Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Stanford's Self Driving Car Tops 120mph On Racetrack

timothy posted more than 2 years ago | from the really-fast-baby-on-board dept.

AI 97

kkleiner writes with this snippet: "Just as Google's self-driving Prius goes for distance, recently passing 300,000 miles, Stanford's self-driving Audi TTS instead has the need for speed. The Audi, known as Shelley, sped around the Thunderhill Raceway track north of Sacramento topping 120 miles per hour on straightaways. The less than two and a half minutes it took to complete the 3-mile course is comparable to times achieved by professional drivers." Now if only Montana could take a cue from Nevada's rules for self-driving cars, and bring back "reasonable and prudent" speed regulation, driving out west could get a lot more exciting.

cancel ×

97 comments

Sorry! There are no comments related to the filter you selected.

Montana needs Montana's rules? (2)

homsar (2461440) | more than 2 years ago | (#41066893)

I believe that the link "Montana's rules for self-driving cars" should have read "Nevada's rules for self-driving cars".

Re:Montana needs Montana's rules? (2)

timothy (36799) | more than 2 years ago | (#41067155)

You're right -- sorry.

I blame cerebral flatulence.

Do they drink ethanol (1)

Anonymous Coward | more than 2 years ago | (#41066919)

I wish I had a robot car.

Re:Do they drink ethanol (0)

Anonymous Coward | more than 2 years ago | (#41067871)

Ever since I was six.

More exciting? (0)

ickleberry (864871) | more than 2 years ago | (#41066927)

[quote]driving out west could get a lot more exciting.[/quote] Nothing exciting about sitting in a driverless sh1tbox and probably soaking up pre-made entertainment content and a few Google targetted ads. Would rather drive the thing myself, despite the miniscule chance of me crashing into a people carrier with 6 kids inside and killing everyone including myself

Re:More exciting? (3, Insightful)

kaspar_silas (1891448) | more than 2 years ago | (#41067089)

Damn straight, why worry about the safety of yourself or others when you can be having fun.

For Americans death by car accident is about a 1 in 100 lifetime chance not massive but hardly minuscule. If you could say half that is that not a reasonable thing to do.

Thou of course everyone is an above average driver so the odds don't apply to them.

Re:More exciting? (1)

Magada (741361) | more than 2 years ago | (#41067317)

It's huge, to be sure. But then you get into the causes of lethal accidents and you realize that it dwindles to insignificance if you're not an asshat (no DUI, no major breaches of traffic laws).

Re:More exciting? (1)

kaspar_silas (1891448) | more than 2 years ago | (#41067593)

So you think that lethal accidents are caused by a minority of very bad drivers. Very bad as in not mere speeding or not paying attention as almost everyone does occasionally. That would be interesting if true. Do you have any stats. or links to back that up?

I would (perhaps naively) have assumed that most types of non trivial road accidents have a chance of lethality. So I wouldn't expect those involved in lethal accidents to have a significantly different ability distribution to normal accidents.

Re:More exciting? (4, Informative)

cduffy (652) | more than 2 years ago | (#41068331)

I don't know the statistics for motor vehicles, but for bicycles, the common accidents are motorist-at-fault but avoidable by following best practices on the part of the cyclist (typically right-hook and left-hook, avoidable by things like proper lane positioning -- taking the lane rather than trying to ride in the gutter to avoid encouraging motorists to pass unsafely, using positioning to encourage drivers making right turns at an intersection to go behind rather than in front of you, etc) or cyclist-at-fault and thus avoidable (riding at night without lights, riding on the wrong side of the street, running intersections), and only a very tiny percentage are motorist-at-fault and unavoidable (ie. the "struck from behind while riding safely and properly" accident that everyone worries so much about... has a high chance of being lethal should it happen, but frequency is almost negligible).

That said -- I'm curious as to whether the parent's asserted statistics more correctly refer to the party at fault in lethal accidents as opposed to the parties harmed in accidents. My suspicion would be very much the former.

Re:More exciting? (1)

DarwinSurvivor (1752106) | more than 2 years ago | (#41078591)

I don't know where you live, but where I am "very bad drivers" is NOT in the minority!

Re:More exciting? (1)

kaspar_silas (1891448) | more than 2 years ago | (#41146835)

Okay "very bad" -> "far below average".

Re:More exciting? (2)

GameboyRMH (1153867) | more than 2 years ago | (#41068671)

That makes cars far more dangerous than terrorists, which you've blown about a trillion dollars on over the last decade or so. Universal adoption of driverless cars should be your #1 national priority.

Re:More exciting? (1)

tyrione (134248) | more than 2 years ago | (#41078163)

Damn straight, why worry about the safety of yourself or others when you can be having fun. For Americans death by car accident is about a 1 in 100 lifetime chance not massive but hardly minuscule. If you could say half that is that not a reasonable thing to do. Thou of course everyone is an above average driver so the odds don't apply to them.

