Most people are more concerned about their safety on an airliner than the drive to the airport, despite the fact that the air travel is far safer than driving. It's a perception that being in control is safer than not. L5 autonomous cars, if they ever become mainstream, will suffer the same hesitancy.
-
Want to remove ads? Register an account and login to see fewer ads, and become a Supporting Member to remove almost all ads.
Autonomous Car Progress
- Thread starter stopcrazypp
- Start date
-
- Tags
- Autonomous Vehicles
Doggydogworld
Active Member
Many were terrified of elevators, and then of elevators without "safety drivers". Apprehension quickly dissipates. I recall Waymo testing with some worried riders early on, they got bored after a few miles.
diplomat33
Average guy who loves autonomous vehicles
Correct. People are wary of self-driving cars because it is a new technology. People tend to be wary of what is new. I think as long as the public has a good experience with self-driving cars, they will embrace them and they will become just another normal technology like everything else we use everyday. I think your Waymo example supports that. People were nervous at first but Waymo did a good job of making sure the rides in Chandler were safe and comfortable so people quickly got used to it and now most riders in Chandler don't think twice about getting into a Waymo. I firmly believe that some day soon, robotaxis will be seen as completely normal and no big deal.
voyager
Active Member
San Francisco, Jan 20 (Reuters) - Luxury carmaker Mercedes-Benz will partner with self-driving sensor maker Luminar Technologies Inc (LAZR.O) to enable fully automated driving on highways for its next-generation vehicles, Luminar's founder said.
/cloudfront-us-east-2.images.arcpublishing.com/reuters/UQO6R4AMZZJV5HOVQS7YH5BFSU.jpg)
www.reuters.com
Mercedes-Benz teams up with Luminar on self-driving tech
Luxury carmaker Mercedes-Benz will partner with self-driving sensor maker Luminar Technologies Inc to enable fully automated driving on highways for its next-generation vehicles, Luminar's founder said.
www.reuters.com
Unfortunately 2024 at the earliest and most likely only from zeekr. unfortunately with the current meme stock environment. announcing that you are building a time machine that will be ready next year is more stock profitable than announcing that you have a working time machine.
Terminator857
Active Member
For those that would like to learn more about Zeekr, I found this:
Could you send me a link to your favorite time machine ETF?
And keep me posted on who's got the best prototype; I'd like to go back and give myself some better investment advice!
@powertoold Just over 3 months after your latest prediction. With just 3 months left, are you still sticking with this prediction?
What "small minor issues" have been fixed and which are left that will give FSD the reliability to be a robotaxi? Can you watch the below vid and tell me whats done and whats left?
What "small minor issues" have been fixed and which are left that will give FSD the reliability to be a robotaxi? Can you watch the below vid and tell me whats done and whats left?
Do we have any indication that Tesla is working towards geofencing anything? I haven't seen one, seems to be full steam ahead towards generalized autonomy and that will require the solving of all problems.
Can only imagine the complexities in attempting geofencing FSD/AP at this stage in the game
Can only imagine the complexities in attempting geofencing FSD/AP at this stage in the game
diplomat33
Average guy who loves autonomous vehicles
No, there is no indication that Tesla will geofence. You are correct that Elon/Tesla are all in on generalized autonomy. It's basically L5 or nothing.
I think the reason some people keep mentioning geofencing is because geofencing would be an obvious way to deploy robotaxis as soon as possible. Safe and reliable L5 robotaxis are not going to happen any time soon. But geofencing would allow Tesla to deploy robotaxis sooner. So people assume that Tesla must be planning to geofence in order to deploy robotaxis. And it probably adds to the confusion that Lex Friedman asked Elon when Tesla would solve L4, even though Tesla has never said anything about L4 and has only talked about L5.
I imagine geofencing would be fairly easy actually. Tesla could just add code that only allows the driver to activate FSD/AP when the GPS coordinates of the car are inside a certain area or correspond to certain roads and deactivate FSD/AP (with an alert to take over) when the GPS coordinates indicate the car is leaving the geofence area or designated roads.
