Slashdot Log In
VW Raises the Bar for Self-Driving Vehicles
Posted by
Zonk
on Sun Jul 02, 2006 04:49 AM
from the take-me-home-jeeves dept.
from the take-me-home-jeeves dept.
Old Man Kensey writes "According to the UK Daily Mail, VW has produced a prototype Golf (code-named "53 plus 1" in a reference to Herbie the Love Bug) that successfully steers and accelerates itself at speeds up to 150 MPH on tracks designed on the spot without pre-programming. It sounds almost too good to be true given some of the problems CMU's prototype has had over the years, but perhaps VW has learned from and extended CMU's research (and within-an-inch GPS positioning probably helps too)."
This discussion has been archived.
No new comments can be posted.
VW Raises the Bar for Self-Driving Vehicles
|
Log In/Create an Account
| Top
| 177 comments
| Search Discussion
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
GPS? (Score:1)
Re:GPS? (Score:4, Informative)
(http://neolicity.blogspot.com/)
Wikipedia is not reliable (Score:5, Informative)
I can claim to be a "rocket scientist", at least I have designed systems for satellite control and tracking, and I work for an aerospace company.
You cannot measure a position to within less than a centimeter using GPS. You can design a ranging system that gives you a measurement with enough numbers to represent that precision, but it doesn't mean that you can trust such numbers.
You cannot use GPS to give you better measurements than the accuracy of the GPS constellation orbit determination, and the satellites' positions vary more or less randomly due to residual atmosphere, solar wind, and solar radiation pressure. The end result is that GPS cannot give any reliable measurement to less than 10 cm, and one meter is closer to the best that one can accomplish in practical situations.
A more accurate system than GPS is LAGEOS [wikipedia.org], which has satellites that are much heavier and smaller than the GPS satellites. They are basically brass balls covered with mirrors. Because of that higher density, LAGEOS satellites suffer less perturbation from non-gravitational solar and atmospheric effects. However, the equipment for doing ranging with LAGEOS satellites is not portable, it's meant for geodesy studies, not navigation.
A good overview of different satellite ranging systems can be found in "Satellite Orbits", by O. Montenbruck and E. Gill, ISBN 3-540-67280-X, and here is a Wikipedia link [wikipedia.org] for the most accurate satellite ranging systems.
Re:Wikipedia is not reliable (Score:4, Interesting)
I don't think, that the satellite positions vary randomly in the sense, that they have gaussian variance in a deliberatly short intervall of time. But their positions contain a systematic error, which can be determined via a fixed known position (actually more, but who cares) and thereby be corrected. This, in general, is the principle behind DGPS. The accuracy does not depend as much on the position of the satelites, but the discrepancy between the systematic error between the fixed known position and the unknown one.
That said, I'm still sceptical concerning the quoted accuracy. Especially for a moving object, like a car.
Comments on Slashdot aren't reliable either... (Score:5, Informative)
Yes, you can. I just woke up, but I'll see if I can explain.
In the case of DGPS, the reference station uses its surveyed coordinate to difference the time encoded in the signals it is receiving against the time it would expect given an estimation of where the satellite is. So any error in the satellite's predicted position is lumped in with all the other naturally occuring forms of error.
In the case of RTK, or other forms of relative carrier phase positioning, the system attempts to determine and track the difference in the number of cycles of the carrier wave of the GPS signal between the base and the satellite and the rover and the satellite. This number multiplied by the length of the carrier wave, 19cm for L1 signals, gives you the length of one side of a triangle between the base station, the rover, and the point between the rover and satellite that is as far from the satellite as the base station is. So, the exact position of the satellite is not as important as the sight line vector the satellite forms against the base line between the base station and rover. And given the great distance of the satellite from the typical base station and rover, jitter in the satellite's position doesn't change that vector much.
In conclusion, given the advances in relative positioning, limiting factors on GPS positioning today are the accuracy of the survey points, the ability of the electronics to precisely measure the carrier phase/doppler of the GPS signal, the quality of the clock in the GPS unit and the speed/accuracy of the algorithms that determine the carrier cycle count difference.
Re:Comments on Slashdot aren't reliable either... (Score:4, Interesting)
(http://carlhoward.org/)
And your point is? These types of errors you list (including satelite path deviations) are presisely what DGPS corrects for if the well known GPS is in relatively close proximity to the onboard GPS. In that case, these unknown variabilities will be reasonably well correlated so they will be removed when taking the differential. (ie. satelite orbit changes, ionospheric refraction etc., though unpredictable, will be nearly exaxtly the same for both GPSs so it gets subtracted out). In my work we generally get DGPS accuracies of less than half a meter which is well below your quoted error of 3 meters RMS.
