Which ADAS is Really Driving? It’s Mobileye!

[pamalabama]

at the same speed?

When cars merge in when I am driving, I do not necessarily slow down - it depends on the distance from me that they have merged in. I may choose to keep the tighter spacing depending on traffic conditions, and I have seen MANY other drivers so exactly the same.

Not all humans automatically slow down when a vehicle merges in. If the vehicle that merges in appears to be making a pass and will get back over in the right lane, I (and again, many others) will maintain speed with a shorter spacing until they return to the right lane. COMPLETELY avoiding any slowdown ripple.

tesla switched to AI on interstates after many years and the driving decision are more natural

Sponsored

 

[Zoidz]

Waymo makes weird decisions at times but in general it has surpassed human driving

That's the whole point of these discussions - IN GENERAL is not good enough. No one wants to waste their time in a vehicle that gets stuck circling a parking lot, which has also happened.

 

[Zoidz]

tesla switched to AI on interstates after many years and the driving decision are more natural

Nice response that conveniently avoids responding to any of my valid points. Driver +1, ADAS 0.

 

[pamalabama]

That's the whole point of these discussions - IN GENERAL is not good enough. No one wants to waste their time in a vehicle that gets stuck circling a parking lot, which has also happened.

This is a waymo issue, not a tesla issue. These problems are solvable. Waymo has a button to stop the driving at any time. People who let the car circle a parking lot are doing it on purpose to get attention

 

[pamalabama]

Nice response that conveniently avoids responding to any of my valid points. Driver +1, ADAS 0.

Because what are you responding to 1/2 mile ahead? You made a point but it wasn't clear what you were talking about. It just sounds like you are overconfident in your abilities. And that's fine, but you can't accept that computers are better. They are

 

[risingphoenix]

ADAS PLUS CARPLAY is better than any human.

/Mic drop.

 

[Zoidz]

Because what are you responding to 1/2 mile ahead? You made a point but it wasn't clear what you were talking about. It just sounds like you are overconfident in your abilities. And that's fine, but you can't accept that computers are better. They are

"Because what are you responding to 1/2 mile ahead?"

If you can't understand why you should be observing traffic 1/4 to 1/2 mile ahead, there's no explaining it to you.

I'm not overconfident in my abilities, I am just very confident in my abilities, based on having learned from professional driving instructors on track and years of autocross racing experience where my eyes and mind are 3 or 4 turns ahead of where my car is. I translate those skills to the highway, and I'm certain there are others here who do the same.

 

[mpshizzle]

CARPLAY

Unacceptable - we do not mention the forbidden word, here ??

 

[JM.]

I also noticed how you didn't tag me in this response to avoid notifying me.

That's also false. Why make stuff up?

ADAS systems cannot operate without human supervision

You're still not grasping what ADAS means????

Nothing, until you claim it’s equivalent to a human driving.

Nobody here has claimed that.

 

[Donald Stanfield]

That's also false. Why make stuff up?


You're still not grasping what ADAS means????



Nobody here has claimed that.

Except for the hundred or so times you did.

 

[risingphoenix]

That's the whole point of these discussions - IN GENERAL is not good enough. No one wants to waste their time in a vehicle that gets stuck circling a parking lot, which has also happened.

This is a ridiculous claim. Of course IN GENERAL is good enough. I use Autopilot/FSD/Driver+ most of the time. Because something doesn't work 100% of the time it makes it useless?? pfffth.

Different tool for different jobs. This is like claiming tennis shoes are not good enough because they don't work perfectly in the snow. And IN GENERAL all season tires are okay year round. There are literally thousands of examples of things in real life that work IN GENERAL that are invaluable.

