this seems like the sort of thing that would be better measured with actual numbers, not just anecdotes from people on the internet.
the NHTSA is a pretty cautious organization, and they like numbers. if they've studied it and found that automatic braking will prevent 24000 crashes and 360 deaths per year, i'd be inclined to believe them. having the car brake for me when i'm not expecting it sounds kind of scary to me too, but i'd rather experience that than let 360 people die every year.
The problem with numbers is that they don't tell the whole story.
I can easily imagine a scenario where it might prevent 25000 crashes a year that are caused because 5% of drivers are staring at their phones, have a high chance of rear-ending someone, and this software makes that far less likely. While also containing bugs causing 1000 crashes a year for the larger number of non-distracted drivers, resulting in a net change of 24000. This would mean that adding the software would be better for society, while making the majority of drivers slightly more likely to crash into someone.
No, that isn't a problem with numbers. That is a problem with letting your imagination run things.
The scenarios and questions you ask are easy to explore in the data. If the number of crashes goes down, contrived scenarios don't really impact things. If they stay flat or go up, then you have to answer why.
To emphasize, for your imagination here to be relevant, the number has to do one of those. If the number goes down, even if it shifted some situations into a wreck that would not have been before, it must have done fewer of those than it moved wrecks to non-wrecks. If it somehow causes more situations to be wrecks, the number, by definition, goes up.
> The scenarios and questions you ask are easy to explore in the data.
This sounds like the beginnings of the McNamara fallacy: that there is some abstract "data" where all the relevant variables can be explored to decide the best course of action. The reason it's a fallacy is that data is itself only a reflection of conscientious decisions about what to measure and how to measure, and these are invariably limited to what we already appreciate and understand, not accounting for the things we don't know how to measure and don't know we should be measuring.
To be more concrete, let's say we follow your suggestion and focus on crashes. Maybe it's found that automatic breaking reduces the number of crashes so it's mandated. But maybe automatic breaking also increases the likelihood that a crash is deadly in some sub-population like pedestrians, construction workers, and motorcyclists. So overall we see crashes decline because a large number of minor crashes are averted but we also see deadly crashes increase because pedestrians, construction workers, and motorcyclists are killed more frequently.
So data isn't a free lunch. Every decision about what to measure and what to optimize involves some prior contextual understanding. A misunderstanding of the context means the data will misrepresent some aspect of the problem and you'll overoptimize yourself into a local maximum.
Again, you are contriving bullshit to scare folks. And you didn't look at the studies. 38% decrease in accidents along with decrease in fatalities. In the data. For the worries you are sprouting, the data would have to look very different.
It is literally the definition of FUD here, though. These aren't things that have happened. And the data is ridiculously clear on progress. To paint these doubts is pretty much only to spread fear and uncertainty.
Yes, but sharing a characteristic with FUD is not enough to make something FUD. It's a realistic concern.
Someone else mentioned airbags. Airbags are great overall but increase danger for some people, and that's without obvious signs of anything being wrong.
With AEB we know it makes dangerous mistakes in significant amounts. So we very much should analyze different implementations under different kinds of weather, road, and driving style.
We don't know it makes dangerous mistakes. Randos on the internet assert that. The data shows fairly convincing evidence is reduces wrecks.
Is it a new behavior and jarring when engaged? Certainly. Should we keep watching the data for problems? Certainly. Should folks report all problems so that they are tracked? Certainly.
Do most people actually have trouble driving safely? Despite their insistent view of how great they are at driving? ...
Let's see, what can I find on youtube in a couple minutes of searching. In increasing order of wrongness:
https://www.youtube.com/watch?v=BLRRBHNjCn4 There's a car that it's reasonable to worry about, but it was clearly braking and almost stopped by the time AEB kicked in, and AEB kept going as that car went to zero.
This conjures the fear that the agency in question is bad at this. Do you have evidence that they are? Can it happen? Yes. We could also have it so that no wrecks from minorities are counted, such that we are blind to how they are impacted. Would be terrible. No evidence that that has happened.
> This conjures the fear that the agency in question is bad at this. Do you have evidence that they are?
Yes. This was my movivation for questioning the "data says" logic. The NHTSA has made decisions based on data that were poor decisions because they misunderstood the problem domain and became overly reliant on specific metrics. Here is a copy-paste of an earlier comment in this thread:
--
> the NHTSA is a pretty cautious organization, and they like numbers.
