Stanford's Stanley wins DARPA Grand Challenge

tonyquan writes "DARPA has just announced that Stanford's "Stanley" autonomous ground vehicle has won the Grand Challenge, a $2 million contest for driverless vehicles over a 132 mile course in California's Mohave Desert. Stanley's winning time over the course was 6 hours, 53 minutes and 58 seconds, for an average speed of 19.1 mph. Second was Carnegie Mellon's Sandstorm (7:04:50), third went to another CMU vehicle "H1ghlander" (7:14:00) and fourth to the Gray Team's KAT-5 (7:30:16) More info from DARPA."

Comments

Can you say...

[It doesn't come easy]

Farfignugen!

Re:Can you say...

[antek9]

No, but I can say Fahrvergnügen, especially since Stanford's team leader Sebastian Thrun is actually from Germany, you hit the nail on the head.
Great run, saw it on TV yesterday, and a major step in development of fully autonomous bots.

Re:Can you say...

[It doesn't come easy]

Sorry, copied that spelling from Google. My bad.

Re:Can you say...

[Anonymous Coward]

BTW, Dr. Thrun was at Carnegie Mellon until about two years ago...

All things considered, the top four times are actually quite close together (less than 10% difference).

Re:Can you say...

[Anonymous Coward]

Site DOWN??? www.grandchallenge.org/ comes up blank screen ONLY ?????

so wait..

[molo]

Last year they had NO vehicles even make it out of the obstacle course.. and this year they had several vehicles actually complete the desert course?? What gives?

-molo

Re:so wait..

[dohzer]

I don't think it shows a great advance in robotics and A.I. (although that is partly responsible), more just an advance in how they handled the DARPA Grand Challenge. If DARPA gave them a different challenge of similar difficulty, it might take them a few years to finish again.

Re:so wait..

[AxsDeny]

Their team leader was on the Red Team last year. I'm sure that didn't hurt them at all.

Re:so wait..

[Ansonmont]

And, most of them were pretty close time-wise. The winner was only about 10 minutes or so ahead of the 2nd place finisher. From zero to five competitive finishers...of course all of these results will only be put to peaceful purposes. Isn't Darpa like a branch of the Peace Corps???

-A

Re:so wait..

[kilodelta]

They learned from their mistakes is what happened.

The boys in the military must be gibbering with joy. Imagine an armored vehicle that can recognize friend or foe. Just set this baby loose and watch the fun.

But the civillian benefits are going to be cool too. For instance, screw magnets imbedded in roads, etc. Just use the roads we have now and tell the vehicle where you want to go.

Re:so wait..

[EEJD]

It's not so much an improvement in the AI as it is an improvement in the sensors. These vehicles look ahead about 30 feet and plot their course based on very simple logic. If there is a negative obstacle (a hole), it is more difficult for sensors to detect than if there is a rock sticking up in the path. Last race, the only thing that stopped red team was a hairpin turn. Their sensors looked straight ahead and only a little to the sides, but when faced with the hairpin turn, the vehicle almost fell off the side of the mountain! But the rules of the AI haven't changed much- just the sensors. If you're driving through jungle, for example, you have to have sensors that don't see leaves as obstacles. Otherwise the path will look totally impassable.

Re:so wait..

[Zathrus]

There are several factors here. First and formost, the vehicles are more capable. The software is vastly better and the hardware is somewhat improved. Did you think that they've been sitting around doing nothing for the past 17 months? They've been working on improvements since the last challenge, and they've spent a lot more time actually testing their vehicles in desert terrain.

There are some people who say that this year's course is far easier than last year's. I don't know myself -- I'm not involved with any of the teams and I don't have detailed knowledge of the courses. But there has been some commentary by those involved to this effect, as well as from bystanders. One huge difference is that the most difficult part of the course (Beer Bottle Pass, a narrow road with a steep drop off on one side) was at the end of the course this year, while the equivalent part was near the start last year. Stanford's leader is quoted as saying something to the effect that if they'd inverted last year's course then a lot of cars would've gone much further, even if none of them finished. The complete lack of media attention last year may have been one reason why DARPA swapped the course around -- it's rather anti-climactic to write about a race where the best racer hardly even got off the finish line and leads to the kind of stories DARPA really doesn't want to see (waste of taxpayer money, will never work, etc.).

In any case, given that less than 25% of the vehicles finished, I'd hardly say that it was a trivial thing to do. It's still amazing. Congrats to those who did, and to all of those who participated for that matter -- it's quite an accomplishment, even if there's a long way to go still before this is really usable in a real world environment.

Re:so wait..

[vertinox]

Last year they had NO vehicles even make it out of the obstacle course.. and this year they had several vehicles actually complete the desert course?? What gives?

Corporate Sponsorship and Moore's Law

Re:so wait..

[axlrosen]

The interview with the Stanford team lead also said that last year, there was talk of the course being much harder and 300 miles long, so teams over-engineered their vehicles. This year they had a much better idea of what the course would be like, so they could spend their time better.

Re:so wait..

[Zathrus]

Imagine an armored vehicle that can recognize friend or foe.

Given that humans have enough problems doing that (friendly fire incidents anyone?), I think you can forget about a completely autonomous armed vehicle for quite some time. Even the Hellfire armed Predators require a human for fire control... it's just that the human can be on the other side of the planet (and often is).

But the civillian benefits are going to be cool too. For instance, screw magnets imbedded in roads, etc. Just use the roads we have now and tell the vehicle where you want to go.

Uh... maybe in a decade or two. The software used on these vehicles is tuned toward one specific set of conditions -- uninhabited desert. They have little to no software for dealing with moving objects, much less dozens or hundreds of moving objects. And when you start talking about street or freeway driving then you have a bunch of other issues that come up -- having to deal with animals or people darting into the street, dealing with other vehicles doing stupid things (either because the human at the wheel did something foolish or because that 18-wheeler just lost a tire and driving through the debris is a really bad idea), etc.

Oh, and then there's the minor issue that a lot of the technology being used (LIDAR, etc) aren't reliable much above 20 mph -- at higher speeds you cannot crunch the data fast enough to rely on them for object detection and collision avoidance. So unless you're excited about driving everywhere at 20 mph, you better hope that GM, Ford, etc. solve the highway driving problem. Even if it does involve implanting magnets in the roadway.

Re:so wait..

[Surt]

I'm sorry, but there's no pretense about this: the competition is designed to help the defense department deliver on its promise to congress to get most of its ground assault vehicles unmanned in the 2010 to 2015 time frame. They state it explicitly, and all over the place. The universities competing in this competition know perfectly well they're helping the armed forces kill people.

Re:so wait..

[ViX44]

The universities competing in this competition know perfectly well they're helping the armed forces kill people.
Oh, snap!
The universities competing in this competition know perfectly well they're helping the armed forces kill people without putting our boys and girls in harm's way. Slight difference there. You make it sound like they're trying to roll out waves of little Terminators. No, they're just trying to achieve the same field presence without having to deal with sending as many sad letters to the families of kids who's final group photo was under an array of U.S. flags inside boxes within the cargo hold of a C-130.

Re:so wait..

[floormasn56]

AND 2 million "Let get serious" money. also the hope of a fat juicy DOD research grant. DOD money = good. DOD recruiters = bad

Re:so wait..

[Anonymous Coward]

The universities competing in this competition know perfectly well they're helping the armed forces kill people.

You're making the common mistake of assuming that the purpose of the military is to kill people. It's not. The purpose of the military is primarily to defend your country, and secondarily to defend other people where this is deemed beneficial to your country's interests. Killing people is one of the ways this is done, but the primary goal in a war is to persuade the enemy to surrender, not to kill as many of them as possible. If you can use smart weapons and special forces to take out their infrastructure or their commanders, you can get the majority of the opposing forces to give up. Similarly, the average soldier, faced with an enemy that knows no fear, feels no pain, and has nothing to lose but money - in other words, an unmanned assault vehicle - is not going to go out and fight it if he can help it.

Oh, and I'll just add at this point that the most recent thing I heard in the media about the US army was this: that they just sent eight military helicopters to help survivors of the earthquake in central Asia. That's not "killing people". That's your army spending a heckuvalot of money to help people who are not only foreigners, but, by and large, actually hate America. This is called "doing good", and I speak for much of the world when I say that we admire America when it does good. And it doesn't take much imagination to think of other ways America could do good, if it had better AI and robotics technology at its command: think of small autonomous reconnaisance robots, being used to locate survivors in the rubble.

Re:so wait..

[gers0667]

A friend of mine was on the CMU team. One of this years robots was in last years competition. Of course they made enhancements to the robot, but the biggest problem they had with it was that they rolled the robot 3 days before the competition. They were pushing the robot to the limits on a test track and went too far, according to my friend. He said they would have faired much better, but when a Hummer filled with computers rolls over, you are bound to have some problems.

Re:so wait..

[greg_barton]

What gives?

Obviously, an infusion of alien technology must be involved. There is no other explanation.

Re:so wait..

[Nutria]

boys and girls

Why do people always say that? What about the people in their 20s, 30s & 40s?

Re:so wait..

[Cerberus7]

Werner von Braun was in the exact same position.

Re:so wait..

[MindStalker]

ground assault vehicles should be placed by supply delivery vehicles. Or atleast thats what the congressional mandate was for.

Re:so wait..

[Surt]

And he was at least equally evil.

Re:so wait..

[Dun Malg]

I'm sorry, but there's no pretense about this: the competition is designed to help the defense department deliver on its promise to congress to get most of its ground assault vehicles unmanned in the 2010 to 2015 time frame. They state it explicitly, and all over the place. The universities competing in this competition know perfectly well they're helping the armed forces kill people.

By all means, don't allow facts to get in the way of your hysterical editorializing. The DoD is not developing an unmanned ground assault vehicle, and they do not state that explicitly at all. They are looking to procure an unmanned cargo carrying vehicle by 2015. You will, of course, probably point to how everything in the military is designed to support operations and is therefore contributing to killing people, but that'd just be weaseling. You clearly thought they were developing killer robots. Let's hear it for reading comprehension! Moron.

Re:so wait..

[operagost]

You might ask the media, which is always portraying our soldiers as poor, immature chumps who were victimized by the administration.

Re:so wait..

[zogger]

In mining now they use embedded sensors to guide robotic vehicles (trucks I think) of the quite large size. Just some data I heard about, no link handy. Probably not very AI intense, just steering back and forth down an established road. I know in farming they have automated GPS enabled steering for doing large operations,you get very precise rows, etc in those huge farms of thousands of acres. You can see the ads for the devices/tractors/etc in the back of farm magazines.

As to the unarmed missile firing drones, one would imagine that a software tweak would make it go from human interaction-required to fire-at-will, say in some area where no "friendlies" were. They could set it on "if it's mechanical and moving destroy it" and just turn them loose in that area. That would seem possible right now. Maybe some AC will confirm or deny this capability.

Re:so wait..

[Surt]

by all means, don't let the facts get in your way either:
http://www.army.mil/fcs/articles/

http://www.uniteddefense.com/pr/pr_20050414b.htm

http://www.jointrobotics.com/history/MP89.pdf

So yeah, it seems utterly clear that the DOD has no plans to incorporate technologies for ground navigation into assault vehicles.

Re:so wait..

[Anonymous Coward]

PURE HILARITY !

Re:so wait..

[lowrydr310]

I don't know what the grand challenge course looked like, but I once went off roading with a Hummer H1 on the White Mountain Trail in Southern California (Hesperia to Big Bear). We encountered many difficult obstacles like extremely steep washed out rocky inclines. It was nearly impossible for manned drivers to travel on this trail, and I would bet that all of these Grand Challenge vehicles would fail miserably under any extreme conditions.

I realize that the Grand Challenge is an important step, however there's still a long way to go before we can drop an autonomous Hummer in Iraq or Afghanistan and give it GPS waypoints to follow.

Re:so wait..