1 in 100 my ass. You have more than 240 million cars in daily circulation, just in the United states. Over the course of a year the total number of cars active is 200 million+ times 365 days. Out of those total vehicle transactions 40,000 fatalities and you come up with 1 in 100? Fail. Try 1 in 1,825,000 auto transactions per year or less result in a fatality. Of course, the total train fatalities were 10 last year and yet no one seems to realize how a mixed use of both would actually reduce your odds of being in a fatal car accident either.

Re:More exciting? (1)

Anguirel (58085) | more than 2 years ago | (#41088407)

I don't even know how to express auto-transactions per year in a life-time chance per person. Here, try something like this:

(~40k people / year) / (~310M total population) * (~78 years life expectancy) = ~1% lifetime chance for an auto fatality, or 1 in 100

I also tried it as (1 - ((~40k people / year) / (~310M total population)) )^78 = ~98.9% chance to not die each year for 78 years, which is once again ~1%, or 1 in 100. I think the original number is technically correct, though I won't claim to be the best at probabilities in math, especially with this sort of strange semi-malleable data set, and it really isn't terribly accurate in the end due to the number of changes that will occur over that lifetime... Anyway, how about a 1 in 7750 chance per year? That matches your ~40k fatalities (which I'm assuming is yearly), and the ~310 million current U.S. population.

Re:More exciting? (0)

Anonymous Coward | more than 2 years ago | (#41067435)

When out West, if it's not a Lotus, Lamborghini, or Porsche, I would rather sleep...

Check out this boring road [google.com] - reminds me of desert bus.

Re:More exciting? (1)

eln (21727) | more than 2 years ago | (#41069005)

Agreed. Driving out west involves vast distances on straight roads. Sometimes the scenery is cool, sometimes it's flat and boring. I'd love to be able to drive through and admire the scenery when it's nice instead of having to pay attention to the boring stretch of asphalt I'm on, and be able to nap when the view sucks. If I wanted an adrenaline rush with my driving, I'd go to the race track.

Re:More exciting? (1)

oddaddresstrap (702574) | about 2 years ago | (#41071027)

Nah, the adrenaline rush comes when you're napping and the car's computer has a kernel panic.

Re:More exciting? (1)

M1FCJ (586251) | about 2 years ago | (#41071857)

This explains American's love of Harleys. Goes fine in a straight line... First corner, not so much fun.

Re:More exciting? (1)

riT-k0MA (1653217) | more than 2 years ago | (#41081661)

Hey, that reminds me of somewhere [goo.gl] .

Re:More exciting? (0)

mcgrew (92797) | more than 2 years ago | (#41068627)

Nothing exciting about sitting in a driverless sh1tbox and probably soaking up pre-made entertainment content and a few Google targetted ads.

*sigh* You remind me of the old Pontiac commercials, "we build excitement." I always took that to mean "the brakes are bad and the handling is shit."

If the car is driving itself, you're free to watch the scenery go by, read a book, take a nap.

Would rather drive the thing myself, despite the miniscule chance of me crashing into a people carrier with 6 kids inside

The risk is hardly miniscule, considering that 40,000 people die on American highways every year. Exciting enough for you, son? If you want even more excitement, next time you see a cop, floor it!

Re:More exciting? (1)

gstoddart (321705) | about 2 years ago | (#41071553)

The risk is hardly miniscule, considering that 40,000 people die on American highways every year. Exciting enough for you, son?

Yeah, but if you look at Causes of Death [wikipedia.org] in the US, that translates into a fairly small (relatively speaking) amount.

More people die in the US from malaria than traffic accidents.

Unless all of the cars get switched over to this, you're still going to have to deal with the randomness of other drivers. And there's simply no way that everyone in the US is going to agree to buy a new car to get them all self driving and therefore safer.

These wouldn't be a magic bullet. And, really, if I'm just going to sit in a self-driving car and read a book or whatever, I'd be better off taking the train or flying. At least they have bathrooms. This is the worst of both worlds -- crammed into a small car and having nothing to do with the driving.

However, I would agree that the way people drive is a huge factor in traffic deaths -- people do amazingly stupid things when behind the wheel. But I still think it would be cheaper to go with rail transit instead of the massive spending which would need to happen to get everybody into autonomous cars.

Re:More exciting? (1)

mcgrew (92797) | more than 2 years ago | (#41080589)

As another poster noted, there are few vehicle deaths in places with few vehicles and poor sanitation. According to the wikipedia link another commenter posted, auto accidents rank fifth in industrial countries. More people die of vehicle accidents than suicide, and murder wasn't even in the top ten.