They may be cautious but they're not necessarily smart. Their vehicle safety ratings only measure the safety of occupants in that vehicle. Result? An arms race where cars keep getting bigger, heavier, and taller to do better in crash tests against bigger, heavier, and taller cars. These "safer" vehicles are now more deadly to everyone else, especially pedestrians and bicyclists.
I'm at against bigger cars as you can be. Literally biking to places when I can. I am not clear that this is the nhtsa's fault.
That said, I could cede this point if you can show evidence of it in these studies. The org is a bunch of people, so I grant they could make mistakes. Without specific concerns, this is the definition of fud. You aren't giving criticism of these studies and actions, but seeding doubt on their data.
I disagree. I've been a licensed driver for over 40 years. I had one minor fender-bender at 16 years old, learned my lesson, and haven't had another accident since. I'm an exceptionally good driver as evidenced by this, plus the fact that I've taken performance driving classes, simulators, and so forth.
I, personally, am a much lower risk than the typical driver. Putting a drivers' aid device in my car may well increase the danger to me and those around me, even while having it in other cars decreases danger.
BTW - my car's traction control is evil. It's a rear wheel drive car, without limited slip. So when I pull out onto the road from a driveway, if there's the slightest bit of sand on the road, I get enough spin to engage the traction control. The car deals with this by vastly cutting engine power. In Texas, where the regular surface road I'm pulling out to is commonly 60mph, and often faster, I need to accelerate quickly to avoid the guy approaching - yet the traction control has just left me wallowing, dead in the water, unable to accelerate strongly. Except in wet conditions, disabling the traction control is always the first thing I do when I sit in the car.
Every person on the planet believes they’re an above average driver. No one thinks they need these types of safety features in their car because they’re a safe driver and the problem is every other driver.
It terrifies me that people are so oblivious to their own flaws that they would willingly disable features such as AEB if they could. I’m extremely thankful for regulations that prevent such life-saving safety features from being disabled.
An average person has 3-4 car crashes in a lifetime. Having 1 minor accident in 40 years of driving is above average.
The only time I ever came close to having a crash is when lane assist tried to drive in the dividers on a highway with construction going on, so lane assist is the first to go in a new car.
The average person also has their wrecks at the beginning and end of their driving. Having 1 while in late 50s to 60s isn't that unlikely, either. And sets you on the average track.
I thought I was a low risk driver, then when doing a lot of hours riding a motorcycle it became very apparent how incredibly terrible of a car driver I was. So much general threat and risk was invisible as a car driver contained in a big metal box.
I do a lot of cycling and it's amazing how much more aware you are when any minor bump is going to cause you injury. I've avoided accidents multiple seconds in advance because something about the way someone was driving made me nervous, it's like you get a sixth sense.
> If the number of crashes goes down, contrived scenarios don't really impact things.
Yes they do impact things.
Consider a pill that, given to a wide population of test subjects, reduces heart attacks by 20%. That's great! But when you look at the data more closely, it strongly reduces the risk for people older than 40, and it increases the risk for people under 40. Should you prescribe that pill to everyone at risk of heart attack? Of course not.
Does AEB have a pattern like this? Who knows! Someone should test or cite a good test!
You're not listening. The 38% number can be true and there can be particular groups that are hurt more than helped. Nobody is trying to "argue against" the 38% number.
> In a cost benefit, if the number drops 38%, you are going to have to work to show it isn't worth it. What would the number have to be?
Where did anyone say "isn't worth it"? The sentence I see is "The problem with numbers is that they don't tell the whole story."
Though in a more general sense, if someone does invent a system that has strong average safety gains, but makes the majority of people less safe... that's a hard sell.
Fair, if you are just pushing that we need to keep looking at the numbers and to be aware of some ways it can go bad, fine. I took the topic here to be that these studies were bad. In a known and showable way.
It isn't a binary choice, you can disable the function for situations it's not suited for. Nothing should be forcing us to enable harmful scenarios just because.
Respectfully, you're taking an extremely naive stance to a topic where others are trying to bring nuance. I think if you listen carefully, you'd learn something that will help you not just on this topic but in your life.
Logical fallacies like the base rate fallacy are real, and they fool all of us frequently, myself included.
Bringing nuance is fine, but it is also an easy stalling tactic in progress. Clear improvements in safety are shown in the studies linked here. From an organization that has shown remarkable progress in safety over the years. And has been beset with such "nuance" since the beginning.