[cloudmaster]

It'd probably be better if our armed forces stopped inovating, and just waited for the rest of the world to advance beyond our own capabiilty to respond, eh? Because, if we stop concerning ourselves with war, the whole world will instantly fall into a state of peace and be covered with pretty flowers.

Obviously, any students who learn more about effectively automate vehicles will *never* find a way to apply that technology in a non-lethal environment...

http://www.edmunds.com/insideline/do/News/articleI d=107011
http://www.jaguarusa.com/us/en/vehicles/s-type/pri ces_and_specs/opt_equipment.htm (look at the first available option)

Yes, anything that can potentially be used to kill someone should be off-limits for research, regardless of its usefulness in other arenas. Especially if, heaven forbid, the *military* encourages development!

Re:so wait..

[Zathrus]

say in some area where no "friendlies" were

Which is exactly the presumption that causes most friendly fire incidents. Communication is incomplete, people get lost, go into the wrong areas, there are always civilians around, etc.

Could the government turn out some fully automated Predators right now? Almost certainly. But I think they know it would be a bad idea to do so, especially given the rather weak onboard intelligence. AFAIK, the Predators were never designed to be completely autonomous anyway, and were always made to have some degree of human intervention (if only plotting route points).

Re:so wait..

[the_xaqster]

Umm, where can I get hold of an unarmed missile firing drone?

Re:so wait..

[Dun Malg]

So yeah, it seems utterly clear that the DOD has no plans to incorporate technologies for ground navigation into assault vehicles.

Nice attempt to braoden and generalize, weasel. You said:

"the competition is designed to help the defense department deliver on its promise to congress to get most of its ground assault vehicles unmanned in the 2010 to 2015 time frame."

Clearly you're talking specifically about the Grand Challenge project, for which the time frame of "2010 to 2015" is relevant, and this is what I addressed. Stands to reason, as that's what this /. topic is about. You added in to word assault between "ground" and "vehicle" based on some internal editorial bias. I never claimed the DoD isn't interested in autonomous armed combat vehicles. I am simply stating the fact that the DARPA Grand Challenge is the preliminary step in developing an unmanned, unarmed, cargo carrier to be fielded in 2010-2015. This is what the linked DARPA site says. This is what all the articles say. You flasely claimed otherwise.

Re:so wait..

[Surt]

There is a difference that a sufficiently intellectual person can draw between developing something intended for lethal uses, and developing something for non lethal uses.

As an example, if the WHO asked you to do some work on understanding the lethality of the asian bird flue, you might consider that work in a different light than doing the same work Al Qaeda, or the Iranian government.

Yes, virtually any invention can be put to lethal uses, but no, not every employer is equally prone to evil and violence.

Re:so wait..

[halltk1983]

TERRORIST!!! err... INSURGENT!!! Fear not people, the black SUV's will be here any moment!! ::whispers:: you wouldn't mind giving your address, would you? Wait... I'll just use the RFIDs in your computer.

Re:so wait..

[halltk1983]

they rolled a hummer What were they doing to it? driving on the side of a cliff?

Re:so wait..

[Anonymous Coward]

People aren't allways saying it, American people are. As to why, my guess is because their TV tells them to. Plus, the people on the other side of military or police action are "the bad guys". It never ceases to amaze me that Americans never complain about that. Their government agents bend over backwards to speak in the most condecending manner possible, and no one seems the least bit offended by it. Of course Americans also didn't think pissing in cups on demand was demeaning in the least, so I don't know why I'm surprised.

Re:so wait..

[usrusr]

so you expect that less people will die then?

one question:

will this lead to

(a) less "boys and girls" involved in doing risky things in foreign countries

or

(b) the same number of "boys and girls" doing risky things in more foreign countries

i'm afraid that (b) might be closer to the future we will see, including more people to take a try at asymmetry.

still the technophile in me enjoys to see how technology advances and i guess it would happen anyways. and besides, this way of getting universities etc involved is definitely better than the usual opaque shifting of defense budget billions typically involved whenever the words "military" and "technology" appear in the same sentence. but we will probably seeing enough of that about autonomic vehicles later.

Re:so wait..

[Surt]

Another helpful website for anyone interested in what the DOD intends to do with grand challenge technology:

http://www.darpa.mil/grandchallenge/overview.html

Note the complete lack of any mention of 'non lethal' and the use of such interesting catch phrases as "autonomous ground vehicles that will help save American lives on the battlefield "

Re:so wait..

[Anonymous Coward]

From the DARPA grand challenge FAQ: What is the purpose of the Grand Challenge?

DARPA's mission is to create technologies for future application on the battlefield. In recent years, Congress and the Department of Defense have envisioned unmanned vehicles teamed with people to create efficient, integrated, agile and cost-effective forces that will lower the risk to American life. http://www.darpa.mil/grandchallenge/qa.html

Their FAQ doesn't really say wether the research is for armed or unarmed.

Re:so wait..

[cloudmaster]

Who exactly was supposed to get killed out there in the desert? If you're talking short-term, these vehicles were designed for a competition. If you're talking long-term, then any research could potentially be used for war. If you wanna be real technical, these vehicles will likely never kill anyone - they're just carrying the killing equipment somewhere. The bird flu could potentially be used directly to kill, so it's different. Do tire companies who make stuff for the military count in the list of people who weer working for the military to kill people? What about those people with Jeeps - how dare they support the company that got our troops into several terrible battles!

Merely being sponsored by the US military does not guarantee evil. I'm a big fan of that Internet thing, for example. Then again, I also own guns which are not intended to kill people, and computers which aren't used to calculate missile trajectories (even though they may well have been designed with other plans), so I'll probably never understand.

Re:so wait..

[j-turkey]

You're making the common mistake of assuming that the purpose of the military is to kill people. It's not. The purpose of the military is primarily to defend your country, and secondarily to defend other people where this is deemed beneficial to your country's interests.

I think that I can clarify this one:

The purpose of the military is primarily to defend your country
...by killing people or intimidating people by threat of death.

and secondarily to defend other people where this is deemed beneficial to your country's interests.
...by killing people or intimidating people by threat of death.

I'm not necessarily anti-military, and understand that the military both helps and harms people. However, your rosy picture of our happy military is a gross oversimplification, and dare I say, bullshit. Here is a link to Wikipedia's definition. An excerpt:

As an adjective, "military" is a descriptive property of things related to soldiers and warfare. It also refers to such context dependent terms such as military reserves which may indicate an actual unit deployable on command or the general sense, of a Nation States reserve troops available to or eligible for duty in its armed forces.

The soldiers and warfare part stands out for me. Those equate to killing people. You can call it whatever you want, but the reality is that it is what it is.

Re:so wait..

[syncomm]

Hmmm... do you get the 72 virgins for martyring yourself to stop a robot? ;) Also it is much easier to "sell" a war to a populance that has little to no fear of human causualties. It's not as if Bender from Futurama is going to appear on 60 Minuites and read the list of fallen robots! Primarily military strategy is based on cowing enemies into surrender; enemies are much less willing to put their life on the line to fight the "demonic machines from BABALON." This will be espically true if they take the idea _all the way_ and develop an expert system to learn from online military shooters. I can't imagine fighting against something that maintained hundreds of kills per hour and never missed. Sounds like some interesting work!

Re:so wait..

[Anonymous Coward]

Na na na na hey hey goodbye. Face it bro, your ass got smoked by a crack monkey on slashdot. You is da deflabulated bomb. You be mo wrong than chimpanze sniffing crack off a horses ass. You is not the shibang you is the dopeslap reciever.

by by

Re:so wait..

[John Harrison]

It should also be mentioned that at least the Stanford team and the CMU team claim to have completed the old course while preparing for this year's event. So even if this year's course is easier, there are some teams that completed the old course anyhow. Obviously this wasn't under race conditions (the most important condition being that you don't know the course until just before the race) but it is still relevant.

Re:so wait..

[ashooner]

Yes, defending our country, as in being on the other side of the world when a major natural disaster strikes. Well done.
Or perhaps defending those 'other people' by, for instance, invading their country and bombing their cities (and refusing to calculate civilian casualties, since it's not their job).

So to recap: To defend me, the military attacks other countries. To defend others, the military attacks their countries. Also, in defending said others, the military doesn't care how many of them they have killed.

If this is defense, you can keep it.

I'm not against the military, but if you equate "pre-emption" with defense, you need to revisit a dictionary (not to mention a 20th century history book)

Re:so wait..

[Anonymous Coward]

Wow. You sure do not know America. Or you do not know very many Americans. Either that or you need to get out of the coasts some more.

Americans are some of the most authority averse people around. Ask any military officer.

Re:so wait..

[Anonymous Coward]

"What a crock of shit. American army hasn't defended the country for half a century now. The only thing it defends is American economic interests in other countries. In other words, the US Army exists to support American imperialism, help the US exploit other countries and rob them of everything they have (oil, metal ores, channels, opium poppy, coca, etc.)."

As hard as it is, I am going to try this without foaming around the mouth. It is true that the defense of Europe was in no small way an endeavor of self preservation on the part of the United States. Nonetheless, the Marshall Plan and the defense of Western Europe benefitted hundreds of millions outside the U.S.

For pure altruism, Somalia, Bosnia, Haiti all were peacekeeping missions performed by the evil U.S. Army and its madmen.

On a strategic level, you are hopelessly clueless and I will not even bother. Just read the above and start from there.

Re:so wait..

[ccp]

The DoD is not developing an unmanned ground assault vehicle, and they do not state that explicitly at all. They are looking to procure an unmanned cargo carrying vehicle by 2015. You will, of course, probably point to how everything in the military is designed to support operations and is therefore contributing to killing people, but that'd just be weaseling. You clearly thought they were developing killer robots. Let's hear it for reading comprehension! Moron.

So let's see...

You read the DoD PR, believe it, and call the other guy a moron?

There's a bridge here that may interest you.

Cheers,

Re:so wait..

[iceanfire]

strangest comment ever.

Re:so wait..

[Locke2005]

The universities competing in this competition know perfectly well they're helping the armed forces kill people. Over 2000 good soldiers dead in Iraq, many by Improvised Explosive Devices... how many of those deaths good have been prevented by using autonomous vehicles for patrols instead of manned ones? Perhaps the universities beleive the opposite is true -- there helping keep armed forces people from being killed. Face, if the goal of the armed forces were simply to kill people, then nuclear, chemical, or biological weapons would do it much more quickly and efficiently than an autonomous vehicle! The trick is not simply to kill people, but to kill the RIGHT people. I don't think anybody honestly beleives that autonomous vehicles can decide who the right people are, so it is much more likely these will be used to prevent deaths rather than cause them. That could only be a good thing, unless you happen to be a member of an "insurgency". Personally, I prefer being able to say "Ha-ha! You just killed a robot!" to anybody that attacks our vehicles.

Re:so wait..

[Anonymous Coward]

As hard as it is, I am going to try this without foaming around the mouth. It is true that the defense of Europe was in no small way an endeavor of self preservation on the part of the United States. Nonetheless, the Marshall Plan and the defense of Western Europe benefitted hundreds of millions outside the U.S.

Firsly I'll acknowledging the absolutely huge efforts the US made in ending the war in Europe, not least by the US Air Force who I believe even ran day-light bombing missions (which is basically suicidal).

But someone far more skeptical than myself might point out that the US did arrive a bit late! And thus:

1. The US might've saved both Europeans and their own service men if they'd turned up a bit earlier, and
2. Perhaps they arrived late because they realised that the end result of not helping their European allies would be far worse than just holding tight (as presumably was the plan before that?)

But like I say, I do truely repect what was done. My point is simply that the current generation seems to believe that the US intervention was a *purely* selfless act that the rest of the world should forever be grateful for! (we are.... but only up to a point!)

Re:so wait..

[legirons]

"Obviously, an infusion of alien technology must be involved. There is no other explanation."

They were intelligently designed...

Re:so wait..

[QuantumG]

It's a bit hard to take you seriously when you call people names. Just state your opinion and shut up.

