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

Autonomous Car Progress

This site may earn commission on affiliate links.
If anyone is interested, Mobileye has posted an informative marketing blog that details the different ADAS/ADS products they are doing:


Mobileye is calling their L4 consumer car system "Mobileye Chauffeur". It will have 6 eyeQ6 High or EyeQ Ultra Soc, 360 degrees cameras, 360 degrees radar/lidar, REM and RSS. They are targeting a cost by 2025 of under $6,000.

5gn40N8.png
To me? That sounds more like (at a minimum) the level of hardware needed to achieve (for example) "NYC to LA with no user input". Not what Tesla's have on them today.
 
  • Like
Reactions: diplomat33
One piece of meaningful information reflected in this chart is that apparently Tesla is alone in their thinking that fewer sensors are better. Will Tesla end up being right? Maybe, but with the bulk of the "leaders" in the field going the opposite way, just based on basic mathematics alone I wouldn't bet on it.
My prediction is that no one will be right and driverless consumer vehicles will not happen for at least another decade. Then Tesla will have wasted the least amount of money.
What Tesla really has to worry about is a competitor developing a full speed highway L3 system.
 
34 companies signed an open letter to CA Governor Newsom asking him to allow AV trucking in California:

Waymo, Aurora, UPS and Luminar are among a group of 34 autonomous vehicle developers, California business organizations, and automotive and logistics companies that signed an open letter to Governor Gavin Newsom on Monday asking him to revisit the California Department of Motor Vehicles’s 2015 prohibition on the operation of autonomous trucks in the state.

The DMV told TechCrunch on Tuesday it plans to work with the California Highway Patrol on developing regulations governing heavy-duty autonomous vehicles, but it has not yet established a timetable for that rulemaking process.

 
34 companies signed an open letter to CA Governor Newsom asking him to allow AV trucking in California:



California has been the go-to place for AV testing, so I'm sure there will be some movement on this soon. On the flip side, a crash involving a truck will cause much more damage.
 
  • Like
Reactions: diplomat33
So GM Supercruise is level 2 hands free
The more I read about GM's approach, the more it appears to be a more strategic, planned, measured, understated, non -braggadocio type approach towards true autonomous driving than Tesla's approach. GM started with 200k miles of road, then expanding to 2 million miles of road, then carefully expanding to grow over 3.4 million miles. And while Im not sure this is factual, its at least perception:

GM’s first-generation advanced driver-assist system (ADAS), Super Cruise, has been praised as a safer, more capable version of Tesla’s Autopilot,
 
  • Like
Reactions: diplomat33
  • Helpful
Reactions: pilotSteve
Correct. SuperCruise is L2. It only works on mapped highways. It requires constant driver supervision. However, thanks to camera based driver monitoring, it is hands-free. UltraCruise will also be L2 hands-free but will work on mapped city streets.
I’m more than willing to state that the torque sensing in Teslas sucks. I’d much prefer that I just be forced to keep one or both hands on the wheel, rather than the current nonsense (to be clear, I have absolutely no problem with satisfying nags, it’s a non issue but it sucks).

However, what is the value of L2 hands-free? It seems potentially more dangerous than requiring a hand on the wheel. And what is the benefit of being allowed to take your hands off the wheel (which you can of course do in a Tesla for short periods which seems like all that would ever be necessary)?

I assume GM has a touch sensor on the wheel which they can enable in future if it turns out that not having hands on the wheel is a demonstrated safety issue in a larger data set.
 
  • Like
Reactions: daktari
I’m more than willing to state that the torque sensing in Teslas sucks. I’d much prefer that I just be forced to keep one or both hands on the wheel, rather than the current nonsense (to be clear, I have absolutely no problem with satisfying nags, it’s a non issue but it sucks).

However, what is the value of L2 hands-free? It seems potentially more dangerous than requiring a hand on the wheel. And what is the benefit of being allowed to take your hands off the wheel (which you can of course do in a Tesla for short periods which seems like all that would ever be necessary)?

I assume GM has a touch sensor on the wheel which they can enable in future if it turns out that not having hands on the wheel is a demonstrated safety issue in a larger data set.

In my opinion, the only real benefit of L2 hands-free is the marketing of being able to claim that the driver does not need to hold the wheel. It allows automakers to sell L2 but give customers something like "self-driving". There are customers who like the idea of going hands-free. So L2 hands-free gives them that.

In terms of safety concerns, if the camera based driver monitoring is reliable, I don't see it as a major issue. The camera based driver monitoring will ensure that the driver is alert and paying attention to the road. And being alert and paying attention to the road is more important than having your hands on the wheel. After all, it is possible to have your hands on the wheel and not actually be attentive. That's the flaw in torque-only driver monitoring. it measures that you are able to take over but it does not measure if you are actually alert and attentive to the road. Furthermore, if the L2 hands-free is restricted to the ODD that it can handle reliably, that will increase safety. But I do think the best L2 driver monitoring system would be one that requires both hands on wheel with a touch sensor AND camera to monitor attentiveness. That way you are measuring both the ability of the driver to take over AND that the driver is alert and paying attention to the road.
 
  • Like
Reactions: momo3605 and Matias
And being alert and paying attention to the road is more important than having your hands on the wheel.

But I do think the best L2 driver monitoring system would be one that requires both hands on wheel with a touch sensor AND camera to monitor attentiveness. That way you are measuring both the ability of the driver to take over AND that the driver is alert and paying attention to the road.
Agreed. I think attention monitoring is necessary but not sufficient.

E.g. With the current capability of Tesla FSD it’s absolutely essential you have your hands on the wheel at all times. Sudden steering movements can happen at any time and the delay if you have your hands off the wheel will likely lead to overcorrection or under correction in the event of sudden unexplained steering events (just happened to me this morning, sudden jerk towards adjacent left turn lane with a car in it; immediate disengagement).

I guess we’ll see how it pans out. With the limited domains right now probably SuperCruise is not an issue to be hands off. For UltraCruise not so sure. Depends on capability. If it can give some very short warning (borderline L3 but not L3) it might be perfectly safe.

I assume they have touch sensors if needed.
 
Last edited:
  • Like
Reactions: diplomat33
I guess we’ll see how it pans out. With the limited domains right now probably SuperCruise is not an issue to be hands off. For UltraCruise not so sure. Depends on capability. If it can give some very short warning (borderline L3 but not L3) it might be perfectly safe.

Personally, I think L2 hands-free will be short lived because L3 and eventually L4 will take it's place. Nobody will want L2 hands-free when L3 and L4 are available on consumer cars. L2 hands-free is only a thing now because we don't have L3 or L4 on consumer cars yet.