Literally the same arguments were and are made against seat belts. Often. And is why I am not too willing to give way here.
Now, if you are just saying, "I hope they keep their eyes on the data and are willing to keep improving," great. I agree. If you are trying to angle it that this is not a safety improvement, I will loudly disagree.
I think it is probably overall a safety improvement, and I think many of the arguments about losing control of your car are a bit overblown. But, there's something to them, and it rubs me the wrong way to ignore and dismiss those you disagree with. It's too easy to characterize a position you don't agree with as one that is operating in bad faith or ignorance.
The question is whether anyone is actually interrogating the data in that way, not whether it can be interrogated. Large data-driven institutions are notorious for taking a narrow view of things.
The problem is precisely a lack of imagination, or perhaps more accurately, critical thought.
The parent is precisely engaged in the kind of interrogation that is necessary. If you are aware or an analysis that bears on his questions, now would be the time to share it.
This feels like sophistry to hinder progress. The OP is literally about studies done. Did you find problems with them? Or are you only imagining problems there could be?
The latter, which is why the actual studies would be most welcome.
But more to the point, there is a track record of narrow interpretation of studies and missing of the big picture. It’s hardly sophistry, it’s critical thought.
The number of crashes will go up because of this "safety" feature. And then we'll be stuck with this "safety" feature for decades till the govt gets their act together to undo what they did.
I'll keep my 30yo car with no computers as long as I can thank you very much.
The confusion here is that some people realize they aren't "average". That is, while some policy or another is good on the whole, it can also be bad for them personally. For them, the chance of a wreck can actually increase. You're demanding that they sacrifice themselves to save imbeciles who probably shouldn't be allowed to drive anyway.
For such people, these policies suck. And it's strange that there are those that demand they either be happy about it, or at least be quiet about it.
That's true of basically any change isn't it? Even seat belts conceivably could result in some very small increase in the chance of death as a result of it being harder to escape a vehicle. Obviously the benefits far outweigh the risk, but then we are just arguing over where to draw the line.
I think you missed their point. It's not that most situations are improved and some get worse, it's that those situations might be unevenly distributed among drivers.
A seat belt is basically the same for everyone. It makes things safer when you look at all drivers, and it makes things safer for just about any subgroup of drivers.
But a buggy AEB might not fit that pattern. Imagine a system that reduces crashes by half, but then adds an extra X crashes per million miles. If someone's unassisted crash rate is 5X, then this system reduces it to 3.5X and is a great help. If someone's unassisted crash rate is .5X, then this system increases their crash rate to 1.25X and is a terrible trade.
Your claim seems to be the group who are not helped are "good drivers"? ... except that doesn't feel like a well-defined group to me, and also is a group that almost everyone would say that they are in.
Well specifically the idea is that it's so uneven it might increase the danger for certain groups, and seatbelts are pretty good overall. But bringing up airbags is a great example. If you're short enough (or possibly if you're tall enough), a standard airbag is more dangerous than nothing at all.
They way you crash in terms of whether your seatbelt helps or harms doesn't depend on your life choices. Features likely benefiting drunk and distracted drivers and likely hurting aware ones are different.
As someone who does ML for a living I can definitely say that false positive data from the field can significantly improve the experience for those 1000. That is what should be standardized if we wanted to see systems that work for everyone.
> the NHTSA is a pretty cautious organization, and they like numbers.
They may be cautious but they're not necessarily smart. Their vehicle safety ratings only measure the safety of occupants in that vehicle. Result? An arms race where cars keep getting bigger, heavier, and taller to do better in crash tests against bigger, heavier, and taller cars. These "safer" vehicles are now more deadly to everyone else, especially pedestrians and bicyclists.
And the actual numbers should include the opportunity cost (in lives saved or QALYs, if you like) of the increased price of vehicles with these systems. Could that money have been spent on smoke detectors or healthier food or ?
On Wednesday, the National Highway Traffic Safety Administration issued a notice of proposed rulemaking that would see automatic emergency braking become a standard feature on all new light passenger vehicles.
And the actual numbers should include the opportunity cost (in lives saved or QALYs, if you like) of the increased price of vehicles with these systems. Could that money have been spent on smoke detectors or healthier food or ?
In response I said:
National Highway Traffic Safety Administration
Then mhb said:
What's your point?
Can you explain what my point was to mhb?
