Slashdot Mirror
Stanford's Self Driving Car Tops 120mph On Racetrack
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.
I believe that the link "Montana's rules for self-driving cars" should have read "Nevada's rules for self-driving cars".
I wish I had a robot car.
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.
10 PRINT CHR$(205.5+RND(1)); : GOTO 10
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?
She was like chocolate when she drank... semi-sweet at first and then increasingly bitter.
Speed limits are for tourists and drunks.
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/
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)
I would like to see them test their robot cars in the congested downtown streets of a large city. With the window washers too.
No good deed goes unpunished.
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.
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.
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.
WWJD -- What Would Jimi Do?
(Smash amp, burn guitar, take home the groupies)
Yes, well it does seem rather ... intuitively obvious that it never actually exceeds certain death.
I have quite a bit of HPDE 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 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. 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.
Please help metamoderate.
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).
Something bad is coming when people are suddenly anxious to tell the truth.
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.
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 give testimonies and can they be a risk of going to prison due to poor coding that leads to some one dieing?
Well, Stanford wins on car choice, at least.
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!
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.
"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 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.
I call it "THE BRICK" !
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.
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.
"When information is power, privacy is freedom" - Jah-Wren Ryel
Depends on the car, are we talking a Yugo or an F1 car?
"When information is power, privacy is freedom" - Jah-Wren Ryel
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?
"When information is power, privacy is freedom" - Jah-Wren Ryel
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.
topping 120 miles per hour on straightaways
Enquiring minds want to know how fast it took the bendaroonies.
systemd is Roko's Basilisk.
A 2:30 seems like a terrible time to me. I did a 2:40.312 in an old Festiva with a busted engine and severely compromised rear suspension on janky old street tires.
Nah, the adrenaline rush comes when you're napping and the car's computer has a kernel panic.
Grandma, do you have robot insurance?
the preceding comment is my own and in no way reflects the opinion of the Joint Chiefs of Staff
Yeah, but if you look at Causes of Death 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.
Lost at C:>. Found at C.
Read your link more carefully. That's world wide, not USA.
See also:
http://en.wikipedia.org/wiki/List_of_causes_of_death_by_rate#Developed_vs._developing_economies
This explains American's love of Harleys. Goes fine in a straight line... First corner, not so much fun.
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.
I don't know where you live, but where I am "very bad drivers" is NOT in the minority!
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.
Free Martian Whores!
Hey, that reminds me of somewhere.
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.
~Anguirel (lit. Living Star-Iron)
QA: The art of telling someone that their baby is ugly without getting punched.
Okay "very bad" -> "far below average".
Maybe try googling " lifetime risk car accident america" and reading the very first link:
http://www.medicine.ox.ac.uk/bandolier/booth/Risk/trasnsportpop.html
They give annual US odds at 1:~6200 and lifetime odds of 1:~80.
*sighs*