Driving to work is the most dangerous thing an office worker do.

actually is less surprising to me than Google's (4, Interesting)

Trepidity (597) | more than 2 years ago | (#41066951)

I would expect a computer-controlled car to do well in these kinds of situations. On a fixed course with no other cars, it comes down to calculating the optimal trajectories, and being able to accurately estimate things like when your tires are about to lose traction. Computers are probably better at that than humans are, given enough data. I mean, cars and tired are already designed with computer simulations of those kinds of conditions.

Google's self-driving cars being able to drive in regular traffic was more of a surprise to me: something I would've have expected for another decade.

Re:actually is less surprising to me than Google's (4, Interesting)

hey! (33014) | more than 2 years ago | (#41069035)

And I expect computers on the road will get better the higher percentage of computer-driven cars there are on the road. The reasons is that people are very good at predicting the behavior of other people. Just the other day I was driving on the interstate in moderate, fast moving traffic and I saw a guy pull up behind a car in the right lane. "Watch this guy," I said to my wife, and sure enough he changed lanes, pulled up to within two feet of the car in front of me (at 70 mph) and cut in front of the first car with hardly a foot to spare. It was exactly what I'd expected him to do, based on the speed with he approached and the kind of car he was driving.

Of course a lot of predictive heuristics about human behavior could be programmed into an automated system. One of them might be recognizing the slow reactions of distracted drivers. As I approach intersections these days I'm always on the lookout for someone on the cross street who is not slowing as soon as he should. Frequently these are drivers on cell phones who not only miss the stop line, but end up well into the intersection before they start looking for traffic.

A robotic driver would be consistently aware and prudent. I suspect well before the point where a robot driver is as good as an average driver (if we aren't there already), we'd reach the point where the roads would be safer if all cars were robot piloted, simply by removing human inconsistency.

Re:actually is less surprising to me than Google's (0)

Anonymous Coward | about 2 years ago | (#41069833)

A robotic driver would be consistently aware and prudent. I suspect well before the point where a robot driver is as good as an average driver (if we aren't there already), we'd reach the point where the roads would be safer if all cars were robot piloted, simply by removing human inconsistency.

And the average driver-now-demoted-to-passenger of the robotic cars would be annoyed to hell and back about the fact that the car follows the speed limit and never takes chances they would have taken.
Before long the annoyed driver will be so worked up that he sets the system to manual and floors it.

Re:actually is less surprising to me than Google's (1)

Anonymous Coward | about 2 years ago | (#41072117)

Why would they be annoyed when the speed limit for an all robot driving force could be so much faster than it is now? As for, "not taking chances", robotic cars would likely be able to move much closer to each other and in concert with each other to get each vehicle where it needs to be much more efficiently than people ever could. There wouldn't be a need to take chances.

Re:actually is less surprising to me than Google's (1)

Leinad177 (2708661) | more than 2 years ago | (#41120993)

we'd reach the point where the roads would be safer if all cars were robot piloted, simply by removing human inconsistency.

And what happens if the driving program freezes while you are at 100km/ph? A single bug can end lives.

Please put a second car on the track (3, Interesting)

Maxo-Texas (864189) | more than 2 years ago | (#41066959)

I'd really like to see a video of that. How do the cars adapt.. or fail to adapt.

What's the point of failure or do they all behave prudently as more and more cars are on the track?

Re:Please put a second car on the track (2)

interfecio (1023595) | more than 2 years ago | (#41067091)

2nd human driver? Or another computer driven car? There would be nothing exciting about having two computer driven cars on the track driving 120mph. It would only be impressive to see the cars drive side by side the entire time without touching, or in line like a train.

Re:Please put a second car on the track (3)

Intrepid imaginaut (1970940) | more than 2 years ago | (#41067895)

120mph no. 320mph, yes. I'd love to watch a race between completely maxed out robot vehicles tearing around the place autonomously at speeds that would make human drivers infeasable. Even better, put guns on them!

Re:Please put a second car on the track (1)

GameboyRMH (1153867) | more than 2 years ago | (#41068735)

Landspeed cars break 320mph while driven by humans, but there's no car yet that could go around even a large track at any such speeds. Completely surpassing human drivers won't be so easy.

Re:Please put a second car on the track (1)

GameboyRMH (1153867) | more than 2 years ago | (#41068711)

I saw the video, the big problem is that the steering inputs aren't smooth, in a corner the wheel is constantly sawing back and forth. They're working on fixing this now by monitoring professional drivers' brainwaves as they drive the course (not sure how that will help, I was thinking a smoothing algorithm would do).

Re:Please put a second car on the track (0)

Anonymous Coward | about 2 years ago | (#41073223)

They should call my brother, he already worked that one out, even if he didn't realize it.

Right Eric?

Re:Please put a second car on the track (1)

slinches (1540051) | about 2 years ago | (#41070763)

Based on my experience with the Gran Turismo driving simulator software, the computer controlled cars would strictly hold to the optimum racing line regardless of whether you're overtaking on the inside of a sharp corner or not. Of course, it won't matter since neither car will suffer any damage from the impact.

