Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Tesla has a self-driving strategy other companies abandoned years ago

arstechnica.com

Post reply on HN
Print view View original

111–120 of 222 posts

Re: Tesla has a self-driving strategy other companies abandoned years ago

#111

Post by moogly »

mikeash wrote: post #57
peeters wrote: post #32

I've always found that half the issue is with the name: Autopilot. On an airplane, autopilot means you can take your focus off of both the physical and mental act of moving the plane through the air, and if it needs you to intercede there is pretty much no emergency in which you wouldn't have a few seconds to react. In a car, Tesla's Autopilot simply doesn't give you that. If you are reading and your autopilot exits,…

A system with lane keeping and traffic-aware cruise control corresponds pretty well to a simple two or three-axis airplane autopilot that just holds heading and altitude.

Maybe if you're out driving on a salt lake bed with no other vehicles or structures around.

Re: Tesla has a self-driving strategy other companies abandoned years ago

#112

Post by Animats »

scarmig wrote: post #87
Animats wrote: post #49

Waymo keeps plugging away. Each year, for the last few years, the number of miles between disconnects they report to the CA DMV has doubled. Three more doublings, and that number will be bigger than average miles between accidents for human drivers. Then they can ship a product. Nobody else is even close. This problem is slowly being solved, by normal engineering practices. The "fake it til you make it" players are b…

Do you have hard numbers so we can establish a trendline? My perhaps false recollection was that Waymo disengagements had flatlined 2017 to 2018.

You're right; 2016 to 2017, not much improvement. Then, twice as good in 2018.[1] (CA DMV stats run on a year from December to November, so the most recent data set is for 2018.)

[1] https://thelastdriverlicenseholder.com/2019/02/12/disengagem...

Re: Tesla has a self-driving strategy other companies abandoned years ago

#113

Post by jaimex2 »

I'm confused.

The article seems to extrapolate that Tesla has failed in autonomous driving because it removed some lines from its Autopilot page. It's still very much in progress and progress is routinely confirmed by the company. Musk is known for blowing timelines but they do get delivered.

When it talks about "old approach" I'm again confused. No one else crowd sources driving data from a real world fleet. They have a unique unsupervised learning datasource from shadowing drivers.

As for attentiveness. I don't see how drivers not paying attention is any different to mobile phone use. Currently Autopilot is very clear on telling at every chance its an assistant. Saying it will kill people is like blaming phones for drivers texting while driving and getting killed. These people die because they are breaking the law and not in control of their vehicle.

Re: Tesla has a self-driving strategy other companies abandoned years ago

#114

Post by Sohcahtoa82 »

ForHackernews wrote: post #18
cbames89 wrote: post #5

This is a (perhaps short-term) failure of first principles reasoning. Elon's known to favor thinking about things from first principles, and there's no theoretical reason that vision can't work. However, technical limitations might take a while to overcome.

Vision alone fails pretty frequently even with a human brain and 700 million years of evolution behind it. Count me as a skeptic that cameras + computer will produce a safe self-driving system.

This implies that the vision itself is to blame and ignores the actual causes of crashes.

A computer doesn't get distracted by a text message. A computer doesn't get drunk. A computer doesn't day dream.

Cases where a crash happens and the person at fault says something like "I didn't see them!", it's usually because they didn't even look, a mistake a computer won't make.

Re: Tesla has a self-driving strategy other companies abandoned years ago

#115

Post by vkou »

cbames89 wrote: post #5

This is a (perhaps short-term) failure of first principles reasoning. Elon's known to favor thinking about things from first principles, and there's no theoretical reason that vision can't work. However, technical limitations might take a while to overcome.

> there's no theoretical reason that vision can't work

Human brains, which are general intelligences, exist, and are collections of atoms.

I'll happily, for $500,000/copy, upfront, promise to sell you artificial general intelligences. I swear I'll get them built in the next two years.

There is, after all, no first principle reason for why my promise isn't worth the paper it's printed on. Human brains are collections of atoms, so we should be able to, out of atoms, build artificial general intelligences.