For use with autonomous vehicles, one can generally do a lot better when the DGPS is augmented with a ground based equivalent of GPS like Terralites (XPS) which can and do routinely give accurate positions in the 1cm range.
No signal (Score:2, Funny)
Re:No signal (Score:5, Funny)
A tunnel?!?! OHhh NOOOOoooooo...!!
Re:No signal (Score:5, Informative)
Daily Mail (Score:3, Informative)
(http://www.askduds.co.uk/ | Last Journal: Saturday October 05 2002, @04:37PM)
Re:Daily Mail (Score:5, Informative)
Re:Daily Mail (Score:4, Informative)
(http://slashdot.org/)
http://www.spiegel.de/auto/aktuell/0,1518,424288,
Unfortunately, the article does not seem to available in English.
Re:Daily Mail (Score:5, Informative)
(http://www.jawtheshark.com/ | Last Journal: Sunday November 11, @08:53PM)
Well, in summary (I just read the Spiegel article), the car in question first learns the track based on traffic cones. Actually, the only thing this cars knows are traffic cones. A program then runs on the collected data and calculates the "ideal" path. When the finanlly activate the "racing mode", the car "simply" drives the studied track and that *blindly*. There need not to be any traffic cones, and it will not stop if something unexpected happens (so if a rabbit jumps in it's way, the researches will have rabbit for dinner) It does react a bit on the data from the sensors in the racing mode, but it's more for avoiding small variations in the track like a wet spot.
The car itself is pretty much a standard Golf GTI 2.0 Turbo (200HP) and the only thing they changed was stronger braking. They use the default sensors to make the program learn. Also, in the Spiegel article, there is not any mention of GPS.
Oh, and the research isn't intended to make auto-driving cars for you and me. They want to create a way that cars do exactly the same test runs on test-tracks to check the settings of the car. The results would be more reproductible. If anything, this tech is to put test-drivers out of work ;-)
They also mention that some of the tech was derived from a Touareg that they used in a competition of the US Defense Department in the Nevada desert. However, that one had completely different goals.
I'm sorry that I didn't translate the whole thing, but it was just too long.
Re:You call that a translation? (Score:4, Funny)
Research (Score:4, Interesting)
(http://onphilosophy.wordpress.com/)
Re:Research (Score:5, Informative)
It's true that academics can pursue riskier, more speculative areas of research. It's cost-effective for them to do so; they've got less overhead and grad students are cheap, and success criteria is different than for businesses -- publish a bunch of well-regarded, widely-cited papers, and you're in good shape. (you never need to earn back the investment money)
However, academics get their money from businesses and funding agencies who do have their eye on the bottom line. If an academic doesn't work on something that they feel is relevant (or abandons research they're funded to do in order to work on something cooler) then the money dries up really fast.
I've been on both sides of this (currently funder, formerly fundee) and I can tell you without doubt that academic research is a market, just like everything else.
Oiled (Score:4, Funny)
(Last Journal: Wednesday October 24, @03:50AM)
Self-Driving Vehicle promptly hits the bar, gets thoroughly oiled and rolls off into the red light district looking for a "service".
And this is why I don't feel comfortable (Score:5, Interesting)
And that bug is probably fixed by now, but the problem is, how do we determine we worked out all the bugs? We can't even do that with Linux/Windows/Anything. The closest we come to that in the OS world is a microkernel with only a few thousands lines of code and controlled input.
But how do we ever determine a program that learns and is subject to varying, uncontrolled data inputs is bug free? You can't and I wouldn't want to see the first literal blue screen of death when it happens.
I don't want to sound like a luddite, but the article mentions that planes have been flying autopilot (did they forget to mention landing/taking off is still done by the pilot) since the 1970s. But I believe we'll have flying cars before self-driving* cars because the problem is several hundreds of a magnitude easier in empty 3D space where all you have to do is stay high enough off the ground and avoid collisions via radar/whatnot.
*The only way is I see anything coming close to a self-driving car is on highways where lanes get marked magnetically and driving problem gets reduce to the car having to stay X feet behind the car in front of it.
Re:And this is why I don't feel comfortable (Score:4, Informative)
VW Raises the Bar (Score:2, Funny)
(http://howto.gumph.org/)
No more soft drinks for the "designated driver".
Just for race tracks (Score:5, Informative)
Re:Just for race tracks (Score:5, Funny)
(http://www.nodomain.org/)
I can't believe it's not been done yet .... (Score:2, Funny)
Details are little more than sketchy, but... (Score:2)
(Last Journal: Saturday December 04 2004, @05:17PM)
In case anyone is still stuck.... (Score:5, Funny)
Driverless cars (Score:2)
(http://slashdot.org/~xnormal)
Reminds me of a William Gibson novel... (Score:2)
(http://www.linkedin.com/pub/1/b92/361)
So... What problem does it solve? (Score:2)
You're going to be spending just as much money on the vehicle, using just as much energy, producing just as much pollution and spending just as much time stuck in traffic.
