Still More on the DARPA Grand Challenge 168
The SF Chronicle has an in-depth story on the DARPA Grand Challenge, with emphasis on the several teams from the San Francisco area. The three teams covered are using a pickup truck, a six-wheeled all-terrain vehicle, and a self-balancing motorcycle...
which doesn't belong? (Score:5, Funny)
a pickup truck,
a six-wheeled all-terrain vehicle,
and a self-balancing motorcycle
Re:which doesn't belong? (Score:2, Funny)
Re:which doesn't belong? (Score:2)
Re:which doesn't belong? (Score:4, Funny)
Re:which doesn't belong? (Score:2)
Re:which doesn't belong? (Score:3, Informative)
What (Score:5, Funny)
Re:What (Score:2)
(the coolest VW pictures I've seen)
One advantage of VWs is that they're very customizable.
Windows (Score:5, Funny)
Re:Windows (Score:2, Funny)
I wanna enter! (Score:5, Funny)
Re:I wanna enter! (Score:3, Funny)
Re:I wanna enter! (Score:3, Funny)
pickup truck? (Score:5, Funny)
I think it comes down to... (Score:5, Insightful)
rover (Score:5, Interesting)
From the article: "The biggest hurdle has been making vehicles see obstacles and react to them"
The mars rovers use a pair of cameras to build a 3d model when it decides its path. Put this system into a 4x4, give it a small cluster for computation, and it should work well enough to make it across the desert, I would think.
Re:rover (Score:3, Funny)
Re:rover (Score:4, Funny)
Italian looks, French engines and British electrical systems, with German price tags.
Difference between heaven and Hell (Score:2, Funny)
The Italians are the lovers
The Swiss run the hotels
The Germans are the mechanics
The British are the police
The French are the cooks.
In Hell:
The French run the hotels
The British are the cooks
The Italians are the mechanics
The Swiss are the lovers
The Germans are the police.
Re:rover (Score:5, Informative)
Re:rover (Score:2)
Re:rover (Score:3, Informative)
Re:rover (Score:5, Informative)
Re:rover (Score:5, Insightful)
Re:rover (Score:5, Interesting)
The rovers aren't even autonomous in real time. They stop, take pictures, plan the next few feet, execute blindly, then stop and open their eyes again to start the next episode. That's not what DARPA is looking for. And the system only looks ahead by a few feet. You might think it's just a matter of adding more computing horsepower, but handling all the disorienting motion from looking while moving is a whole different problem.
The DARPA contest will hopefully be won by somebody pushing the field forward, not by recycling a technology time-tested enough to go on a rover.
Math is good (Score:5, Informative)
Re:Math is good (Score:4, Insightful)
Re:Math is good (Score:2)
Slow and steady wins the race.
Re:Math is good (Score:2)
Maybe in the end, one of the slow vehicles will win, but I wouldn't bet $1,000,000 on that. I'd run my truck/bike/whatever as fast as it can go reliably.
Re:rover (Score:2, Insightful)
In this case, the teams cannot aif their creation in any way. So in Nasa's case, an engineer might say that the rover is getting to close to a rock, and the team will stear it away, whereas the people in the Darpa thing cannot do that.
Re:rover (Score:5, Funny)
Yeah, plus they have a week of meetings, planning sessions, etc. to decide whether the rock is really an obstacle worth diverting around or not.
BTM
Re:rover (Score:2)
Yeah, plus they have a week of meetings, planning sessions, etc. to decide whether the rock is really an obstacle worth diverting around or not.
You're forgetting that NASA is CMM Level 5. Add six weeks for paperwork and peer reviewing.
Re:rover (Score:2, Informative)
those rovers are travelling at max 2-inch per second, which gives the processor plenty of time to build a 3D model, analyse it and make a decision.
confusing the issue (Score:5, Informative)
Just because DARPA is collaborating with NASA, don't get your hopes up if you're thinking about some 'geekcool' super-Star-Trek-beam-me-up-scotty rocket their buddy. DARPA is strictly defense, and anything they can get to the benefit of a defense project is worth gold.
If DARPA is doing something with NASA, it will likely use this for the killing fields nothing more nothing less.Re:confusing the issue (Score:2)
True, they are doing research for the military, but this will trickle down to civilian applications, as the jet engine did, as micro-electronics did. Darpanet was the precursor to the Internet, originally designed as a redundant communications system that would survive a nuclear strike. Thats right, it was Darpa, not Al Gore, that invented the internet. I am a big fan of Darpa (except for the Total Information Awareness program). They do really cool stuff. If you haven't been
Re:confusing the issue (Score:2)
What is rover's top speed? (Score:2)
Paul B.
Picture of /.'s own Animats (Score:3, Interesting)
Re:Picture of /.'s own Animats (Score:2)
Re:Picture of /.'s own Animats (Score:5, Informative)
If I'd paid more attention to what Berkeley was doing with ACK delays, TCP would work better in that area today. Both algorithms went in around the same time, and they don't play well together.
A simple solution (Score:5, Funny)
Leave the vechicle unlocked in a bad part of Barstow with the keys, a pile of Vegas casino chips and case of booze in the car.
If no one watches the car, I predict at least 50% chance that it with disappear from Barstow and reappear in Vegas. (Or in a ditch on the way there.)
Re:A simple solution (Score:5, Funny)
KFG
Re:A simple solution (Score:4, Funny)
When does the movie come out? (Score:5, Funny)
Re:When does the movie come out? (Score:2)
Whatever Bender and Hal are driving. