descendants of the same contest, in terms of the codebase, hardware setup, and people.
There's no comparison between the tech stack of 2005 versus the tech stack of Cruise and Waymo. Stop spreading misinformation.
 
  • Like
Reactions: diplomat33
I’m looking at track record. GM promised Super Cruise, they delivered it works well in the limited settings it is allowed.
Seriously? It's a lane centering product shipping on a tiny list of models and geofenced to a subset of limited access highways. Tesla almost certainly has more FSD beta cars on the road right now than GM has super cruisers. The ONLY feature it has that vanilla lane assist doesn't is the "hands off" driver monitoring thing, but let's be honest: that's basically a gimick (and per some random youtube I saw, it barely works, you can fool it trivially). They're betting that their limited rollout will see no accidents before they can complete a more competetive offering.
 
So 2 millions miles. Is that all using HD maps ? If so - lets do some fun calculation.

How long does it take to create HD map of 1 mile ? You have to run the map-car slowly - say 25 mph ? Then, someone has to manually remove all the dynamic objects from the video/image. May be some of that is automated - still needs manual input. Essentially we are talking about "labeling" every 3-D image of that mile. Lets assume that is 1 person day per 1 mile.

So, we are talking about 2 Million hours of work to prepare HD maps for those many miles. If 1,000 people are doing the labeling - it would take them about 8 years to label 2 Million miles.

Its hilarious when Tesla fans who wholly believe that ML can solve the motherload of AI problem which is L5 self driving yet believe that mapping can't be solved/automated by ML.
(Hint its already been solved)

0DGJP3V.png


Well, currently Super Cruise probably don't even touch 0.1% of paved roads in US. So much easier to keep that up to date.

Realistically - there is no way to claim "all paved roads" and needing HD maps. Are they using just 2-D maps ?
Mobileye already has ~virtually all of US mapped. Again this has been repeated 1,000 times here.
It baffles me. Secondly these cars don't just stop working just because there's no HD map. They still use the sensors onboard to drive as GM mentioned.
The difference is that in L2 you don't need a MTBF of hundreds of thousands / millions of miles so you can drive on practically any road even if you don't have HD map because human is the backup.
 
  • Like
Reactions: stcptl
GM’s next version of Super Cruise to be called Ultra Cruise will allow HANDS FREE driving on all paved roads in US and Canada. Will debut on 2023 Cadillac models next year.

This is similar to Tesla’s FSD (but hands free) and is a game changer IMO as far as autonomous tech that’s available to retail consumers.

No surprise here as GM is known for leading the entire planet in transition to EVs. They did it again.
 
No object detection and avoidance was the primary job of Lidar in the Grand challenge. You are pushing misinformation.

Based on what? There's plenty of reading material about this. I.e. the Stanford team's paper. The leading team failed in 2004 because of GPS availability and IMU error on map localization, not because they ran into obstacles. They failed by running off the road because of localization drift. They came back the next year with a LIDAR-based SLAM solution and won. It was added specifically to solve the localization problem.

There's no comparison between the tech stack of 2005 versus the tech stack of Cruise and Waymo. Stop spreading misinformation.

Sure Waymo has the most mature tech stack, but it's silly IMO to deny the obvious ancestry of these things, that's misinformation. The same people keep popping up over and over, there's this clear bifurcation in self-driving approaches. There's the Google team who was originally based off the Stanford team's entry, and all the copy cats (i.e. Zoox, Cruise, Aurora). And then there's the vision-based approaches like Tesla, Mobileye, OpenPilot.
 
  • Like
Reactions: JHCCAZ and stcptl