ChatGPT:
It seems like you're suggesting that the responsibility and scope of the National Highway Traffic Safety Administration (NHTSA) is primarily focused on improving safety on the roads, specifically through regulations related to vehicles, rather than other broader public health initiatives like smoke detectors or promoting healthier food.
Your comment may imply that while considering the opportunity cost is a valid point for an overall public health or policy perspective, it may not be directly relevant to the mission and function of the NHTSA. The NHTSA's mandate is to ensure the safety of vehicles and roads, so they would prioritize improvements and regulations in that area, even if those funds might have a higher impact if spent elsewhere from a wider public health perspective.
In other words, the comment might suggest that each organization has its own scope and priorities, and while we can consider overall opportunity costs, we also need to consider the specific roles and responsibilities of different organizations. However, without more context, this is just one possible interpretation.
Yeah. Duh. If you had included, in your prompt, the NHTSA quote that I quoted, ChatGPT might have been more helpful to you. Viz: On Wednesday, the National Highway Traffic Safety Administration issued a notice of proposed rulemaking that would see automatic emergency braking become a standard feature on all new light passenger vehicles.
That point being: maybe NHTSA's advocacy of a requirement for all new vehicles is beyond the scope of its mission and it should confine itself to providing information to the policy makers who might possibly understand the tradeoffs.
Removing distractions like poor user interfaces would probably overlap with the improvements from emergency braking. So if you want to be throughout you would have to check if they still make sense with the other changes in place.
I experienced it multiple times and not even once it triggered in a correct situation. Usually a weird angle on a t-junction triggers it unnecessarily.
But they didn't study anything real world. They looked at all rear-end collisions, assumed that a percentage would be prevented and did the math to result in the 24000/360 numbers. No analysis of other affects (like sudden stops causing crashes from the cars behind them). No extrapolating from measured data.
> No analysis of other affects (like sudden stops causing crashes from the cars behind them).
At least part of that effect will show up in these vehicles being rear-ended themselves (as they're exhibiting that exact sudden-stop behavior), and that sort of accident should be reduced if all cars come with AEB.
You'll never be able to wipe out all variables in this sort of study, but I don't think the methodology's as flawed as you're asserting.
It's fair that you can never wipe out all variables. However, a lot of people (especially taeric) were dismissing any attempt to discuss if other aspects were important as "the NHTSA has data and you only have conjecture."
While the costs of phantom breaking are decreased if everyone has AEB, I don't think this makes the roads safer for me unless I want to buy a newer vehicle and I don't want to have to do that.
Exactly. It's 0.92% of the 38,000 car crash deaths in the US annually. I agree, this is noise and honestly it doesn't make sense the NHTSA would even consider a mandatory "safety" feature like this for that small of an expected change. Personally, I will not be purchasing a car with this feature until I'm forced to.
Feel free to look at the numbers in the PRIA [1]. Those 360 deaths are a significant reduction in fatalities from baseline in the types of collisions they expect to be impacted by this rulemaking. That baseline itself assumes some 65% of new vehicles will come with compliant AEB systems regardless of this rulemaking.
Another interesting question is how many of the other 24,000 crashes were serious. And how many additional crashes wouldn’t have been avoided but would have had a lot of kinetic energy removed before impact.
> A metanalysis in 2015 found a 38 percent decrease in collisions for vehicles that utilized such a system, for instance.
Barring massive fuckups in methodology, that should account for false positives that cause an accident. The number of non-collision severe injuries (are we theorizing folks get their head banged against something when it brakes heavily?) is likely to be pretty small versus that 38% stat.
> The number of non-collision severe injuries (are we theorizing folks get their head banged against something when it brakes heavily?) is likely to be pretty small
(People can be injured directly by the seatbelt, and there's also whiplash to consider.)
> People can be injured directly by the seatbelt, and there's also whiplash to consider.
I don't doubt it's possible, just like it's possible for a seatbelt to trap you in a burning car... but common enough to offset a 38% drop in crashes? I severely doubt it.
If someone can demonstrate that people driving these cars have a dramatically increased incidence of whiplash or seatbelt injuries, by all means, but I'm comfortable saying the burden of proof is on them there.
the NHTSA is a pretty cautious organization, and they like numbers. if they've studied it and found that automatic braking will prevent 24000 crashes and 360 deaths per year, i'd be inclined to believe them. having the car brake for me when i'm not expecting it sounds kind of scary to me too, but i'd rather experience that than let 360 people die every year.