Re:so wait..

[SebNukem]

Because, if we stop concerning ourselves with war, the whole world will instantly fall into a state of peace and be covered with pretty flowers.
No, but one less warmonger. technically closer to the state of peace described.

Re:so wait..

[Dun Malg]

Their FAQ doesn't really say wether the research is for armed or unarmed.

True, but this has previously been their stated goal. I don't have a link to it offhand, but even without an explicit statement of such all it takes is a common sense examination of the facts. First, the Grand Challenge does nothing to advance the real hard part of building autonomous "killer robots": when and at whom to fire. We don't even have autonomous combat aircraft and the "friend vs. foe" problem is orders of magnitude easier in the air. Second, the ability to go from point A to point B represents only a fraction of the combat maneuvering problem, but it represents essentially the entirety of the cargo delivery problem. So what we have is clearly a project whose only useful result will be robotic vehicles that can drive long distances over rough terrain unattended: a cargo transport system. It will easily take 5-10 years to get all the bugs worked out of a system designed simply for that alone. There's no way in hell they could deliver an autonomous weapons system by 2010-2015. Someday, maybe as soon as 25-30 years from now, they will have built upon these early successes and field an autonomous combat robot; but to claim that universities are participating in building such devices because they are in the Grand Challenge is as asinine as saying Alexander Wood is responsible for IV drug use because he invented the hypodermic needle.

Re:so wait..

[Dun Malg]

It's a bit hard to take you seriously when you call people names. Just state your opinion and shut up.

Frankly, I don't give a fuck. I don't have to work or live with anyone here, and I could not possibly care less how seriously my comments are taken. If I'm feeling like a jerk one day, I will call someone on /. a fucktard if it suits my fancy. As evidenced by the factually incorrect assertions in the original post, slashdot is a freee-for-all. Clearly, anyone can say anything they want, they don't have to wait their turn, or be quiet when they've had their say, or stick to only the topic at hand. If someone's truly out of line (and it takes a LOT to be out of line HERE) then the post will be modded down, right?

Re:so wait..

[QuantumG]

If you don't want people to take you seriously that's your prerogative. I was just letting you know.

Re:so wait..

[ashooner]

fine, we could have fought for the germans... (there are americans who really think we should have, more WWI than II)

Re:so wait..

[Anonymous Coward]

fine, we could have fought for the germans... (there are americans who really think we should have, more WWI than II)

But if you'd done that, you would never have got access to their rocket scientists, and thus you would've remained under threat.

Re:so wait..

[Darth23]

So what's your point?

Re:so wait..

[Anonymous Coward]

The DoD is not developing an unmanned ground assault vehicle
...
I never claimed the DoD isn't interested in autonomous armed combat vehicles.

Liar. For what it's worth, I'm a student at Carnegie Military University, and yes, they are developing autonomous attack vehicles. Like the gladiator. To think these are technologies that DARPA is planning on researching and developing entirely separately is naive.

Re:so wait..

[iamlucky13]

Ooh, Ooh, Ooh! Flamebait! I can't wait to respond.

Seriously, who ever said there was a pretense? We are talking about the military here. The same goes for joining the military. Every recruit or cadet knows they could be ordered to kill another human being. That's a part of war. Sure war sucks, but that doesn't change the fact that we have to deal with it. You can go on hating all the soldiers and all the people who, with good intent behind their endeavors, try to make life easier for our soldiers by making things like unmanned vehicles, but that isn't going to magically end war.

Re:so wait..

[Profound]

Sadly our boys and girls in harm's way is the only restraint on the US military's actions at present. The mass media, politicians, mainstream public sentiment etc do not care about the deaths of foreigners, only of Americans.

Almost all calls for troop withdrawl from Iraq mention the thousand or so US soldiers deaths, not Iraqui civilians, even though there are 100x more of the latter. The Vietnam withdrawl had more to do with the deaths of tens of thousands of soldiers than the millions of Vietnamese civilians. This is not specifically an American sentiment, it works pretty much this way in all countries.

If the US can invade other countries with no negative consequences back home, what will put an upper limit to the force exercised overseas? If Americans can move joysticks and program computers to kill man shaped blobs from hundreds of kilometres away, what's to make them feel bad when they shoot at a slightly smaller, child shaped one?

When wars are waged where casualties are massively one sided, the side suffering the greatest losses will feel cheated and opressed and desire to move the conflict to "spread the pain and grief around". This would probably means more civilian attacks against the US - "Why should our children be the only ones to die?"

Re:so wait..

[ashooner]

Pretty wild to imagine a U.S. vs. Nazi Eurasia cold war.

Re:so wait..

[danila]

As hard as it is, I am going to try this without foaming around the mouth. It is true that the defense of Europe was in no small way an endeavor of self preservation on the part of the United States. Nonetheless, the Marshall Plan and the defense of Western Europe benefitted hundreds of millions outside the U.S.
Well, the defence of Western Europe from whom? Soviet Union was not a threat to Western Europe. This "threat" was manufactured by US propaganda to justify the Cold War agains the Soviet Union. Most original US documents have been declassified (50 years passed), so read them. So all that "defence" was bogus. Soviet Union liberated the Europe from the Nazis, not threatened it. Marshall Plan was a successful attempt to tie Europe closer to the US, while making sure that US industry benefits from the reconstruction (just like in Iraq and elsewhere today).

For pure altruism, Somalia, Bosnia, Haiti all were peacekeeping missions performed by the evil U.S. Army and its madmen.
Somalia was altruistic? Perhaps the US-led attacks on women there were also altruistic? Like blow up a pieceful meeting of Somalian delegates and then pretend it was a terrorist cell. Read up the prehistory of the Mogadishu disaster someday. To call Bosnia altruism is just as ridiculous. The US manufactured lies about ethnic cleansings, armed the Albanian Islamic extremists, ignored massacres of Serbs, destroyed the infrastructure and overall caused innumerable harm. Haiti wasn't any better - a total mess, with supporting some pro-American dictators, assassinating heads of state, then invading and killing tens of thousands of civilians. Is supporting FRAPH death squads an act of altruism? If yes, then the US indeed acted altruistically in Haiti. Or how about the fact that Aristide had to agree to all requirements of the IMF and allow the continued operation of sweatshops in Haiti in order to get the US backing? Altruistic too? You are hopelessly naive, or indeed brainwashed by the government-sanctioned propaganda that you are subjected to by the corporate-owned US media.

Re:so wait..

[Surt]

The parent to which I was responding suggested a pretense that the vehicles would only be put to peaceful uses.

I didn't suggest it was good or bad, just that the universities involved must know they are helping to kill people.

Re:so wait..

[Dun Malg]

The DoD is not developing an unmanned ground assault vehicle
...
I never claimed the DoD isn't interested in autonomous armed combat vehicles.

Liar. For what it's worth, I'm a student at Carnegie Military University, and yes, they are developing autonomous attack vehicles. Like the gladiator. To think these are technologies that DARPA is planning on researching and developing entirely separately is naive.

Good job quoting me out of context, fucktard. The first statement is specifically in regard to the DARPA Grand Challenge goal, as promised to congress, of fielding a vehicle system in the 2010-2015 time frame. This planned vehicle is not an autonomous attack vehicle, it's a cargo carrier. Here, let me rephrase the two quotes above with explicit elaboration of their context so that a dimwit like you can understand:

The DoD does not have as its stated goal the development of an unmanned ground assault vehicle, utilizing the results of the Grand Challenge participants, to be delivered within the 2010-2015 time frame, as they original poster suggests.
...
While it is patently obvious by the limited capabilities and short term nature of the Grand Challenge goal that the vehicle they intend to deliver will be capable of no more than delivery of cargo from point A to point B, I in no way implied that the DoD isn't interested in the idea of autonomous armed combat vehicles in general and doesn't have other programs in various states of completion working towards that goal.

Dumbass.

Re:so wait..

[iamlucky13]

I see. Parent must've been modded down to heck, because I couldn't find the comment.

Re:so wait..

[Surt]

Indeed, it appears to have been modded down severely, I can no longer easily find it either. At the time I responded it was at +5, so some mod posse must have gotten mad at it.

Re:so wait..

[Anonymous Coward]

And you're a looney bin.

"Soviet Union was not a threat to Western Europe."

Facts counter you easily. Say that to the satellite nations which were subservient to Soviet military strength. Say that to the blockade of Berlin. Say that to trying to subjugate Berlin after going in a raping nearly the whole female population of that city.

Complete inane bullshit on your part.

"This "threat" was manufactured by US propaganda to justify the Cold War agains the Soviet Union."

Yup, namely because destablizied nations such as those in Europe and the Pacific front were ripe pickings for uprisings, which the Soviets persisted in cultivating directly if they didn't threaten by force first.

The Cold War was already on during the time the Soviets were supposedly our allies. When they had spies in our nuclear weapons development. When there was a direct outplay from the Soviet's declaring war on Japan in the late stages of the war as a political power and land grab, despite not being involved in the eastern front nearly at all to that point. Oh, you forgot the Soviets declaration of war on Japan when they were, oh, gee, nowhere to be seen prior?

Again, your false claims are directly counter to known history. It has nothing to do with a few papers or propaganda, unless you are also saying the Soviet nation were such idiots that they were played by these classified documents, which would undermine your very point that they were not a threat.

Further, for your disingenous argument lies soley re propaganda, that's why there's a word of it. The Soviet threat was real, namely because of the Soviet propaganda to their own people about US military might. Overblown US claims? Most certainly. Played up by the US? Definitely. But it existed due to their own actions, and our actions did not rise to anything reckless or greater than the political and economic norms of the time. This was the age where in Europe, it was considered a coming of age for young men to go to war.

"To call Bosnia altruism is just as ridiculous."

Then what was the benefit to us? Certainly the world's perception of us did not improve, because we had cries from folks claiming the US waited too long to get involved, neighboring countries didn't like us being so close or our military presence (which had no military advantage given our already present bases in Europe), and certainly there was a heavy monetary cost we shouldered.

We didn't give a shit about Bosnia before or since. We did give a shit about people getting murdered because of their look or religion. Bosnia could be wiped from the face of the planet and it would have no impact on our economic or military dominance. So why did we get involved? Altruism IS the only answer.

Besides, what we did was still better than what the rest of the world, you wankers, we doing. Better than what was going on at the time, and far more than what the direct European nations neighboring Yugoslavia were doing. Are you saying every mistake the US does is direct evidence that we should not get involved?

Under the Europe's nose, you let the Holocaust occur. Under your nose even with US involvement, you let the Soviets wreck economically and environmentally eastern block Europe and this went on even WITHOUT US involvement because the Soviets were scared of the US. Under your nose, you directly caused 2 world wars. Under your nose, you didn't have the economic capacity or the wherewithall to come up with a global economy which leads directly to fewer wars (most wars are started for the same reason the US is in Iraq--they have something the invading country wants, something a more capitalistic world economy directly offsets).

You are a nutcase who reads a few papers and thinks conspiracy and then carries that over to some larger one that involves the world's evils. Conpiracy, plan propaganada, maybe, but nothing to rise to the overall world trend which involved other parties. The US beat up on our own neighbors; Canada and

Re:so wait..

[danila]

Say that to trying to subjugate Berlin after going in a raping nearly the whole female population of that city.

Facts counter you easily. Complete inane bullshit on your part.

The Cold War was already on during the time the Soviets were supposedly our allies. When they had spies in our nuclear weapons development. When there was a direct outplay from the Soviet's declaring war on Japan in the late stages of the war as a political power and land grab, despite not being involved in the eastern front nearly at all to that point. Oh, you forgot the Soviets declaration of war on Japan when they were, oh, gee, nowhere to be seen prior?

What? What? What? Do you enjoy making stuff up that much? Please try to build a coherent argument and not just ramble on, ok?