Montana rules (1)

Anonymous Coward | more than 2 years ago | (#41066981)

Speed limits are for tourists and drunks.

Re:Montana rules (1)

Anonymous Coward | more than 2 years ago | (#41067145)

And people who don't want to kill pedestrians or cyclists [humantransport.org] . If you hit a pedestrian at 5 mph, there is a 5% chance of death. If you hit a pedestrian at 40 mph, there is an 85% chance of death.

Considering that cities are trying to become more cyclist friendly, perhaps we need to think about trying not to kill them. You may feel like a big man driving 35 mph in a 25 mph zone, but if you only have a split second to slow down 5 mph in each case, the death rate is ten times higher than driving the speed limit.

TYPO (0)

Anonymous Coward | more than 2 years ago | (#41067223)

That is a 5% chance of death at 20 mph and a 45% chance of death at 30 mph. Higher than that it plateaus near certain death.

Re:TYPO (4, Funny)

CrankyFool (680025) | more than 2 years ago | (#41067307)

Yes, well it does seem rather ... intuitively obvious that it never actually exceeds certain death.

Re:TYPO (2)

Antarius (542615) | more than 2 years ago | (#41067581)

Au contraire, once you're driving 150mph, the scale inverts and the cyclists start having chances of Undeath.

If these self driving cars are going to be allowed to travel at 200mph, we're going to be seeing zombie cyclists everywhere!

Re:TYPO (1)

GameboyRMH (1153867) | more than 2 years ago | (#41068773)

Depends on the car, are we talking a Yugo or an F1 car?

Re:TYPO (1)

GameboyRMH (1153867) | more than 2 years ago | (#41068801)

D'oh didn't realize we're talking pedestrian safety. Well in that case are we talking an F1 car or a new S-class?

Re:Montana rules (1)

Bigby (659157) | more than 2 years ago | (#41067529)

Speed limits were always set in pedestrian areas.

Re:Montana rules (1)

MetaDragon (2098352) | about 2 years ago | (#41069697)

Considering that cities are trying to become more cyclist friendly

Citations? I know of exactly 0 cities within my geographic vicinity that have expressed such an intention.

Re:Montana rules (1)

Anguirel (58085) | more than 2 years ago | (#41088565)

It would help to know your geographic region. I'll give you Denmark [nytimes.com] and theUnited States [usatoday.com] . I specifically chose normal news sites, rather than eco- or cycling-specific news sources, but there's a lot more out there on similar sorts of movements in many municipalities across several nations, including moves to create pedestrian and cyclist only downtown regions.

Re:Montana rules (0)

Anonymous Coward | about 2 years ago | (#41075531)

You may feel like a big man driving 35 mph in a 25 mph zone, but if you only have a split second to slow down 5 mph in each case

then your problem is not driving at 35, but not paying sufficient attention to the road. 35 in a 25 is a bad idea, yes, but accidents are almost always caused by inattentiveness rather than outright speed.

Re:Montana rules (0)

Anonymous Coward | more than 2 years ago | (#41078127)

If you hit a pedestrian at 5 mph, there is a 5% chance of death. If you hit a pedestrian at 40 mph, there is an 85% chance of death.

The lethality of a collision has just as much to do with the mass of the vehicle as the speed at which it is moving. I've ran into plenty of shit on my bicycle going well over 5 mph and had only minor bruising. I've swung my fist in excess of 50mph and not killed anybody with it.

You may feel like a big man driving 35 mph in a 25 mph zone

State highways (in MT) are never marked lower than 55mph except for when they go through a town or city, and in most places it's 75mph for regular vehicles. The "reasonable and prudent" law only applied to State highways, not city streets or federal roads.

And the problem we had with the limit was mostly due to morons from out of state coming up here to try and drive 180mph in their flashy sports cars. The other problem is that there isn't a good definition of what constitutes "reasonable" or "prudent" so it's hard to prosecute people for reckless driving.

But the guy you have to worry about isn't the heavy-footed highway driver, it's the people who drive in town. It's the soccer mom going to the mall in her minivan with 12 screaming kids and 3 ringing phones, who has a head full of prescription pills. It's the drunk leaving the bar at 1:30AM on his way to the gas station to get a six pack for the house party. It's the old lady who confuses her gas and brake pedals. It's the kids from the high school trying to make it to the fast food place and back in 20 minutes on their lunch "hour". It's the guy who just is a plain old shitty driver.

BMW Track Trainer (2)

Aphonia (1315785) | more than 2 years ago | (#41067055)

Isn't this roughly BMW's track trainer? http://www.autoblog.com/2007/12/11/bmw-330i-races-around-the-top-gear-track-without-a-driver/ [autoblog.com]

Seems like it did impressively well on the top gear test track, but a 330i is much slower than a TTS... (Clarkson does mention you can fit it to a M3 though)

Stop and Go (1)

jasper160 (2642717) | more than 2 years ago | (#41067087)

I would like to see them test their robot cars in the congested downtown streets of a large city. With the window washers too.