Yes, ADAS is unable to REPLACE humans at this time. Yes, ADAS is not perfect and in increasingly fewer cases is WORSE than humans. But those facts do not discount the fact that ADAS is (and is becoming increasingly) SAFER than humans. And what everyone refuses to acknowledge is that ADAS is intended to be used WITH a human, making it safer than either one. There are 40,000 motor vehicle deaths per year in the US. That is, to quote Zoidz, NOT good enough. Anybody arguing against the continued development and improvement of ADAS as a driver assistant (and eventual replacement) is a nincompoop. Arguing about which one in isolation is better RIGHT NOW is a complete waste of time and loses sight of the entire point and goal, which is saving a life, or maybe 40,000.

 

[Donald Stanfield]

This is a ridiculous claim. Of course IN GENERAL is good enough. I use Autopilot/FSD/Driver+ most of the time. Because something doesn't work 100% of the time it makes it useless?? pfffth.

Different tool for different jobs. This is like claiming tennis shoes are not good enough because they don't work perfectly in the snow. And IN GENERAL all season tires are okay year round. There are literally thousands of examples of things in real life that work IN GENERAL that are invaluable.

Yes, ADAS is unable to REPLACE humans at this time. Yes, ADAS is not perfect and in increasingly fewer cases is WORSE than humans. But those facts do not discount the fact that ADAS is (and is becoming increasingly) SAFER than humans. And what everyone refuses to acknowledge is that ADAS is intended to be used WITH a human, making it safer than either one. There are 40,000 motor vehicle deaths per year in the US. That is, to quote Zoidz, NOT good enough. Anybody arguing against the continued development and improvement of ADAS as a driver assistant (and eventual replacement) is a nincompoop. Arguing about which one in isolation is better RIGHT NOW is a complete waste of time and loses sight of the entire point and goal, which is saving a life, or maybe 40,000.

What about all the lives being put at risk due to inferior systems and people being encouraged not to pay attention to them. Do we just ignore those in hopes that eventually ADAS is better than humans. Also you contradicted yourself by first saying that it's worse than humans in some cases but is safer than humans.

First off, prove it's safer than humans. Please show me a NTSB or other certifying body study showing that ADAS is safer than humans. Second, what YOU are discounting is the laziness of people. Give them a system that works well 85% of the time, and they will stop paying attention 100% of the time. Now, easily avoidable accidents are created due to the false sense of security that these systems can encourage.

I don't consent to being a test dummy for some vehicle manufacturers' little pet projects. That's my issue with these systems, especially the more permissive ones. I don't want to be on the road with them anymore than I do with drunks or people eating cereal while driving.

 

[SILVERR1S]

"Key Findings
The study measured a 49% reduction in front-to-rear crashes for vehicles equipped with AEB across all vehicle segments and model years. Further, the study measured a statistically significant improvement in the reduction of rear-end crashes, from 46% across model years 2015–2017 to 52% across model years 2021–2023, indicating that advancements in AEB over time have yielded tangible benefits.
For every 1,000-pound decrease in vehicle weight, the study measured an approximate 4% reduction in front-torear crashes for vehicles equipped with AEB. Understanding this effect is crucial as vehicle weight increases on U.S. roads [5].
The study also measured a 9% reduction in single-vehicle frontal crashes with non-motorists for vehicles equipped with PAEB, marking the first time PARTS has quantified a statistically significant measure of PAEB effectiveness.
Systems with active interventions (LDW + LKA and LDW + LKA + LCA) showed effectiveness in reducing single-vehicle road-departure crashes, although rates were low and varied with speed limit."

Source

 

[JM.]

Except for the hundred or so times you did.

Not one time have I claimed it was equivalent to a human. I've said the opposite. If you can find where I said that, I'll send you $100.

 

[JM.]

NHTSA Findings: A 2017 NHTSA investigation into a fatal Tesla crash found that crash rates dropped by nearly 40% after Autosteer (a key Autopilot feature) was installed in Model S and Model X vehicles from 2014-2016, reinforcing the system’s role in reducing collisions.


Over a 12-month period ending in early 2023, Teslas with FSD Beta engaged experienced an airbag-deployed crash approximately every 3.2 million miles, roughly five times safer than the U.S. average of one police-reported crash per 0.6 million miles.

Sponsored