Further, for your disingenous argument lies soley re propaganda, that's why there's a word of it. The Soviet threat was real, namely because of the Soviet propaganda to their own people about US military might. Overblown US claims? Most certainly. Played up by the US? Definitely. But it existed due to their own actions, and our actions did not rise to anything reckless or greater than the political and economic norms of the time. This was the age where in Europe, it was considered a coming of age for young men to go to war.

Are you on crack?

We didn't give a shit about Bosnia before or since. We did give a shit about people getting murdered because of their look or religion.
Do the words "Tutsi" and "Hutu" ring a bell? I thought not.

What you say doesn't make any sense. I can't really respond to that rationally, because how does one respond to such gibberish? You just make stuff up, pile one outlandish claim upon another. You don't seem to care about facts or reality.

Really, you seem to be crazy. Can't help you much, though, sorry, pal.

Good news

[Data Link Layer]

I honestly didn't think this contest would ever be won. Maybe in 20 years we can have auto driving cars that can make it so there is next to 0 car accidents.

Re:Good news

[freg]

I'm fully confident in our ability to make good software to meet ever increasing challenges, even to the point that we can have smart cars who take over driving if the driver is incapacitated. But to have a car drive me around on its own free will is a level of trust I wouldn't leave with Microsoft or any car manufacturer around today.

Re:Good news

[OverlordQ]

I would, I sure as hell couldn't build/design a car, much less one that'd pass the strict federal safety guidelines. If not them, then who?

Re:Good news

[Council]

Maybe in 20 years we can have auto driving cars that can make it so there is next to 0 car accidents.

This is problematic.

Re:Good news

[October_30th]

But to have a car drive me around on its own free will is a level of trust I wouldn't leave with Microsoft or any car manufacturer around today.

I would certainly let a computer drive me around in a car -- whenever I fly somewhere I'm already trusting my life to a computer.

Modern commercial passanger airplanes come with fly-by-wire flight control system. That means that the onboard computers essentially decide whether or not to adjust the flight surfaces according to the pilot's wishes -- if the computer system gets fuxored, there's no way to fly the plane manually. Doesn't seem to be that big a problem.

Re:Good news

[prefect42]

Aircraft on autopilot aren't exactly good at avoiding flocks of birds and the like though are they?

The skies are a blissful place compared to the M25 on a friday night. The navigation side is easy, avoiding next doors dog is hard.

Re:Good news

[October_30th]

I was not talking about an autopilot. All the commands (including the stick) of the pilot on-board an Airbus 320, for instance, are vetted by the onboard computer. Essentially, the computer flies the plane and the pilot is just asking it to fly in a certain way..

Re:Good news

[cerberusss]

Maybe in 20 years we can have auto driving cars

I can already imagine the following scene:
You: *steps in car* "Drive me to uncle George?"
Car: "Why do you want me to drive to uncle George"
You: "Because it's his birthday, dammit. Now start driving!"
Car: "You seem to be a bit angry. Where does this anger come from?"
You: "Start DRIVING you gas-guzzling piece of shit!"
Car: *accelerates to 100mph* *dumps core*

Re:Good news

[silas_moeckel]

Funny building a car isn't that hard the power plant is rather complicated but the rest can be made of some nice tube stock and sheet metal for the most part. Granted it wont ride as nice as most commercial cars but it will stand up in an accident better than any of them. Granted I'm talking about good old fashion dune buggy with sheet metal attached. Never had any federal guide line issues just one state inspector made sure nothing would fall off and the wheels were covered.

Re:Good news

[should_be_linear]

Maybe in 20 years we can have auto driving cars that can make it so there is next to 0 car accidents.

Unless those are much requested "flying cars" there is next to 0 chance to create this for legal reasons. Families of walking city crowd killed by such cars would demand trillions from car makers each day. So, car companies will rather leave _you_ responsible. If auto driving cars are flying, thats another story. Without any way to switch to "manual" navigation, accidents could really be eliminated. Users would be allowed only to choose target location from pre-defined set on iPod-like dialer.

Re:Good news

[ta ma de]

We will never have auto-driving cars available for consumers. The auto-manufactures were developing these systems however, they have tabled the efforts; not from failure, but liability. Auto manufactures want the responsibility of driving to reside totally with the driver. They will not risk a single accident from a system that places the responsibility on the manufacturer.

Re:Good news

[prefect42]

Sorry, an incomplete reply on my part. Fly-by-wire is I agree in a critical position, but it's a different challenge. It's not really making decisions, it's just processing the input (from the stick and from wind speed sensors etc.) to determine what to do.

I know you could consider that's all any autonomous system has to do, but it really isn't that complex.

Re:Good news

[Jedi Alec]

We will never have auto-driving cars available for consumers.

Gotta love comments like these...how long have cars been around now? A hundred years or so? Look at the development they've undergone since then. It might start as a small pilot somewhere but something like this will happen at some point. Governments change, people die, but scientific progress seems to be unstoppable when looked at in a bigger picture.

Re:Good news

[rjstanford]

Granted it wont ride as nice as most commercial cars but it will stand up in an accident better than any of them.

Personally, I'd rather have a car designed to absorb that impact at the cost of itself rather than just passing it along to me... heck, maybe I'm just weird that way. Forces have to go somewhere, don't'cha know.

Re:Good news

[stienman]

The intial phase of automatic driving cars would only be on freeways in a special lane. The cars would communicate with each other in a limited fashion and form very efficient "trains" following relatively closely. The car would be capable of moving in such a lane, and merging into and out of that lane, but little else.

Once people find that the automatic lane saves 10-15 minutes or more (cars don't rubberneck, they can all accelerate/decellerate as a train, etc) then they will upgrade to have the units. Eventually the freeway would consist of fewer 'regular' lanes than automatic lanes.

Automatic cars on regulars roads - that's many decades away.

But we can automate what we're able to automate. It'll be the best of both worlds - private tranpsortation with all the freedoms of a personal vehicle, as well as many of the benefits of public transportation (cheaper since it'll be more fuel efficient, don't have to focus on the road during the commute, etc)

-Adam

Re:Good news

[ta ma de]

I shall rephrase, no one alive today will live long enough to purchase an auto-pilot car. Until legislation is adopted that limits a manufacture's liability, no car builder will knowingly risk being the cause of an accident. If a car crashed on auto-pilot the insurance company would deny the claim based on the fact that the insured was not driving. The claimant's insurance company then files suite against the manufacturer. It doesn't take a legal sooper-genius to see that no sane company would offer a product that has unlimited potential for litigation.

One could argue that the systems will improve and mitigate the risk, however with improved systems comes proportional increases in responsibility. The auto manufactures want the responsibility of an accident to lie solely with the driver, and they are not going to be that driver. If you want an auto-pilot car you will have to build it yourself.

Re:Good news

[jacksonj04]

The trouble is, how would you merge? You would need to be driving alongside the auto lane on manual as you switched to automatic, which then leaves the car the decidedly tricky job of working out *exactly* how to get from what you were doing to what it should be doing without damaging anything in the automatic lane, or accelerating into the back of the car in front of you. Merging out would be even worse, since you would be coming off a fully automatic lane at say 100mph, into a flow of manual traffic. The whole system would need to work out where other cars were which may not have a transponder *before* trying to merge into the side of them.

The only solution I can think of, at least initially, is to have 'transfer' lanes which you will merge into manually, then the system will take over control and move you into the next free space in the fully automatic lane. If you say the only cars permitted in the transfer lane are transponder equipped cars, at least you stand a chance of knowing where they are and how fast they are moving. This also allows for the possibility of merging you out of the fully automatic lane and then slowing you down before handing control over without slowing down the 'fast' lane.

Re:Good news

[Anonymous Coward]

You're acting like such limited liability legislation will never be adopted, or at least is very unlikely to be adopted. It doesn't seem that hard to do: "In instances in which an electronically or mechanically controlled device causes property damage or destruction, or harm or death to an individual, the manufacturer of the electronic or mechanical control component shall assume no liability if a competent human controller would've likely caused at least the same amount of harm." Or we could set up some regulations that if passed, makes the computer controlled car both legal and absolved from any litigation.

Now, the challenge lies with actually passing such legislation. On one side, you have trial attorneys that will oppose it. On the other hand, you could create a lobby group that includes car manufacturers, transportation companies, insurance companies, etc... to push for the legislation. It seems perfectly reasonable to me that such legislation could be passed during our lifetimes. We have similar laws for drug companies. We also currently have a government in power that favors limited corporation liabilty (among other tort reforms) and would likely pass such legislation especially if there were some serious lobby effort behind it.

Re:Good news

[lowrydr310]

Is your dune buggy street legal?

It's funny how our laws are written. I know a guy who built a Lamborghini Countach kit car out of some steel tubing, a pre-made fiberglass body, and an engine that isn't even close to passing federal emission laws. He had no problems getting it inspected, registered, and getting a license plate for it. Custom choppers are the same: It's easy to weld some tubing together and slap on wheels, an engine, and a transmission and you're out on the streets in no time!

I want to import a new Toyota Hilux diesel pickup because a compact diesel pickup truck isn't available in the USA. Unfortunately I'm not allowed to do this because it hasn't been tested against US crash standards and the engine isn't EPA certified (despite being less polluting than just about any diesel engine currently offered in the USA).

Re:Good news

[OwnedByTwoCats]

I would be more than willing to let the machines drive me around for the parts of my journey that were on limited-access, multi-lane highways that had the appropriate infrastructure for the machines. I travel (mostly) to get places, and if I can get there without the boring bits demanding my attention (and consequent risks if my attention wanders), so much the better.

The choice of conditions reduces the problem space. I don't need to trust my car to do the right thing when a kid chases a ball out into the highway; it won't happen (unless there's a breakdown, and then the machine alerts me, following traffic, and slows down, yadda yadda yadda). Likewise, oncoming traffic. Blind curves... won't be there. Engineered for 70 mph, and going 70 mph. The robot won't have to decide whether the grade is too steep.

Sudden onset of poor driving conditions would be the hardest engineering and safety challenge.

When the car gets to the off ramp, I am rested and ready to do the driving again.

Re:Good news

[Enrico Pulatzo]

Where I grew up, as long as there are deer, there will be accidents :)

Re:Good news

[usrusr]

Personally, I'd rather have a car designed to absorb that impact at the cost of itself rather than just passing it along to me... heck, maybe I'm just weird that way. Forces have to go somewhere, don't'cha know.

If it packs enough mass those forces will simply go into the other vehicle involved. Just don't try to hit another SUV, i abolutely see your point :-)

Re:Good news

[mustangsal66]

Users would be allowed only to choose target location from pre-defined set on iPod-like dialer.
Great. Would each location cost 99 cents? Would I have to repurchase these locations if I upgrade my car? Would I be allowed to use these location in my wife's car, or allow her to borrow my locations?

Just kidding around. I like this contest. If we had to go into battle, I'd rather throw a few million dollars of robots there, then our children.

Re:Good news

[Anonymous Coward]

Merging out would be even worse, since you would be coming off a fully automatic lane at say 100mph, into a flow of manual traffic.

Where I live, I am able to navigate my vehicle from a complete stop onto the highway via these amazing on/off ramps. I even see other people completing the task with no problems. How would this be different than the limited access HOV lanes? Cars could use a ramp to enter the system and a ramp to exit the system.

Re:Good news

[jacksonj04]

It still doesn't solve the problem of needing a zone where the car can slow down in order to exit without slowing the rest of the lane. What you are suggesting is either putting the auto lane on the inside, which means manual traffic will need to cross it, or building a whole new lane with dedicated ramps etc.

Re:Good news

[ahem]

I can't imagine that a human flying a plane at 300mph (400 feet per second) would be able to see a flock of birds far enough away to be able to effectively dodge, either. I think planes just fly through birds, and the airplane's components are tested by hurling frozen turkeys at or into the various parts (like windscreens and engines).

