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

81–90 of 222 posts

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

#81

Post by rootusrootus »

matthewdgreen wrote: post #45
pjkundert wrote: post #23

Earlier quoted context omitted.

... working on this stuff day and night ... —- in California . I’ve been driving for 40+ years, millions of km, 1/2 during winter. Now, Elon is a Saskatchewan boy, so he should know better. Perhaps he’s forgotten. Winter driving is at best 1/2 vision dependent, often much less. Many times, you have to actively ignore your vision (everything you see is “moving” sideways). Quite often, you’re modulating your throttle t…

The vision problems are real. But the ability to handle ice/snow-induced wheel spin and slew seems like exactly the kind of problem that can be handled with sensitive electronic traction control, perhaps augmented with accelerometers. That specific problem doesn't seem intrinsically more complicated than, say, keeping a drone level on a breezy day -- which is something machines already do much more reliably than huma…

Traction/stability control can only help with the situation you are already in. Being able to see the condition of the road -- the sparkle of ice forming, for example, or a sheen that suggests black ice, etc -- allows you to act instead of just react.

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

#82

Post by mikestew »

wil421 wrote: post #67
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…

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?

I have a self-driving automotive product you can buy. It doesn't work as advertised, either.

Calling a lamb's tail a leg doesn't make for a five-legged farm animal. This reminds me of the conversations about, say, phone authentication using facial identification. "Samsung had it before FaceID!" Yeah, I had one of those Samsung phones. It did not do what it said on the tin. So, yeah, Tesla has a product you can buy, but it is not a self-driving vehicle despite what they might tell you.

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

#83

Post by FireBeyond »

leesec wrote: post #70
CPLX wrote: post #69

Earlier quoted context omitted.

> I don't think Musk 'lies' to earn more money. Telling people that the actual physical car they are currently purchasing from his company will soon be capable of autonomous driving when, in fact, it isn't, and won't ever be, seems to be a pretty straightforward contradiction of that statement.

Why do you think it won't ever be? Also that's literally just your opinion that it won't soon be capable. It's definitely Musk's opinion that it will soon be capable. Mine too.

Musk is stating, for the record, that your Tesla will be able to drive, _coast to coast_, full level 5 autonomy - poor roads, blizzard conditions - THIS YEAR.

Given that the autopilot system has been evolving for five years (introduced in 2014 for Tesla) and still has problems like "aims at water barriers and accelerates", "fails to recognize that trucks may be more complex than simple cube in space", "fails to recognize that vehicles of a certain color may be hard to see when driving towards the sun"... and that will all be solved "this year" (t minus 9 months and change) seems...

supremely optimistic. I was going to call it naive, but that's an insult - Elon certainly knows far more about self driving than I do.

But this is the equivalent of man kind making fire, making the wheel, and then turning that into a car as the next logical step, ignoring all the interim.

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

#84

Post by leesec »

mikestew wrote: post #82
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? I have a self-driving automotive product you can buy. It doesn't work as advertised, either. Calling a lamb's tail a leg doesn't make for a five-legged farm animal. This reminds me of the conversations about, say, phone authentication using facial identification. "Samsung had it before FaceID!" Yeah, I had one of those Samsung phones. It did not do what it said on the…

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.

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

#85

Post by FireBeyond »

haberman wrote: post #65

I got a Tesla last year. I love it. But it's been painfully obvious to me that Autopilot is nowhere close to something that will let you take a nap. Often when I'm stopped at a light, cars that are standing completely still will appear to be constantly moving forwards and backwards on the display. My best theory so far is that the Tesla's spatial model is getting thrown off by the other car's turn signal. This does n…

> In general, I find the radar-enhanced cruise control very reliable (so nice in bad traffic)

Which is great but hardly unique to Tesla. Every major manufacturer out there offers adaptive cruise control. My car even recognizes the difference between in traffic stop-and-go/rush hour, and "queue" mode (exiting parking lots after events, etc).

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

#86

Post by leesec »

FireBeyond wrote: post #83
leesec wrote: post #70

Earlier quoted context omitted.

Why do you think it won't ever be? Also that's literally just your opinion that it won't soon be capable. It's definitely Musk's opinion that it will soon be capable. Mine too.

Musk is stating, for the record, that your Tesla will be able to drive, _coast to coast_, full level 5 autonomy - poor roads, blizzard conditions - THIS YEAR. Given that the autopilot system has been evolving for five years (introduced in 2014 for Tesla) and still has problems like "aims at water barriers and accelerates", "fails to recognize that trucks may be more complex than simple cube in space", "fails to recog…

I don't think the bar is set at 100% autonomy. I think he's saying it will be possible your car can do those things and probably do them safer than a human, there will still be edge cases for many years I'm sure. I do think blizzards are unlikely to be solved soon but that's a very small % of driving that humans are also bad at.

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

#87

Post by scarmig »

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.

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

#88

Post by zaroth »

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…

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 all around you and keep situational awareness of the drivers around you while the car keeps itself in lane. It’s a totally different experience.

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

#89

Post by matthewdgreen »

rootusrootus wrote: post #81
matthewdgreen wrote: post #45

Earlier quoted context omitted.

The vision problems are real. But the ability to handle ice/snow-induced wheel spin and slew seems like exactly the kind of problem that can be handled with sensitive electronic traction control, perhaps augmented with accelerometers. That specific problem doesn't seem intrinsically more complicated than, say, keeping a drone level on a breezy day -- which is something machines already do much more reliably than huma…

Traction/stability control can only help with the situation you are already in. Being able to see the condition of the road -- the sparkle of ice forming, for example, or a sheen that suggests black ice, etc -- allows you to act instead of just react.

While vision is a hard problem in general, the specific challenge of "ice detection" seems like exactly the kind of problem that computers can be programmed to do better (and more tirelessly) than humans, particularly with specialized detectors and LIDAR. Better sensors, better reaction time, zero distractions. (I don't have any expertise here, just intuition.)

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

#90

Post by close04 »

zaroth wrote: post #88
FireBeyond wrote: post #77

Earlier quoted context omitted.

> 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…

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…

> The difference between having to steer the car and not having to steer the car is extreme

Assuming you keep your hands on the wheel as required what exactly is the difference? I only found it to be a distraction as it takes me considerably longer to reengage (in less than expected situations) as the human driver after a period where I just let go a little.

Post reply on HN