Re:Stop and Go (1)

tgd (2822) | more than 2 years ago | (#41067153)

Clearly you've never been to San Francisco, where Google did much of its 300,000 miles.

Tourists, dirty hippies, hipsters, you name it, they're walking around in the street looking to be hit.

Re:Stop and Go (2)

vbraga (228124) | more than 2 years ago | (#41067475)

I hope Google coding team gets a bonus when the car runs over a hipster :-)

Re:Stop and Go (0)

Anonymous Coward | about 2 years ago | (#41070697)

Well not exactly, but they do get a bonus for iPhone/iPad/MBP users so there is quite a lot of overlap with the hipsters.

Reasonable and prudent (5, Informative)

longhunt (1641141) | more than 2 years ago | (#41067147)

I grew up in Montana under the "reasonable and prudent" speed limit. Man, I miss those days. The problem was that too many tourists came in that didn't know the roads and got themselves killed, so the feds threatened to yank our highway money unless we changed the law. Unless you can do away with either the Federal government or idiot tourists, it's probably not coming back.

Re:Reasonable and prudent (1)

Anonymous Coward | more than 2 years ago | (#41067293)

I had myself a high speed adventure in a desert state a few years back. I found a stretch that was perfectly straight for over 5 miles on a slight decline so visibility was over 20 miles. I drove the course, dropped off my buddy to act as a spotter with binoculars and a walkie talkie, backed up 3 miles and floored it until redline in 5th. The car started getting floaty so I didn't want to reach down to shift to 6th. And of course there were no other cars in sight. I'd say thats about as reasonable and prudent as you can get.

Re:Reasonable and prudent (1)

Anonymous Coward | more than 2 years ago | (#41067351)

Bullshit. The law was changed because it was challenged in court as being too vague. The Montana Supreme Court ruled that there had to be a numerical limit in order to charge people with speeding as "reasonable and prudent" violated due process. The Montana government didn't even call a special session for the legislature. They waited a few months until a regular meeting (during such time there was no speed limit, not even a "reasonable and prudent" one) and then enacted a 75 mph limit. The Federal government had no impact. That is a myth trying to slime the Federal government. There are enough real reasons to dislike the Federal government, why do you have to invent fake ones?

Re:Reasonable and prudent (3, Informative)

BigT (70780) | more than 2 years ago | (#41068225)

That was in '98. OP is talking about in the 70's when all states were required by the feds to have a 55 MPH speed limit or lose highway funding.

In '97-'98 there were way too many idiots on the roads thinking 120 mph was reasonable and prudent. Even on the twisty 2 lane roads.

Re:Reasonable and prudent (1)

Tekfactory (937086) | about 2 years ago | (#41072471)

I was in Montana on a networking gig in 97, we did 90 everywhere on the highway. Never saw a police car on the interstate they were all in town responding to real crimes. Story I heard was there was a dealership in Colorado letting folks test drive the fast cars over in Montana. Also heard that if you did get pulled over real tickets started at $300.

Re:Reasonable and prudent (0)

Anonymous Coward | more than 2 years ago | (#41078713)

Bullshit. The law was changed because it was challenged in court as being too vague.

Well, yes and no. The only reason it ended up in court was because some guy who drove race cars for a living got busted doing something like 150 and the cop said that "It's never reasonable or prudent to drive that fast." The courts eventually decided that the vague definition of what is reasonable isn't valid, even though the courts have upheld, and continue to uphold, that you can be charged with driving "faster than is safe for the conditions of the road" even when you're under the marked speed limit.

shrug.

The Federal government had no impact. That is a myth trying to slime the Federal government.

Actually we were getting leaned on pretty heavily by the Feds, and because people were crossing state lines to drive here they were making a lot of bad noise about trying to yank our highway funding.

They waited a few months until a regular meeting (during such time there was no speed limit, not even a "reasonable and prudent" one) and then enacted a 75 mph limit.

And that's not true at all.

Re:Reasonable and prudent (4, Funny)

Fwipp (1473271) | more than 2 years ago | (#41067357)

Montana has tourists?

Re:Reasonable and prudent (0)

Anonymous Coward | more than 2 years ago | (#41067669)

> Montana has tourists?

A reasonable and prudent question IMHO.

Re:Reasonable and prudent (0)

Anonymous Coward | about 2 years ago | (#41073301)

Yes, that's where Glacier National Park is located.

They're right about it being a featureless plain with a small hill on the horizon that gets taller as you drive towards it.

Re:Reasonable and prudent (0)

Anonymous Coward | more than 2 years ago | (#41078739)

Yes, that's where Glacier National Park is located.