From Snopes:

The chicken gun (also known as the chicken cannon, turkey gun, or rooster booster) has been around since 1972. It's used for the "chicken ingestion test," one of a series of stress tests required by the Federal Aviation Administration before a new jet engine design can be certified. The tests take place in a concrete building large enough to enclose an entire jet engine. With the engine operating at full speed, the cannon uses compressed air to shoot chicken carcasses into the turbine at 180 mph. (The Air Force is known to launch its poultry projectiles at 400 mph into F-16 canopies.)

Re:Good news

[Daktaklakpak]

Maybe in 20 years we can have auto driving cars...

Now why would you want to have cars driving cars? Isn't that a bit redundant? :)

Re:Good news

[Anonymous Coward]

Hint: Some companies from "the car city" lobbied heavily for "environmentaly friendly diesel standards".

"MOVE OVER BUDDY"

[MosesJones]

Less than 20mph in an SUV through the desert. These Robot control cars are worse than my Grandmother on an interstate.

Quite clearly these Robot controlled cars are part of a sophisticated plot to increase the amount of road rage in the US to enable the Robots to take over the country... and then the world.

It is not too late to stop them, we must insist that the next competition involves only Ford Broncos and takes place on the Freeways of Los Angeles during rush hour.

Re:"MOVE OVER BUDDY"

[Libor Vanek]

AFAIK it was not just desert but there were lot of obstacles on the road. And remember that the main mid-term target of this competition is to create the autonomous supply truck for army - and there you just don't care about the speed (the urgent cargo can be sent always by heli or drop-down).

Re:"MOVE OVER BUDDY"

[earthforce_1]

Yeah but according to Moore's law, the robot cars should be able to break Mach 1 sometime around 2010.

Re:"MOVE OVER BUDDY"

[Chosen Reject]

Yeah but according to Moore's law, the robot cars should be able to break Mach 1 sometime around 2010.

Moore's law states the number of transistor's per square inch will double every 18 months. What does this have to do with speed of a vehicle, especially since it doesn't even have anything to do with the speed of a processor? According to this Moore's law can also be interpreted to be a doubling of data storage every 18 months. But that doesn't have anything to do with going faster.

Re:"MOVE OVER BUDDY"

[EvilMagnus]

This Autonomous Vehicles will not be complete until their right turn signal is switched on all the time.

Patriotism... sigh

[Anonymous Coward]

DARPA Grand Challange - Harnessing American Ingenuity ... as it turns out, the leader of the winning Stanford car team is a German.

Re:Patriotism... sigh

[reed]

Well, so were Einstein, Werner von Braun... etc. :)

Re:Patriotism... sigh

[SimilarityEngine]

In fact, Einstein's nationality was not constant throughout his life (although he was born German) - see here.

Re:Patriotism... sigh

[Flying Purple Wombat]

It ain't the vehicle, it's the robotics!

Completing the Grand Challenge has very little to do with the vehicle chosen, and nearly everything to do with the robotics that drive the thing. VW sponsored the team, so they used a VW vehicle.

The only reason the VW vehicle finished, and finished first, is because the team from Stanford is made of briliant people. I'm sure they would have won with a Jeep, Hummer, Ford or whatever.

My congratulations to all of the teams that finished. That was a difficult problem. I honestly didn't think that any team would finish, given last years performance.

Re:Patriotism... sigh

[Anonymous Coward]

"The only reason the VW vehicle finished, and finished first, is because the team from Stanford is made of briliant people. I'm sure they would have won with a Jeep, Hummer, Ford or whatever."

Well, probably, but it sure made it a lot easier that they were given plenty of VW's to work with, along with VW engineer's to boot. While other folks had to design exterior actuators for throttle / brake / steering along with feedback sensors and the like, Stanford could simply tie into the built in vehicle computer and harness the drive-by-wire features. And unlike others who had vehicle computers on board, they didn't have to reverse engineer the vehicle computer. Now again, those guys were smart and they still had a ton of things to tackle (like the rest of us), but they got half of the equation handed to them. And don't think that VW just donated a single vehicle. Like Red Team (AM General and GM in their case) they were sporting multiple vehicles. In fact they had another robot identical to Stanley (except for smaller computers on board) that they just used for spare parts. Must be nice.

I give props (oh yes I said it) to grey team. They probably dumped money into their vehicle, but I am willing to bet it is a small fraction compared to CMU and Stanford.

As with anything, knowledge is behind everything, but money sure makes it easier.

Re:Patriotism... sigh

[Anonymous Coward]

"Our Germans are better than their Germans."
-- The Right Stuff

Re:Patriotism... sigh

[Locke2005]

This is America... we don't breed the smartest people in the world, we just attract them from wherever they happen to have been born. Ultimately, the ability to attract the brightest, most highly motivated people from all over the world has always been America's only real advantage.

How few remain

[necro81]

Looking at the final stats on the Grand Challenge website, it would seem that only five teams, out of the 23 that made the finals, were able to finish the course. The team that got the farthest before calling it quits managed about 80 miles, which means that the cut between those who made it and those who didn't was still pretty big. Another interesting thing about the final results is that, if you look at the pretty red and blue graph lines, they describe what looks like a sort of decaying function...

Or perhaps I'm just a dork.

Re:How few remain

[knix]

I believe that team, Team ENSCO just blew a tire. They were doing very well and on pace to win I think until they had a mechanical malfunction, not a computer malfunction.

Re:How few remain

[Anonymous Coward]

It would be really nice if there was some place to look up why the teams that didn't make it had to stop. The last-place team made it 0 miles, but it's unclear as to why - the DARPA page doesn't say, and one of the more accurate listings of reasons suggests that either they were disqualified or their vehicle broke down before it could actually start the race.

A lot of the vehicles that didn't make it seem to have stopped due to equipment failures - primarily various sensors malfunctioning. It would be really interesting to find out why the ones that didn't finish didn't.

Broken sensor? Drove into a reporter? Tire fell off?

It would be nice to know where the weak link was - poor hardware, poor software, or just a poor car?

So if you know where to find this information, I'd love to know. :-)

Re:How few remain

[eh2o]

Someone from ENSCO said they suspected that the blown tire may have actually been due to a computer malfunction. The jury is still out until they do a detailed analysis of the logs.

Re:How few remain

[Gryphn]

http://en.wikipedia.org/wiki/2005_DARPA_Grand_Chal lenge has information on some of the failures.

Re:How few remain

[zurmikopa]

They blew a tire and were somewhere around 60 feet off course when they were eliminated, if I remember correctly.

I know that a good number of the teams were actually still moving when they were eliminated; they had generally just wandered far enough off course that it was determined that they would be unable to finish.

There were a number of reasons why people did so much better this year than last year.

The biggest reason I think is that people knew a little better what to expect this year, and focused development on more important items for the race. For instance, for the first race I had done work on using a terrain database for path planning, but it turned out that the waypoints are so close together that it ends up just being a waste of CPU cycles for the most part.

Another important reason is there was a rather large jump in the quality of the software running on the bots, and a moderate jump in the quality of the hardware. The integration was much more refined.

Finally, the course was easier overall this year and the difficult part was put near the end. There was nothing in the course really comparable to Daggett ridge from the first race. Also, pretty much the entire course was graded along with the edges of the road often had banks. We had cliff detection that pretty much went unused this year due to this.

Overall, it was a pretty good race this year. Stanford did an awesome job and really deserved the win. Not that you guys have that much interest, but we (Axion) ended up in 7th place (right after Ensco) with about 66 miles. We ended up getting stuck in some sand. The current candidate for the cause is a broken sway arm bracket that caused us to pull to the right a bit. Further analysis will be required to determine if that's actually the case.

Re:How few remain

[cheesy9999]

Hey, you guys may not have won, but you had the hottest models out of them all so I give you props for that!

The downside to this

[Elrac]

While I'm happy that these hard-working academics were successful, I can't help but note the downside to this development.

Forget military applications. What I foresee is that, for computer scientists who've lost their jobs to outsourcing, this will deprive them of one more alternative, namely a career as a taxi/truck/bus/etc driver.

Re:The downside to this

[Anonymous Coward]

Forget military applications. What I foresee is that, for computer scientists who've lost their jobs to outsourcing, this will deprive them of one more alternative, namely a career as a taxi/truck/bus/etc driver.

Not to disparage the Grand Challenge results, but if you actually think about it, you'll realize that menuvering through moving traffic is a lot more difficult than driving down an almost deserted desert road.

19.1?

[Donniedarkness]

19.1 mph? I mean, congradulations to the winners, and I'm sure there's a reason for the speed to be so low...but can anyone explain what that is to me?

I mean, I can understand the fastest solar-powered vehicle going just over 100..... but what is the reason for these driverless vehicles? I understand that they navigate these things by themselves, but is there any other reason? Is the track pretty much nothing but ridiculous curves or something?

Re:19.1?

[Schweg]

Almost 20 miles per hour on unpaved roads with an autonomous vehicle? That's not the same as driving on paved roads in the city or on the highway. I think that's pretty good, actually.

Re:19.1?

[jrboatright]

Take a look at the route on the darpa web site.

Portions of the route DARPA set the speed limit as low as 5 mph. The highest speed limit on the course was 45 mph. The route included very very narrow passages, twisty bits along the side of mountains with 100 foot droppoffs and no guard rails, chunks with no roads at all going through gullies, tunnels with no GPS feeds where you have to navigate inertially and with sensors.

This was _hard_

Re:19.1?

[necro81]

The course did have a fair number of twists and turns in it. There were some places, like dried lake beds, where the cars could open up a bit, but for the most part it was bumpy dirt tracks one which even you or I couldn't do more than, say, 40 mph. There were also, intentionally, a fair number of obstacles designed to throw the computer systems off. You and I wouldn't have much difficulty in recognizing a cattle gate on a road, but imagine trying to teach a computer vision system to distinguish that. In other cases, the robots had to drive through tunnels that would not only be dark (making vision systems less accurate) but also lack any GPS signal.

So, yes, it did average out to a pretty slow "race." But, on the other hand, it is a marked improvement over last time, when no one even came close to finishing. I think that, in the interests of trying to ensure that they safely finished the course, let alone win, the various teams were playing it a little conservatively, and not trying to go for pedal-to-the-metal performance. Maybe next year, now that they have some confidence.

Re:19.1?

[Anonymous Coward]

I swear I am so tired of people who post ignorant shit here. RTFA asshole. They have to drive on open terrain in the desert. The desert in california is not sand like the sahara. It's pretty damn rough terrain with lots of plants and rocks. I'd like to see you manually drive a truck out there at 20mph. $20 says you'd get stuck.

Re:19.1?

[Anonymous Coward]

There were speed limits set on the course in some areas as low as 20 mph.

Re:19.1?

[necro81]

One other thing to note is that this is hardly the first instance of cars driving themselves. Even in the late 1990's, there were several institutions that had programs to develop cars that could drive themselves. I believe CMU outfitted a minivan to drive coast to coast autonomously. There were some caveats, like having a human driver in the seat, hands poised over the steering wheel, ready to take control in an instance. I also think that, when the team was pulling off the highway to find a motel for the night, that was done by humans, too. But, for the highway stretches, where the car was operating autonomously, the vehicle was able to cruise at highway speeds (i.e., around 65 mph).

Re:19.1?

[Yvanhoe]

In fact, one member of the team explained in a conference that they aimed to finish the race. Which was already a great achievement. DARPA has put a time limit on the race and Stanford chose a speed which was the lowest possible (to lower risks of accidents) while still providing a secure margin for unexpected events. (From what I remember, they planed to have an average of 30 mph so they race must have been thougher than they thought)

If there is a Grand Challenge in 2006, it will probably look more like a race, now that everyone knows it is possible.

Re:19.1?

[jbburks]

Yes, and the Wright Brothers' first flight was 120 feet - less than the wingspan of a MEDIUM-sized plane today. Everyone said (even for the first ten years or so) "why bother flying" when the railroads were the way to travel. Read Clayton Christensen's book "Innovator's Dilemma" for more ideas on how 'small' technologies can end up taking over.

Re:19.1?