While automated driving is cool and interesting, it's not revolutionary, it doesn't solve any of the big problems caused by car usage we have today. It's worth noting that it's not possible for any of the existing public transport technologies to solve the problems caused by car usage either.
http://www.vectusprt.com/ [vectusprt.com]
http://www.atsltd.co.uk/ [atsltd.co.uk]
http://www.skywebexpress.com/ [skywebexpress.com]
http://www.mist-er.com/index-en.htm [mist-er.com]
It solves a lot of problems, actually (Score:4, Interesting)
(http://www.orion-com.com/)
The holy grail is cars that talk to each other to get around more efficiently yet. If the traffic up ahead narrows from four lanes to two because of construction, and car computers can talk to each other and say "Hey, you're two miles back but get ready for this", then orderly traffic flow can be maintained as the cars merge into the remaining lanes and decelerate. This in turn saves gas, etc.
Hell, think how much money you'd save if you car just automatically avoided potholes if it could. Tires, struts, shocks, suspension, all those would last much longer. Look at the figures on how much money it costs drivers annually in a city like Baltimore that's infested with chuckholed roads.
Nice, but not enough. (Score:3, Interesting)
Now if they managed to get this car travelling at 20mph down a city street during rush hour, we'd really have something useful on our hands.
Don't get me wrong, I'm impressed. But a self-driving car on an empty track is a million miles away from the everyday driving conditions we encounter.
hmmm (Score:3, Funny)
This would imply to me that the position has been filled.
VW? Reliability and Quality SUCK. (Score:2)
(http://www.wemissjerry.org/)
They suck.
That said, these jokers can't even design an ABS controller that lasts 5 years. How the hell do they think that they're QUALIFIED to design a life critical componant like this?
Self-driving? How about quality and reliability? (Score:2)
Fixing glove box doors that break at the hinge constantly.
Making window regulator clamps out of metal instead of plastic so the window doesn't fall into the door.
Using MAF sensors that last longer than 30,000 miles.
Using O2 sensors that last longer than the previously mentioned MAF sensors.
Engineering sunvisors with built-in lights that stay working (wires too short so they break in the headliner).
Assembling 2.0L engines so they don't use 3 quarts of oil every 3,000 miles.
Re-engineering a 1.8t turbo overboost valve out of metal so it lasts as long as the turbo.
Re-engineering combi-valves so they also last as long as the turbo.
Making all oil pans out of steel so oil change technicians don't strip the pan threads after 10 oil changes.
Making interior rubber coated plastic parts that don't peel after 2 years.
Making brake light switches right on the first try - not the 4th or 5th revision.
Let's get the basics of autos right first before we make them drive themselves....
-ted
But it's FUN to drive! (Score:1)
(http://www.thec.org/)
1 inch GPS (Score:5, Informative)
(http://web.abnormal.com/)
So they are cheating if you consider the real world.
I've been in a car that could drive its self on one very well surveyed road. If it got confused it would beep and assume the human was in control within a second. The internal guidance system alone cost over 1/3 of a million dollars and it used several different GPS systems to cross check the fiber gyro.
The only way cars are going to take over for driving the mini-van in place of the drive soccer mom is if there is a serious attempt to clean up the road markings. This means no more optional parking on the side as a road will either be a parking spot or a lane. Signs will need to be redone and cleaned up. The white lines must be far more precise than they are now and more places will need to deal with the yellow centerline (which has now been dropped in the EU even though its the cheapest road safety device ever)
Things have gone a long way. 2 decades ago I had a system that would indicate that a steering adjustment needed to be done. A decade ago there was Miata convertible that could maintain road position and deal with deer. This year we have a VW that can avoid traffic cones. Maybe in a decade we can see a car that can avoid the phone talking, breakfast eating SUV driver.
Raising The Bar... (Score:2, Funny)
Speeding tickets (Score:3, Interesting)
Car pulled over by the highway patrol for doing 150 in a 65 zone.
Officer is puzzled by the fact that the only person in the car is asleep, in the back seat.
"Did you know what speed you were doing, sir?"
"Huh, um, wha? Oh - the car was driving, Officer".
Car has to appear in court next Wednesday.
Again, (Score:2)
I don't understand why car companies are wasting time and money in developing self driven cars. While there might be useful purposes for the technology, such as "off-world" exploration, or for use in the military, there will never come a time when we turn over control of our cars to a computer and sit back and enjoy the ride.