They're right about it being a featureless plain with a small hill on the horizon that gets taller as you drive towards it.

We also have a little bit of Yellowstone, a lot of people come in/out of the park through MT.

And just FYI, that "small hill" is the continental divide, and is one of the highest points on the continent. Only the eastern half of the state is plains, the western half is all mountains. I do have to say you're the first person I've ever heard call Montana "featureless" and manage to keep a straight face. We get a ton of tourism, but more of the outdoors variety.

Not to take away too much, but... (3, Interesting)

spagthorpe (111133) | more than 2 years ago | (#41067273)

Racetracks are known quantities, down to every minute detail. Back in the 90s, when the F1 cars were loaded with every possible form of electronics, the computer was programmed with every turn on every track. All the driver had to do was stomp on the gas and let the car handle the maximum traction, braking, etc for every place on the track. Even the prime steering track can be programmed in. Ever played any of the more recent driving simulations?

I can appreciate the achievement to some extent. The ability to sense where it is, and things of those nature are impressive to me, but lets see how the car would do in a pack of other drivers where conditions weren't always ideal. If you could convince other race drivers to get on the track with it.

Re:Not to take away too much, but... (4, Interesting)

Krneki (1192201) | more than 2 years ago | (#41067409)

First learn to walk, then you learn how to run.

For AI is the same, don't worry soon it will outrun, outpace, ... and make you completely useless. But it's ok.

On car topic: I can't wait for this to be a safety feature, Imagine, you drive full throttle down the road, but you miss-judged a corner, the AI, with light-speed reaction time understand that you can't make it at that speed and applies the little correction you need to make it through. It's the same, with traction-control, ABS, ... this will just be the next logical step.

Re:Not to take away too much, but... (0)

smooth wombat (796938) | more than 2 years ago | (#41067681)

you drive full throttle down the road, but you miss-judged a corner, ... and applies the little correction you need to make it through.

So you want the AI to keep people alive who don't know how to drive safely? You want to thwart evolution and allow the stupid/careless/whatever to be able to keep reproducing?

We have enough hippos going to Wal Mart, we don't need to keep the herd growing. A little culling now and then will do the trick.

Re:Not to take away too much, but... (1)

Anonymous Coward | more than 2 years ago | (#41067821)

Yeah, the obvious problem with that is bad drivers tend to take out good drivers while they are at it. Many times they take out the good drivers without themselves kicking the bucket. Especially if they are driving a huge gas guzzling tank while the good driver is driving a fuel efficient compact.

Re:Not to take away too much, but... (1)

Anonymous Coward | more than 2 years ago | (#41067855)

We have enough hippos going to Wal Mart, we don't need to keep the herd growing. A little culling now and then will do the trick.

A shame that the culling all too often involves collateral damage, wouldn't you say ?
Try thinking a little more before making such a statement again.

Re:Not to take away too much, but... (1)

KingMotley (944240) | more than 2 years ago | (#41068475)

The obvious solution is an AI with a self-destruct.

Re:Not to take away too much, but... (0)

Anonymous Coward | about 2 years ago | (#41071835)

      What about the bus full of attractive sleeping professional stunt drivers oncoming in the other lane on their way back from a stunt driving convention that would get hit by your one bad driver were it not for the technology to save them? In the end human lives are measured in dollars, not arbitrary herd survival fitness whims.

Re:Not to take away too much, but... (1)

hey! (33014) | more than 2 years ago | (#41069063)

First learn to run, then learn to walk through a room full of furniture, then learn to walk through a hallway full of morons talking on their cell phones.

not that impressive (5, Informative)

SuperBanana (662181) | more than 2 years ago | (#41067311)

Sigh, I've been reading a lot of stories now about Stanford tooting their horn about this...and they just can't seem to stop blabbing about how they're "as good as a human driver". Bullshit.

I have quite a bit of HPDE [wikipedia.org] experience.

First off, quoting times around the track is silly unless it was in the same car. Which it wasn't. However, if you want to see what "fast" is, look at the SCCA records [sfrscca.org] for various classes. Spoiler: lap times of 1:39 to 2:12. Read that again: the absolute slowest competitive race time is 2:12, and that was done by someone in a Mazda Miata in a stock racing class (ie, limited modifications.) The Stanford car has more than 100HP over the Miata, all wheel drive, big brakes, and a dual-clutch gearbox that shifts virtually instantly.

120MPH sounds impressive, until you realize that we're talking about a nearly 270HP car and a very open track. [thunderhill.com] 120MPH isn't that hard to hit on many racetracks, even for a novice, and it's not a demonstration of skill; what's a demonstration of skill is how fast you exit each turn. Just by looking, I can tell you the fastest part of the track is between turn 8 and 9, most likely, for high-powered cars; slower, lighter cars may be faster between 9 and 10.

Second: "professional driver" could mean anything from someone who drives a taxi, to someone who races dirt-track, to someone who races Formula 1. Anyone can call themselves a "professional driver."