Re: Tesla has a self-driving strategy other companies abandoned years ago

#116

Post by leesec »

FireBeyond wrote: post #77
wil421 wrote: post #67

Earlier quoted context omitted.

At least Tesla has an actual product you can buy? Where’s Waymos product? Will they sell to consumers or the incumbent car makers? I agree with your statement about Tesla’s marketing of self driving. My Grand Cherokee isn’t so far off their mark. It has lane assist, adaptive cruise control with stop, parallel and back in parking. I’d bet Jeep could do summon and more stuff on the highway.

> At least Tesla has an actual product you can buy? What self driving product do they have? Elon's "Oh yeah, we will have full self driving coast to coast in [8 months]" is horseshit to the point of "How is he allowed to say this on an earnings call?" Other competitors, widely recognized to be ahead of Tesla estimate 5, more likely 10 YEARS. Coast to coast? Your Tesla will navigate a Pittsburgh winter storm on poor r…

How are you going to say Tesla doesn't have a product and then go on to list a bunch of worse products as if they are better?

Tesla has effectively incorporated Lane Keep Assist/Automatic Cruise Control into a single product called Autopilot that has vastly better software than other similar products.

Simply put, if other companies had a product that would have allowed for billions of miles to be driven hands free feet free, they would have it, but they do not, not even close. Tesla does.

Re: Tesla has a self-driving strategy other companies abandoned years ago

#117

Post by leesec »

close04 wrote: post #94
leesec wrote: post #84

Earlier quoted context omitted.

What do you call it when a Tesla drives me 90% of the way to work where I don't do anything but observe? It's not full self driving but it definitely is driving it self and providing value.

What kind of traffic and road conditions does that trip involve and how much are you an observer vs. you hanging on to the wheel and paying attention to everything as if you were driving yourself (staying engaged) as you are required by the law and by common sense? And if you don't mind me asking, how would you quantify in real money the value added by the system?

The 90% I am talking about is a 12~ mile stretch of poorly maintained highway near Detroit usually in stop and go traffic and yes I am paying attention.

I wouldn't quantify the value in real money. I would say the main benefit provides is that I have much less decision fatigue and am less stressed after my commute. I also don't care how fast I really get there anymore since I just optimize for less stress, and my trip is enjoyable.

The other main value I commonly see overlooked is safety from distracted people. If we can assume people are going to keep texting and driving ( they are ), would you want them to do it while actually driving or with this system engaged?

Re: Tesla has a self-driving strategy other companies abandoned years ago

#119

Post by eclipxe »

mbreese wrote: post #95
zaroth wrote: post #88

Earlier quoted context omitted.

My wife’s car has a similar long list of “features” (Mercedes DISTRONIC package with active lane keeping) and it is nothing even remotely comparable to driving my TM3 with autopilot. Those cars do not steer themselves. The difference between having to steer the car and not having to steer the car is extreme. It totally changes the way you drive. Instead of looking down your lane and keeping the car centered, you scan…

And my wife’s Acura will completely steer itself (with a much shorter list of features), but requires your hands on the wheel. It works without your hands, but it gets testy if you don’t move the wheel slightly every 15 seconds. It’s significantly nicer to drive long stretches with this system, but I can’t imagine doing it without your hands on the wheel. When the sensors fail (weather or poor lane markings), you nee…

Your wife's Acura does not steer itself the same way a Tesla steers itself. Your wife's Acura will try to keep the car from exiting a lane.

Re: Tesla has a self-driving strategy other companies abandoned years ago

#120

Post by UncleMeat »

garmaine wrote: post #109
onlyrealcuzzo wrote: post #108

Earlier quoted context omitted.

What's the problem? If a a robot can drive a car more statistically more safely than a human, that seems like a net win. Maybe humans shouldn't be making left turns in traffic or passing trucks either. Those are probably, statistically, the most dangerous things you can do when driving. But we do them all the time, because we have no idea how dangerous they really are.

The problem is the other car has a human in it, and those situations are ones where the reaction of the other human is critical to safety analysis, but generally unpredictable.

A computer will be able to react to a sudden crazy movement by another driver far better than a human will.
Post reply on HN