There are too many variables involved in a self-driven cars, things that a computer cannot take into consideration, such as the often random and stupid nature of how people drive. In a mixed environment, where human and computer driven cars are allowed, it will be a huge disaster waiting to happen. The first time some idiot swerves across 4 lanes of busy traffic because they don't want to miss their exit (because they were not paying attention in the first place) and causes a massive car pileup because all the computer driven cars could not react fast enough to the sudden chaotic input will essentially pull the plug on the whole idea. Companies like VW and Honda working on automated cars will be named in a massive class action lawsuit that will effectively bankrupt these companies (good riddance, both companies are overly hyped about anyways).
Even in an environment of purely computer driven vehicles, where you have a safe enough (and powerful enough) computers controlling all the cars, robust and secure wireless networks, along with radar and all the sensors needed so that every car knows about the existence of every other car on the road in a 10 km radius, there is still a level of uncertainty and chaos that computers will not be able to handle. A sudden rainstorm or white out, while may not affect the navigation of the vehicle, may cause the computer to react poorly in a sudden stop situation when it hasn't gauged the slipperiness of the road. Driving down a dark highway at night, human eyes may pick up the deer standing still on the side of the road, and slow down accordingly assuming the deer might dart across the road suddenly, but a computer will not register the fact that there is wildlife near the road, and will not react quick enough when the deer darts pass, regardless of how good the avoidance detection and mechanics are. There is no computerized counterpart for human intuition and experience.
In the end, you will have to build a roadway underground, where you can almost guarantee no inadvertent input of chaos into the computer controlled environment. If you take weather and wildlife out of the equation, and can guarantee a pretty much predictable environment, then I would agree that computer driven cars makes sense. But it would cost trillions of dollars to upgrade the highway and transit systems to implement this kind of system for computerized car control, and I would move that it would be criminal to allow a human driver in this environment, enough for jail time and a life long suspension of your license. Movies like iRobot where Will Smith takes manual command of his car while driving down an automated tunnel is pure fiction, and it will remain that way.
In the end, this is a pipe dream and I am afraid that every dollar wasted on this technology could be put into making cars more fuel efficient, ecologically friendly, or research in alternate fuels or power technologies. They can also be made safer, or at least, implement computer assistance that could effectively prevent the car from spinning out of control if the human driver isn't skilled enough to handle the situation.
I don't think I am alone in assuming that this technology will never see the light of day in a real world application. The real world is too unpredictable and chaotic to turn over to a computer to drive around in. If they invent anti-grav engines and force fields, then maybe I would turn over my vehicle to a computer, but they don't even let the computer drive a spaceship 40
Herbie was nuts (Score:1)
Raising the Bar to Drive (Score:1)
could someone please give stanford their due? (Score:2)
Personally I hope they aren't using DGPS (Score:1)
"availability of 99.7% per month"
Now, assuming my math doesn't suck, that means that for 129 minutes a month it won't work... Those could be a very exciting few minutes!
We could probably have self-driving cars today... (Score:2)
(http://www.phoenixgarage.org/)
However, we have all the technology to enable such a vehicle, especially if we limit it to highway travel (where conditions tend to be less variable than surface streets). One such improvement for guidance would be a combination of active and passive "dots" lining the lanes. The passive ones could be simple rare-earth magnets. The active ones would take a bit more work, but I can easily envision a small solar panel with an integrated RF/IR transponder - perhaps it could even communicate with other dots wirelessly to forward information toward on-coming traffic about road conditions and such. I am also thinking of a system like an ant-trail, where the communication could be forwarded by "hitchhiking" packets of information onto the car as it travels, and then it could deposit the info in a later dot (not sure if or how this would be useful, but it sounds like it could be in some manner).
Couple this with signage broadcasting data, cars with navigational aids (GPS and radar, mainly), standard vehicle-to-vehicle communication protocols (so cars could talk to each other to let each know intent and yielding) - I would be willing to bet that all of this is easily available, without needing special DGPS systems installed. Even without special "active dots", most of the system would be easy and cheap to develop.
The expensive and hard to develop part isn't the hardware - it's the software. This includes not just the software for the system and the cars, but the "software" (ie, business processes) needed for insurance and liability concerns for all parties involved.
one thing this might be good for... (Score:1)
On another note, if these scientists think they're so smart... let's see them do it with a motorbike =)
This can't come too soon (Score:3, Insightful)
(http://www.templetons.com/brad/)
Estimates for the costs of crashes range from 10 to 30 cents/mile, factoring in everything -- health, repairs, suffering -- which is more than the cost of gasoline or depreciation.
It's now down to an engineering problem to build self-driving, crash-avoiding cars. It's the largest preventable cause of suffering and death we have.
Why use CMU when you have Stanford (Score:1)
a lone crusader in a dangerous world (Score:2)
-KITT
Re:Rocker-Bogie (Score:2)
Cute and ingenious design but not something you'd want to go faster than about 2mph.
(Let the obvious rocker-boogie jokes begin...)