Third: the way that thing drives itself is absolutely atrocious and reminiscent of the worst kind of first-day HPDE students. The ones who think they know how to drive, don't, and are aggressive. Hammers it down the straights, not smooth with the controls at all, misses the apex (the inside center of the turn) by half a dozen feet, overloads the tires (hear them screaming? That's not a "I'm giving you the most grip" noise, that's a "I'm past my limit and am sliding all over the place" noise)...ugh.

From the way the car dives and rolls, as well as how the 'driver' is thrown around and the steering wheel is jerked - there is absolutely no finesse, and that is critical for driving fast.

Lastly: "For example, the math involved in getting a spinning wheel to grip the pavement is very similar to recovering from a slide on a patch of ice. "If we can figure out how to get Shelley out of trouble on a race track, we can get out of trouble on ice," Gerdes said."

Haha, no. Pavement, ice, dirt, and snow all have very different characteristics and "getting out of trouble" on them is different. Effin' Californians... Spend a winter in Vermont, then tell me about how to drive on ice.

Re:not that impressive (1)

Quiet_Desperation (858215) | more than 2 years ago | (#41067443)

Third: the way that thing drives itself is absolutely atrocious

Oh, woe, my dancing, talking bear can't sing an aria!

Re:not that impressive (1)

Kokuyo (549451) | more than 2 years ago | (#41068047)

Well, then don't go bragging how your bear can do everything. It obviously can't. That doesn't reflect negatively on your bear as long as you don't give people false expectations.

Re:not that impressive (1)

Quiet_Desperation (858215) | more than 2 years ago | (#41069353)

-.-

Re:not that impressive (0)

Anonymous Coward | more than 2 years ago | (#41078797)

Well, then don't go bragging how your bear can do everything. It obviously can't. That doesn't reflect negatively on your bear as long as you don't give people false expectations.

They didn't say it can do everything, they didn't even imply that. And surprisingly, neither did the summary. You got butthurt that you were called out for trying to downplay a rather impressive feat for a piece of software.

As for the way it drives being "atrocious", if you'd read the article they talk about how they're working on improving the track times by making the AI drive smoother and more like human drivers.

in other words, go fuck yourself.

Re:not that impressive (1)

FatAlb3rt (533682) | more than 2 years ago | (#41068091)

Gee, maybe they should just give it up. Or maybe you should take the lead.

Re:not that impressive (4, Insightful)

CaptainLard (1902452) | more than 2 years ago | (#41068119)

I have some HPDE experience of my own and what you're basically describing is how a beginner drives on a race track. I don't know how many "track days" the standford team has done (or can afford for that matter...renting out the whole track is probably a large part of their budget) but I'm guessing the car is more or less a beginner. Once it's done a few events I'm sure it will be trail braking, hitting apexes and tracking out just fine. The real question is when will it be able to acknowledge corner workers and other cars?

Re:not that impressive (1)

TheMiddleRoad (1153113) | more than 2 years ago | (#41068179)

I circle Thunder Hill at about 2:30. I'm a shit driver in a 4000lbs luxury car who way overbrakes. I figure my car is capable of a 2:15.

Re:not that impressive (1)

nschubach (922175) | more than 2 years ago | (#41068807)

someone in a Mazda Miata in a stock racing class (ie, limited modifications.) The Stanford car has more than 100HP over the Miata, all wheel drive, big brakes, and a dual-clutch gearbox that shifts virtually instantly.

The MX5/Miata routinely competes with much bigger and more powerful cars. It's renowned for it's handling and ability to take corners at much higher speeds than the bigger heavier and more powerful cars.

Re:not that impressive (0)

Anonymous Coward | about 2 years ago | (#41070129)

Stock Miatas are quick, and Spec Miatas are no slouch, that's for sure. The right drivers at our local tracks are able to give me trouble in the highly technical areas of our local tracks (my track car is stock-ish C6 Z51 on 140-treadwear DOT-approved tires with a full set of track pads and rotors, maybe ~415 at the crank). But Thunderhill isn't Hockenheimring or Monaco - it's a fairly wide-open track, more like Road America. I've got 1,000 pounds on the Spec Miata guys, but all that weight and sticky tires doesn't help them as much through high-speed cornering.

I understand his frustration - having a fair amount of HPDE experience myself and being that most of my life outside of work orbits around an automotive obsession. Automated cars are a serious threat (probably the wrong word, or at least the wrong connotation) to my hobby and the things I love doing the most - namely, driving. I suppose it was inevitable, and I know we'll still have tracks, but I love my morning commute in my old CTS-V. I don't want to be a Luddite, but I'll be really sad to see it go.

Re:not that impressive (1)

KozmoStevnNaut (630146) | more than 2 years ago | (#41078677)

Yeah, "threat" may be a strong word, but it is an upsetting force in regards to being able and allowed to drive your own cars.