[Donniedarkness]

Oh, I wasn't insulting the technology, nor the achievements of those involved in this competition. I think things like this are wonderful, and should get more media attention and perhaps government funding. I was just simply confused as to why the speed was so low (I understand now, after reading all the replies... THANKS, guys!).

Re:19.1?

[pstapley]

You mean besides the fact that it is hard to create an autonomous vehicle? These vehicles have to take many things into account and try to make sense of it. I am sure this is probably why the average speed is so slow. It is also easier to avoid obstacles when moving at a slower speed. This is the first time this has been done and you are wondering why the vehicles are not averaging 80mph down the road.

Re:19.1?

[kc01]

Lower speeds are quite normal when driving off-road. There are all sorts of things to negotiate around- rocks, bushes, holes, etc. I ride motorcycles both on- and off-road. I ride freeway speeds on the asphalt, but commonly 15-35 on the dirt. Believe me, 35 on dirt, even on mildly rough dirt roads, can be considered flying! For bushwhacking across the desert, fording streams and bouncing around rocks, 19.1 is pretty respectable, especially for a robot who doesn't have the benefit of millions of years evolution learning how to balance.

Remember, that's an average speed- Sometimes it's easy to fly across the landscape, other times you have to crawl over obstacles.

Re:19.1?

[igny]

So they could go 10mph in some places, and up to 50mph in others. 19 mph is still inexcusable.

Re:19.1?

[Anonymous Coward]

Going according to previous statements by Slashdotters, the sensors could see 30 feet ahead. 19.1 mi/hr = 28.01 ft/sec.

Re:19.1?

[Anonymous Coward]

You do it then.

Re:19.1?

[Anonymous Coward]

Prediction: he won't reply to your comment. Another Internet tough guy gets the boots.

Re:19.1?

[Anonymous Coward]

19.1 mph? I mean, congradulations to the winners, and I'm sure there's a reason for the speed to be so low...but can anyone explain what that is to me?

20 mph isn't bad for an off-road vehicle, or military convoy (which is the ultimate goal of this technology). Last time I went for a ride in a Humvee across the Iraqi desert, we didn't go much more than 30 mph - and that was over mostly flat desert.

Re:19.1?

[yincrash]

DARPA made the max speed for the race be 45mph

Re:19.1?

[SamSim]

Speaking for robot-kind: faster than you, meatbag.

News?

[Anonymous Coward]

Darpa has just announced? I read this in my morning paper (in the UK) several hours ago.

Re:News?

[Anonymous Coward]

pesky brits.

Stanford + Volkswagen

[SamuraiMike]

"Drivers unnecessary"

Re:Stanford + Volkswagen

[Locutus]

There IS a driver onboard, but the driver is in the glovebox and he's a cute little penguin.

Actually, 7 penguins kept Stanley on course and pointed at the finish line -
Tom's Hardware: Driven By Linux: Laser Sensors, Stereo Camera And GPS Navigation
http://www.tomshardware.com/game/20050713/darpa-03 .html

Re:Stanford + Volkswagen

[Anonymous Coward]

It actually did say "Drivers not required" around Stanley's wheel wells, along with the VW logo.

Re:Stanford + Volkswagen

[oliner]

Actually, the side of Stanley was stenciled with the phrase "Drivers not required" in the VW slogan font. They beat you to the punchline. :-)

More info

[Zathrus]

For far better info than the anemic (and completely flash based) gc.org site:

http://www.darpa.mil/grandchallenge/discussion.htm l -- DARPA's GC message boards
http://www.tgdaily.com/2005/10/08/darpagrandchalle nge2005/ -- Was updated throughout the actual event. Best coverage I've seen yet.
http://www.popsci.com/popsci/darpachallenge/ -- Popular Science's rather disorganized site

I'm still looking for "highlight" video myself... or pretty much any non-bland video (seeing them cross the finish line is nifty and all, but that was not a challenging part of the race). I particularly want video of Alice trying to take out some reporters!

evil german scientists

[mbaudis]

well, german genius. do i have to remind slashdot of the other great evil german scientist of this century - prof. Krassman? "do you think we sleep in duesseldorf? do you think we take a nap at cologne? we work ..." and "if i can inflict some pain, i sleep well at night" apologies to mel brooks and the muppet crowd for errors...

Stanley hasnt won

[rajeshgoli]

Its just the first to cross. From the site: " .. this is a time elapsed challenge.. The winner will be decided after all the robots either complete the race or drop out "

Re:Stanley hasnt won

[Anonymous Coward]

The race was run on Saturday. The final results have been posted for over a day now. The confusion is understandable, however. This article is quite late in arriving on slashdot.

Re:Stanley hasnt won

[usrusr]

maybe they are still in the process of uploading the results, you know, DARPA, having all the really really old internet hardware ;)

Rudimentary logic

[hal9000(jr)]

I suspect is the case. Think about all the thinking you do when your driving just to keep your car on a smooth, paved road with every one pretty much following the same set of rules. You have to manage speed, negotiate turns, adjust for bumps, wind, grooves in the pavement. Once you drive long enough, it's pretty much "second nature" but your making adjustments to the vehicle based on visual, aural, and directional input.
Now try to codify that into an algorithim that makes the right decisions 99.999% of the time and can adjust (again, correctly) for the .001 wrong decisions. It's pretty amazing.
A simpler problem is create an algorithm for a robot to enter solve a maze. You could just write a right or left wall following algorithm that will work, eventually, but try to do something smarter.
It's not a trivial task. I imagine as more research is done in this area, speeds will increase. What makes sense to me is a hybrid approach where the vehicles are largely autonomous, with augmented human input and problem solving.

Sorry: wrong info

[rajeshgoli]

The info I had was old.. :-D

Quote from the winner

[VeganBob]

01001001001000000111000001110111011011100110010101 10010000100000011110010110111101110101001000000110 0001011011000110110000101110

Re:Quote from the winner

[FoxDude0486]

After receiving that from the winner after the race, I'd hate to hear the conversation between the vehicles before the race started.

Re:Quote from the winner

[Anonymous Coward]

Translation for the binary disabled:

"I pwned you all."

Re:Quote from the winner

[GweeDo]

The other cars responded with: 01000101011000010111010000100000011011010110010100 101110

Re:Quote from the winner

[stienman]

01001001001000000111000001110111011011100110010101 10010000100000011110010110111101110101001000000110 0001011011000110110000101110

For the binary impaired: "I pwned you all."

-Adam

Re:Quote from the winner

[Archimboldo]

And a couple of the losers powered by Altair 8008's were reputedly swearing using 4 bit words.

Driverless?

[cciRRus]

a $2 million contest for driverless vehicles over a 132 mile course in California's Mohave Desert.

The car is powered by 7 Pentium M laptops. No drivers? Are the laptops running in Safe Mode? Ah, that explains why its average speed is 19.1mph.

Re:Driverless?

[j.bellone]

No, what really happened were that the computers were running Ubantu and they stopped midway for a few hours to run "apt-get." After apt-get was finished, were running good again.

Re:Driverless?

[vertinox]

The car is powered by 7 Pentium M laptops [newscientist.com]. No drivers? Are the laptops running in Safe Mode? Ah, that explains why its average speed is 19.1mph.

The cars powered with AMD chips averaged about 80mph... til they overheated in the desert sun in 5 minutes after starting. The Mac G5's drained all the power cars batteries before they left the starting point. The team that used Sun Sparcs couldn't afford gas for the entire trip. The secretley re-released new Cyrix (remember them) powered cars ran comparably to the Intel but would crash into rocks and drive off the sides of cliffs for no good reason (it is a desert you know).

Re:Driverless?

[stienman]

a $2 million contest for driverless vehicles over a 132 mile course

Wow, that's $15,152 per mile.

I thought I was doing good to get $0.48/mile for work.

-Adam

and so was the car

[Anonymous Coward]

a German Volkswagen
and with Delphi entering bankruptcy (plus the ripples it will cause) it looks like the American car industry is more or less over,
of course anyone who has driven a Ford/GM/Chev/American car knew that anyway

20 years? ah!

[XXIstCenturyBoy]

Automatic driving will never happen unless the road itself change (with some sort of built in guidance system or something). Everyone has to have an automatic car, or no one can have one. Imagine a nostalgic 2005' SUV driver on a 2025 road where everyone as a car with easy to predict, set behavior.

cmu won all three

[Anonymous Coward]

sort of.

the stanford leader (thrun) and their lead software developer
(mike montelermo (sp?)) were originally from cmu.
they only recently moved to stanford. although thrun claims it's coz of his wife, some people think it was coz of too much competition and bad blood at cmu which has lots of people working in mobile robots (wittaker, simmons, nourbaksh, choset, ...) while i think palo alto has much better weather than pittsburgh :)

the particle filter based localizer and mapper was developed while at CMU. Frank Dellaert (now at georgia tech) first introduced that to mobile robotics after reading about the
condensation algorithm in computer vision (i like to believe that i had a part in that last bit :) I would'nt be surprised if they also use large parts of the basic control and command software infrastructure (TCX) written by thrun and others while at cmu. if it is, no wonder they required
7 PCs for redundancy, that is some of the worst spaghetti code i've ever had the displeasure of working with. it's easier to make it fault-tolerant by just throwing more hardware at it.

i'm not trying to belittle stanford in any way, but i just thought people might be interested in knowing that the real story in this case is a lot more complicated. the relationship between the winning teams were a lot more incestuous :)

thrun BTW is an amazing all-round guy with an infectious smile all the time.

Re:cmu won all three

[Anonymous Coward]

Agreed. Our team called Stanford "Red Team Three".

Both teams seemed like one during the NQE.

I personally am most excited about Grey Team, who finished the course and most importantly is *not* CMU or Stanford.

Re:cmu won all three

[Anonymous Coward]

If you're curious, Mike Montemerlo graduated with his Ph.D. from CMU's Robotics Institute right about when Sebastian Thrun defected from CMU to the better weather found in Palo Alto, in 2003. Mike's thesis work was advised by both Thrun and Red Whittaker, as shown here

So, yes, a lot of work on Stanley was based upon work done at CMU, but let's not forget the addition of vision work done at Stanford as well as the help of the VW people, as I'm sure they were both critical in Stanley's success.

Re:cmu won all three

[epgandalf]

I haven't heard too much about bad blood between Robotics Faculty at CMU. I do know that Red Wittaker is a real slave driver. Someone I know quit working on Sandstorm because he didn't like Red. Another person I knew kept working even though he knew that he wouldn't be sleeping at all for about 2 years.
I also know that there's some bad blood between Illah Nourbakhsh and Howie Choset. Illah's a great guy and Howie is a real asshole. Anyone who's taken robotics classes at CMU knows what I'm talking about.

Re:cmu won all three

[Anonymous Coward]

Any way you look at it, it's not surprising to me that Stanford pulled it off. I mean, isn't there some crazy statistic that over 50% of Silicon Valley's tech industry comes from companies of Stanford alumni (HP, Google, SUN, Yahoo, SGI, Cisco etc. etc. etc.)? I guess this is just another W under their belt, which makes for some very cocky Stanford people and some very very bitter CMU people.

This is awesome

[CrazyJim1]

I thought the sensors on the cars wouldn't be able to avoid obstacles in the road. I'm quite interested in where this might lead. If they have sensors that can tackle big static objects in the road, maybe they can refine them for more advanced driving. I'm pleasantly suprised.

Re:This is awesome

[Anonymous Coward]

Been done -- ten years ago! Highways are much easier than the desert, especially if you DO have a driver on board who can intervene. Google for "No Hands Across America", e.g.
http://www.cs.cmu.edu/afs/cs/user/tjochem/www/nhaa /nhaa_home_page.html

Why so long to post?

[brindafella]

The real question for me is, "Why did it take at least 7 hours after I saw this online for the information to appear on /.?" I did not even bother to go near /. to post it, because I figured that I'd been comprehensively beaten to the story. And, I know that the story had been online several hours by the time I saw it. So, why the big delay, /.?