I don't recall seeing a Tesla responding correctly to officer hand signals yet, such as a forced turn. These have been said to be in the works and are an essential feature for L4/L5 operations.
EVNow
Well-Known Member
Its just a question of error rate or as Mobileye calls it MTBF. Difference between Tesla L2 and Tesla L5 is MTBF of 1 mile & 100k miles.
Tesla will have a working "L2/ADAS" sometime this year and that will not be "nothing".
ps :
Elon has zero interest in geofencing - though in practice, it will be geofenced by countries/continents/regulatory boundaries.
Last edited:
powertoold
Active Member
I like how Diess is subtly calling out Mobileye's bullsugar. Diess knows Tesla's approach is way ahead and superior, but Volkswagen has no choice:
diplomat33
Average guy who loves autonomous vehicles
diplomat33
Average guy who loves autonomous vehicles
And Tesla is very far from the MTBF needed for safe L5. Hence, my statement that Tesla is far from L5.
I agree. Except Elon has not talked about achieving "L2/ADAS", he's only talked about Tesla achieving L5.
Last edited:
The geofencing technical capability is already there I'm sure, defining all the roads and conditions is what I think would be insanely complex and then whatever implications associated with juggling multiple different branches of the software across all the different configurations etc -- I don't believe these are challenges other Robotaxi companies face.
Not sure how they would go about defining which municipal roads the system won't function on across an entire country and then maintain it. Unless we're talking going right down to the scale of current Robotaxi competitors and working on individual cities. But trying to do something Waymo-style across the US would be such a ridiculously massive task.
Is it even possible to strictly define an ODD without something like HD maps? Are the TomTom maps accurate enough to do Robotaxi-style geofencing while FSD draws everything in real time? Are the maps current enough?
diplomat33
Average guy who loves autonomous vehicles
Mobileye says that the MBTF for vision-only (which will only be L2) should be 1 per 10,000 hours of driving but their camera, radar, lidar system (L4) should have a MBTF of 1 per 10M hours of driving. Not sure where you are getting the 100k miles MTBF from.
I question whether Lex Friedman can act impartially to Elon, and whether Lex is really aware of why the L4/L5 question is so important.
To me it seems like Tesla is using the promise of L5 like capabilities while knowingly not having the HW to achieve that. This allows them to buy time.
As a customer the answer to this question is vital.
If Elon acknowledges that the whole L5 thing was a fantasy, and is shifting focus to a geofencing L4 where possible it makes it seem realistic that I might get something.
If Elon doubles down on L5 and laughs off L3/L4 then I more likely to bail, and get something else that satisfices my wants outside of autonomy.
I can't blame any company in the US for failing to deliver on autonomous vehicles. As a nation we simply didn't do a good job of standardizing on technologies to help automate the driving task.
Like yesterday I was coming back from the coast, and a sign said the road was closed 26 miles ahead. The Tesla navigation didn't show anything so I tried Apple maps, and it desperately wanted me to turn around and go a different way. I then tried Google Maps, and it said there was an accident ahead but simply said there was a delay. I'm not sure why I didn't turn around. It was probably curiosity as to what the result would be, and the result was that I was an idiot. It seemed like they were allowing one lane of traffic to go through as it we'd move a bit, and then stop. But, then when I got further ahead about an hour later they were just turning cars around.
I bring that up because it shows how unready we are. I'm not sure how Apple Maps managed to get it right, and why Google Failed. I believe Tesla uses google for traffic information so I don't expect it to be right when Google isn't.
Navigation comes before anything else.
Last edited:
Apple's maps are extremely good in the latest updates and the navigation functions are outstanding. You can also drop pins for accidents, traffic issues, and speed traps -- I've come across a few of these dropped by other people when using CarPlay.
Pretty neat when you enter navigation mode in a city and can see all the buildings for blocks around you as well
You can tell Apple is putting a lot of effort into this
Pretty neat when you enter navigation mode in a city and can see all the buildings for blocks around you as well
You can tell Apple is putting a lot of effort into this
Last edited by a moderator:
Similar threads
- Article