I don't have any HPDE experience myself. People tell me that I am a very good, responsible and occasionally spirited driver, for whatever that's worth. I also ride motorcycles and understand braking zones, ideal cornering lines, grip levels etc., and I volunteer on the track construction team for a local historic racing event. Again, for whatever that's worth.

My car is not nearly as fast or powerful as a CTS-V, but it is a very well-sorted car that handles good without resorting to electronic helpers and is immensely fun to drive. I would be very sad if the ability to drive my own car was taken away from me, even if it is just a 160HP Peugeot 406.

I think what you and I both fear from automated cars is the end of being involved. I like being a part of making my car go down the road. I like changing gears, feeling the clutch engage and the feedback through the steering wheel when I navigate corners in a spirited fashion. I like knowing that I'm in control and that my skill is instrumental in making my car perform the way it should.

Prior work: 100 mph on straightaways (0)

Anonymous Coward | about 2 years ago | (#41069603)

I'm posting anon and being vague so I don't get anyone in trouble, but a former colleague once took an autonomous car to 100 mph on a straightaway. This was around the turn of the century, not on a race track, and the vehicle was definitely -not- a sports car. The data trace was presented in m/s so the non-engineers in the room wouldn't realize how fast he went.

The problem with montana (2)

doug141 (863552) | more than 2 years ago | (#41067331)

was european driving tourists coming over and assuming the higways were autobahn quality (not even close) and dying after flying off a bump. Montana realized that their highways weren't safe above 85 and posted it.

Re:The problem with montana (-1)

Anonymous Coward | more than 2 years ago | (#41067645)

european driving tourists coming over and assuming the higways were autobahn quality (not even close) and dying
 
I fail to see the problem here...

Re:The problem with montana (1)

dkleinsc (563838) | more than 2 years ago | (#41067971)

It hurts GDP for tourists to die before they've spent all their money on useless stuff made in China saying "I Love Montana".

I wonder how the public will react (2)

doug141 (863552) | more than 2 years ago | (#41067375)

to a visually spectactular, high speed, failure and breakup of a driverless car. One way they will react is to play the footage over and over, that's for sure.

what about the courts will the coders have to (1)

Joe_Dragon (2206452) | more than 2 years ago | (#41067411)

what about the courts will the coders have to give testimonies and can they be a risk of going to prison due to poor coding that leads to some one dieing?

Owdi (1)

Quiet_Desperation (858215) | more than 2 years ago | (#41067417)

Well, Stanford wins on car choice, at least.

Reasonable and Prudent Won't Happen..... (1)

Anonymous Coward | more than 2 years ago | (#41067641)

"Reasonable and Prudent" was nixed when someone was given a speeding ticket and challenged it in court. The court held that "reasonable and prudent" was arbitrary and what one police officer thought was "reasonable and prudent" was not necessarily what another officer would think and that there was no way for a citizen to feel confident that they were within the bounds of the law. (I.e., What if you had gone through advanced drivers training??? Does that mean you can go faster?)

Along these lines, I'm waiting for someone to challenge the catch all charge "Disorderly Conduct" which you can be nabbed for just walking down the street at the wrong time and thousands of innocent people get caught in this catch all charge annually.

The robot will eventually become unbeatable (1)

kaspar_silas (1891448) | more than 2 years ago | (#41067715)

The main advantage of computer driven cars is that they learn faster than humans. A human is at a massive learning disadvantage as he can't exactly replicate his actions, recall his sensory input perfectly, vary aspects of his driving without affecting other aspects nor make changes that are smaller than his biologically imposed resolution limit. The computer can learn more from every previous race and try more things in the search for lower lap times. After sufficient versions/updates (and assuming a sporting governing body doesn't implement blocking rules) the AI's ability will exceed the upper limit imposed by the biology of the driver.

I can't see any other way this could possible work out.

My automated car reaches 200 MPH on a straight (2)

tommeke100 (755660) | more than 2 years ago | (#41068051)

I call it "THE BRICK" !

Re:My automated car reaches 200 MPH on a straight (1)

ThatsMyNick (2004126) | about 2 years ago | (#41070463)

Can it also turn at accelerate back to 120 mph on the next straightway? Impressive!

120 mph on the "straightaways"? (2)

wonkey_monkey (2592601) | more than 2 years ago | (#41069121)

topping 120 miles per hour on straightaways

Enquiring minds want to know how fast it took the bendaroonies.

Only a 2:30 in a new TTS? (1)

WebMasterP (642061) | about 2 years ago | (#41070933)

A 2:30 seems like a terrible time to me. I did a 2:40.312 [mylaps.com] in an old Festiva with a busted engine and severely compromised rear suspension on janky old street tires.
Check for New Comments
Slashdot Login

Need an Account?

Forgot your password?