Can we install this system in all the cars in LA?

[tinrobot]

I think having the robots drive would be much safer than having to deal with drunks, rageaholics, and senile citizens who can't tell the difference between the gas and brake.

Gray Team?

[mikeee]

Anybody know anything about the Gray Team and their bot? Their 4th-place finish seems to be far the best of any of the 'low budget' teams; about all I can find is that it was sponsored by The Gray Insurance Co., that their IT department (and founders who were bored of spending money on yachts?) worked on it, as well as some Tulane students, and that it was a Ford Escape (small SUV) hybrid.

They don't seem to have a webpage for the team...

Re:Gray Team?

[Anonymous Coward]

Gray Team included at least two students from Tulane U. Other than that, I don't know much else about it.

Re:Gray Team?

[ET097]

I go to Tulane and I can think of about 5 Tulane students I know who helped with the bot at one point or another including one of my good friends. Tulane was mostly helping out with programming and I know they were using Java. The story I heard is the sailboat Gray Insurance had been spending money on sunk, so they decided to enter the grand challenge for fun. Luckily the car wasn't destroyed by Hurricane Katrina (they were keeping it about an hour outside of New Orleans). Some of the Tulane students stopped working with the project after the hurricane because they are attending school this semester in other states (since Tulane is closed right now), but a few of the guys took the semester off to work on it full time. As a side note, I am impressed that anything my friend touched actually worked and did what it was supposed to since I personally know his track record of breaking things over the past three years (including MY CAR).

Re:Gray Team?

[blackcoot]

their vehicle was equipped with two novatel gpses and setup to do differential gps. they had at least two sicks mounted on top of their vehicle mounted so that the lasers were scanning vertically. the scanners pivoted on their mounts. they may have had an additional sick scanning horizontally (i don't recall).

they were running a mix of mac minis, a power book, and some linux boxes.

("my" team was right next to them, so we got to have a chat with them).

all in all, i'm very impressed by what they accomplished. their practice runs were in a walmart parking lot at 2am (i guess they did a good job of obstacle avoidance by necessity!).

a great add for linux

[Anonymous Coward]

This vehicle is a great potential ad for whatever linux group wants to put it together....."in some conditions, you just can't afford a blue screen of death"

Re:a great add for linux

[Anonymous Coward]

Yeah... great for an advertisement some 5 years or more ago.

Re:a great add for linux

[Anonymous Coward]

Fine, "in some conditions, you just can't afford a red screen of death". Happy?

Luckily...

[benhocking]

Luckily, there are very few trees on Mars! One of the stated objectives of the DARPA Grand Challenge was to contributed to unmanned missions to Mars, etc. The main reason for having a totally autonomous system (as opposed to one that responds to remote control) is for when the lag time for remote control is too large.

Granted, the tree observation does potentially limit Terran deployments.

Re:Luckily...

[CreatureComfort]

Actually, planetary rovers are just a tiny, tiny portion of the reason for this challenge, otherwise NASA would be sponsoring this, not DARPA. The primary reason for this challenge is for troop supply and support vehicles that can accompany troops into a battlefield, or be sent in autonomously. Which means the jungle scenario is non-trivial. One of the reasons the challenge is being held where it is, is due to the development lifetime projected force deployments being in mainly desert regions. Another major projected use for these kinds of vehicles is for deployment in a bio-hazardous area for testing and sampling in an autonomous measure. But once again, the is a DARPA challenge, not a CDC one.

Re:Luckily...

[usrusr]

we all know the real challenge will be autonomously driving a tanker truck filled with nothing but sand while hordes of insane punks on jury-rigged buggies are trying to stop the vehicle.

but you are surely right about the the mars rover scenario, it is most likely just a cheap excuse to keep pacificsts who are able to resolve some levels of indirection from shouting "murderers" at the teams. after all we wont be seeing any humvee-sized mars rovers anytime soon and vehicle speed is not a bottleneck as the prolonged mission of the current rovers shows.

Re:Luckily...

[plover]

What you've written is absolutely true -- deserts are the ideal terrain for a first deployment of autonomous vehicles. But I suspect these may fall prey to the same fate as other autonomous technology we've seen deployed in a hostile environment, namely unattended web servers on the internet. How long will it take the bad-guys (hackers) to figure out that a row of inflated garbage bags might appear as impassable boulders to these things? Or that a couple of mannequins may act like scarecrows, making the machines falsely report "hostile activity"? Or that they can perhaps "paint a hole" (a la Wile E. Coyote) that the robot will think it has to dodge? (Not to mention a little pile of "FREE BIRD SEED" on a cardboard train track!)

Yes, I know that various radars and sensors can detect those specific ruses, but I'm suggesting that a determined opponent would have lots more incentive to try lots of tricks to defeat these things. If a $10 trick can keep the U.S. Army from sending well-equipped forces down your valley, that's a helluva good investment.

Autonomy is a nice idea, but it works best in a nice environment. These things might be best suited as "slave units", loosely tethered to a lead vehicle operated (locally or remotely) by an actual human.

Obligatory sillyness

[dapendragon]

I, for one, welcome our new S.U.V. overlords.

Re: Misleading averages

[Anonymous Coward]

Averages are misleading. The robots did well.

Looking around the Net, the average speed for a typical human-driven commuter vehicle in the USA at rush hour is around 16-24 mph depending on the city. Given that, the robots seem to be doing quite well. This weekend I drove for over 2 hours on open highways with the speedometer mostly between 60-70 mph, but when I calculated my average speed it was about 50 mph due to the stop-and-go surface streets at the beginning and end of the trip.

Stanley - Agressive Driver Rehabilitation

[digitaldc]

Stanley would be the perfect vehicle for agressive driver rehabilitation. Replace the agressive driver's vehicle with Stanley and they can do nothing but scream obscenities as it plots its course to their workplace at a blazing 19.1 miles per hour. Three weeks of this and the agressor becomes as docile as a lamb.

Re:Stanley - Agressive Driver Rehabilitation

[blake3737]

Or after a week and a half of rage he reaslize 19.1 mph isn't all much to throw off the aim of his guns, which are even more accurate now that he can use 2 hands on the gun instead of wasting a good arm on that damned streering wheel.

Re:Stanley - Agressive Driver Rehabilitation

[HermanAB]

Actually, that would be very fast in a any city rush hour...

Twice the prize.

[redNuht]

Nuff said.

Sensors

[maximthemagnificent]

That makes sense. I used to do some work with mobile robots at Brown University's AI lab, and I found that the difficulties were all about sensors. Once you could turn the physical obstacles into data abstractions and once you knew where the robot was in relation to them, the algorithms were pretty darned easy. I used to walk around pretending that I only had the information available to the robot and see how I did, with human intelligence, at avoiding obstacles. Our vision system was very slow and took 3 seconds per frame, so I'd close my eyes and blink them open for an instant every three seconds. It was very hard. Moving slow helped a lot, of course. Of course we were running on a 486 back then...

drivin' drunk

[buback]

If I'm drunk and alone in a bar parking lot, I would be praying for an autodrive car, 'cause it would have a better chance of getting me home safe.

they had no problems...

[zogger]

...with DUI in ye olden days, because no matter how snookered you got, old dobbin knew the way home. If you could make it into the saddle, the rest was biological guidance system that could function quite well with little to no input from the pilot/driver/operator. The fuel source was environmentally friendly and sustainable as well, heh. Solar powered, intelligent and self replicating, something to be said for the "old ways".

Stanley = not the Mac Touareg..

[microcars]

When I first saw this news ELSEWHERE (google news) I thought it was the Touareg that was "powered by Mac OS X"

*bzzzttt*

that one doesn't even register on the chart as having moved.

Integrity of the Stanford University Team Leader

[despinoza]

Maybe it has not incurred to anyone yet, but if you check out Sebastian Thurn's homepage, and download his C.V. http://robots.stanford.edu/cv.html (bottom of the page) or even check on the home page of the Carnegie Mellon University http://news.cs.cmu.edu/Releases/demo/33.html, he said correctly in German that he did obtain his VORDIPLOM. He, however translates this as having attained his B.Sc.. If you check with the German translation engine Leo (provided by the University of Munich), and enter the name VORDIPLOM into the box dict.leo.org, the following items come up: intermediate diploma das Vordiplom p intermediate examination das Vordiplom p pre-degree das Vordiplom p. Given that a Vordiplom is NOT a degree leading to a profession, but a pre-degree and that as a rule of thumb, it should be attained after TWO years of study, and a B.Sc. (Honours degree) can take up to FOUR years, Mr. Thrun has either a poor command in the English language, or for his U.S. employers, he has not told the truth, I am afraid to say. I think academic integrity should also entail the respective person's C.V.!

Sir you've got your head on the wrong way around

[Anonymous Coward]

You're making a very strange argument, are you saying a German can't be an integral part of harnessing American ingenuity? Perchance you've mixed up patriotism with nationalism?

Hasn't it always been the case, and still is, that America attracts many (if not most) of the finest scientist, engineers, analysts, and thinkers no matter where they were born or the type of society they originate from?

My answer would be yes.

You see for all the populist scorn the United States of America receives both within and outside its borders the fact of the matter is that for all its faults the U.S.A. still actually works pretty well (or do you perhaps think that people travel to work and live and integrate into the U.S. because somebody forced them? Do you think a large percentage of middle eastern youth and grownups look to american institutions of learning and justice because they were brainwashed? Do you think the U.S. government has such influence internationally because others don't want them to have it? Except France once in a while on that last one ;) but everyone knows why and it's ok once in a while lol).

*Glomps America from across the pond*

What makes America great is its openness to anybody who wants to achieve, you don't get much for free except tons of opportunity, it might not be the best place in the world for people like me who haven't achieved much of anything but I'm truly happy such a place does exist, even with its faults.

Why isn't this a bigger deal?

[prozac79]

Why is the fact that 5 autonomous vehicles where able to traverse 132 miles not a bigger deal? I hardly saw any media coverage on this (not even mentioned in those closing "isn't this interesting" segments on local news). IMHO, this is another great "first" for mankind on par with Lindberg crossing the Atlantic or Rutan winning the X Prize. In the future, when automnomous vehicles are more ubiquitous, we will see that the pioneers were vehicles like Stanley. These engineers solved (or at least furthered our understanding) some very difficult problems of computer vision and perception. However, whenever I mention the Grand Challenge to people, they just give me a blank look. One person asked me if the Grand Challenge was some sort of football event.

Oh well, from what I heard no one was too excited about the Wright brothers' achievement at the very beginning either.

Re:Why isn't this a bigger deal?

[tlk nnr]

I hardly saw any media coverage on this (not even mentioned in those closing "isn't this interesting" segments on local news).

There was some coverage in Germany: Main news show in at least some channels. Probably due to Volkswagen, then wanted some advertising for their car.

Re:Why isn't this a bigger deal?

[Anonymous Coward]

Why is the fact that 5 autonomous vehicles where able to traverse 132 miles not a bigger deal?[...]
  One person asked me if the Grand Challenge was some sort of football event.

Some people don't know what the Grand Challenge is all about, some other (me included) know it's just not that big a revolution. I mean it's great OK, but in 2003 during my studies I worked with a research lab in France, and they had a car able to drive autonomously on roads. We encountered similar projects in Germany (with trucks) and in the USA too. I'm sure there are tons of working prototypes elsewhere too.

The fact that you don't know about them (just like your friends don't know about the Grand Challenge) doesn't mean they don't exist.

 

In the future, when automnomous vehicles are more ubiquitous, we will see that the pioneers were vehicles like Stanley.

Stanley is great for what it was designed for, that is driving for the army mainly off road while carrying equipement.
Other projects will be more suited for driving on regular roads and in towns, with passengers onboard.
Different security problems, different unpredictabe events to deal with, different budget and size constraints ...
There's a lot to learn from the Grand Challenge for other projects but they share a lot of common solutions already. (LASER radar and obstacles avoidance comes to mind when I compare Stanley's NQE 4th video with the quite identical video of the project I know about).

Re:Why isn't this a bigger deal?

[doxology]

It's on the front page of the Stanford Daily, for what it's worth.

Re:Why isn't this a bigger deal?

[evilviper]

I hardly saw any media coverage on this (not even mentioned in those closing "isn't this interesting" segments on local news).

Local News isn't a good indicator of anything. Unless you live in Nevada, this isn't local news for you. For anything not local, it has to be extremely significant for local news to cover it.

The fact that most people only watch local news has long been a major source of problems. For example, all the major news outlets listed and debunked the justifications for invading Iraq, on their National/World news programs, long before the first bombs were dropped...

I know that ABC's World News program had a segment a few minutes long on the results of the Grand Challenge. The CBS News website has some interesting RAW video of the race (rtsp://real.tvc.cbsig.net/cbsnews/2005/10/10/vide o931213.rm) which obviously didn't air, but perhaps in a day or so when the news about the earthquake in Pakistan, NYC Subway hoax, and Bird Flu fearmongering die down, you will likely see a story about it.

About Thrun

[Anonymous Coward]

Thrun also has a bad habit of fidgeting really excitedly while he's lecturing, to the point that it looks like he's dancing. It's really quite distracting. -c3

Drivers Wanted

[Anonymous Coward]

I bet the advertising guys didn't have this in mind.

Avoiding Birds...

[OwnedByTwoCats]

Aircraft on autopilot are out of range of birds...

Re:Avoiding Birds...

[prefect42]

Two things.

You'd be surprised how high birds fly, reportedly up to around 20,000 feet. You'll be using Autopilot *way* below that.

Fully automated landings are hardly something new.

mod parent up

[awtbfb]

Related quote:

William "Red" Whittaker, the Red Team leader, minimized whatever disappointment he felt at the finish, noting the close links between Carnegie Mellon and the Stanford leaders -- former CMU professor Sebastian Thrun and a former doctorate student of Dr. Whittaker, Michael Montemerlo.

"You take off those blue shirts," Dr. Whittaker said, referring to the Stanford Racing Team color, "and they're Carnegie Mellon."

I do have to disagree with a comment by the parent: "...some people think it was coz of too much competition and bad blood..." I never perceived this and computer science at CMU is remarkably sparse in bad blood compared to other universities.

Re:Integrity of the Stanford University Team Leade

[bap]

I guess no one cares because once you have a PhD it doesn't really matter if you correctly translate some piddly small German degree as roughly equivalent to the correct piddly small American degree? Maybe he had a typo in the name of his second-grade teacher too: no one cares about that either.

Scoring?

[vectorian798]

Does anyone know how exactly they scored the Grand Challenge? I was watching the leaderboard the whole day as I was coding, and one of the CMU vehicles was the first to finish as far as I can recall...furthermore, the spread BETWEEN the top three vehicles (CMU, Stanford, CMU) seemed to vary from time to time.

I have my doubts as to the validity of the data since there were also a couple glitches during the race where all of a sudden a bunch of vehicles' mileage and stuff were kicked back by a good amount.

Re:Scoring?

[Freeptop]

Keep in mind that each vehicle was racing against the clock, not each other, and they had staggered starting times. Also, the judges for the race had the ability to "pause" the vehicles for various reasons, which would not be considered an impact on their travel time (the clock would be stopped for that vehicle while paused). Apparently most vehicles were paused throughout the race.

That said, I was watching the end of the race, and Stanford's "Stanley" passed CMU's "H1ghlander" about 30-40 miles from the end of the race, pulled ahead by several miles, and kept the lead. Stanley was second out of the gate, and the first to cross the finish line. H1ghlander finished several minutes later, with CMU's "Sandstorm" finishing close behind.

In the end, though H1ghlander was the second to cross the finish line, Sandstorm was actually on the course for less time, and thus, took second place. Gray Team took significantly longer than the top 3 to finish, so it was both the fourth to cross the line, and the fourth in standings, while TerraMax didn't technically complete the requirements (it took longer than 10 hours), though it did finish the course.

Re:Scoring?

[chimpanzee00]

Does anyone know how exactly they scored the Grand Challenge? I was watching the leaderboard the whole day as I was coding, and one of the CMU vehicles was the first to finish as far as I can recall...furthermore, the spread BETWEEN the top three vehicles (CMU, Stanford, CMU) seemed to vary from time to time. I have my doubts as to the validity of the data since there were also a couple glitches during the race where all of a sudden a bunch of vehicles' mileage and stuff were kicked back by a good amount. -------------- I also monitored the GPS based map-tracker the entire Race. Stanley was on H1landers bumper on the upper-portion of the course (west of the 15 fwy). On the bottom part of the course (before Beer Bottle Pass), Stanley made the pass. I uploaded a few screen shots: http://darpagc.textamerica.com/ Stanley was the 1st physical finisher. I was involved with robotics/vision research as a grad student & I am also involved with OffRoad Racing (see http://www.jumplive.com./ I can say this years route seemed to be way easier..mostly just dirt roads. No whoop sections. Last year, it was in the Barstow area, where it can be pretty rough (all the top OffRoad Racing teams test there). Here's a sample of some REAL OffRoad Racing (there was "pausing" for the DARPA GC '05, if a 2nd vehicle got on the bumper of the 1st vehicle): http://web.archive.org/web/20000925132425/www.seel eyracing.com/barstow/end/vgeorgel4fps3.mov It was taken from the area known as "Mile of Danger". Could the 'bots read a "fork" in the desert? Someone (who was part of a team for awhile) claims the DARPA GC was a sham. https://dtsn.darpa.mil/grandc/forum/topic.asp?topi c_id=1657&forum_id=30&Topic_Title=What+a+scam%2C+r ace+wa+sno+challenge+at+all!&forum_title=Grand+Cha llenge+Event&M=False&S= It wasn't a race, more like a rally. I did a LiveWebCast of the SCORE Primm 300 offroad race a month ago: http://primm300.textamerica.com/ These vehicles took an a far rougher/tougher course, even the stock VW Baja Bugs: http://www.dezertrangers.com/iB_html/uploads/post- 1-87711-class11s.jpg I bet one of these bugs coulda placed high (or even won) the DARPA GC. You can see this thread for more pics of the Primm 300: http://www.dezertrangers.com/cgi-bin/ib/ikonboard. cgi?s=e3be4804ea8ddd2f033271bbc686d107;act=ST;f=1; t=27465;st=0 You can see some silty areas. Stanley woulda had a problem, the CMU Hummers probably not.

Re:Scoring?

[chimpanzee00]

2nd try for the URL for the stock VWs: http://www.dezertrangers.com/iB_html/uploads/post- 1-87711-class11s.jpg

Team Grey is the Real Winner

[humankind]

When you look at the results, and you see two colleges with virtually unlimited resources and millions of dollars spent on their vehicles, huge corporate sponsors and engineers at their beck and call from Boeing to Catepillar, who finished, and then this dinky little Team Grey from a suburb of New Orleans, with a splintered development team as a result of the Hurricane Katrina disaster, and they FINISHED just behind the big guys, leaving other heavily-funded vehicles in the dust.

Relatively speaking, a small indy group, even if their time was a tad slower than CMU or Stanford, essentially put those three teams to shame when you compare the resources they had available to them.

The real story here is who is behind the Grey team's car. It must be a far superior design than either CMU or Stanford's considering the limited resources and experience they had in addressing the challenge.

Re:Team Grey is the Real Winner

[humankind]

btw, I guess I misspelled the team name. It's "Gray." Sorry about that.

Probably the Earthquake

[hughk]

The last DARPA challenge had some coverage, most of it along the lines of "Gee look at those stupid retarded robots" with shots of them stuck a few yards from the start line.

This one had almost none. I would like to think that it is because of Earthquake coverage, but there wasn't that much on US TV. This is very sad given the scope of the achievement.

Miles Davis and Vaughan Pratt in Stanford Team

[helfen]

well, they have Miles Davis and Vaughan Pratt in team

Lack of reading comprehension, indeed

[CGameProgrammer]

Note the complete lack of any mention of 'non lethal' and the use of such interesting catch phrases as "autonomous ground vehicles that will help save American lives on the battlefield"

Well they're not going to save American lives in the bathrooms, now are they? The challenge was held in a desert to simulate the conditions of Iraq and Afghanistan because that is where the robots will be deployed -- but not to kill people. Rather, they will be doing the opposite -- helping out the human soldiers that are there, sending aid and cargo, etc.

Obviously DARPA will eventually want completely autonomous killing vehicles but that's not what this particular challenge was about. Navigating an environment without crashing is a hell of a lot easier than choosing a target -- even humans can't tell the difference between innocent civilians and combatants.

Mohave? Spell-check...

[evilviper]

"Mohave"? It's spelled "Mojave"?

See "Mojave Desert", "Mojave River", "Mojave, CA", etc.

Re:Integrity of the Stanford University Team Leade

[despinoza]

For the piddly small American degree is called B.S. and NOT B.Sc., the degree as awarded in the U.K., Eire, Australia, New Zealand, Hong Kong, South africa and India. Being only 17 miles away from where he was born, in Hildesheim, Germany, it really annoys me that a crook is the leader of the stanford team. DARPA chuck them out of the race...at least I care.

Kills the ad campaign

[RexDart]

So much for Volkswagen's 'Drivers wanted' slogan.

Re:Kills the ad campaign

[Anonymous Coward]

Holy crap this joke has yet to be used in this topic?!

Official finish time for TerraMax?

[teneighty]

Has anyone been able to find out the official time (i.e. time with stops/pauses substracted) that TerraMax took to complete the course? I get the impression that TerraMax was really unlucky, getting paused by other competitors many times and then being forced to shutdown for the night.

Also, does anyone know the top speed that was reached by any vehicle on the course?

Re:Official finish time for TerraMax?

[epgandalf]

I don't know the official time for TerraMax, but I do know that it was over 10 hours. They wouldn't have been eligible for a prize even if nobody else had finished.
Still it's impressive that a 16 ton truck was able to get through beer bottle pass.

Highlander

[Deflatamouse!]

I wonder if the H1ghlander team name is referring to CMU's cafeteria. Highlander is the name of the cafeteria at CMU... infamous among students for it's grade D radioactive beef and other yucky food... well, at least that's 6 years ago... wonder how the campus food is like now at CMU.

Re:Highlander

[KewlJedi]

Campus food here still sucks, I had to ditch the mealplan after freshman year. But Highlander cafe is long gone.

Re:Highlander

[KirschH20]

The pun on the cafe might be part of it, but H1ghlander is a converted H1 Hummer. H1 ... H1ghlander. Check your fonts in case you see the 1 as an I.

It was exciting out there. At the event, I was only an observer, but it turned into a real race. And everyone cheered all the bots on.

TerraMax was 12+ hours to finish. Way over the time limit, but just in time for the closing ceremonies. :-)

The www.grandchallenge.org site now has some decent videos of the finishers.

Oblig Soviet...

[fbg111]

In Soviet Amerika, cars drive you!

Imagine: apply this enthusiasm to alt energy!

[sterlingda]

Paul Noel wrote an excellent article talking about how this Grand Challenge could now spur a race to real "auto" mobiles -- vehicles that drive by themselves, similar to the Internet revolution, which DARPA also launched. He then poses the question: Just think what could happen if the next Grand Challenge were in the area of energy development technologies!

Miserable failure

[HermanAB]

For thousands of years, man used autonomous vehicles. The 20th century will stand out as a glaring anomaly, when man tried to drive vehicles by himself and failed miserably, with tens of thousands dying each year in crashes. Going back to autonomous vehicles again is an interesting regression.

Re:Sir you've got your head on the wrong way aroun

[Anonymous Coward]

Dude, just wanted to say, great post. I noticed you have been modded a 0. Unfortunately, no surprise, this being /.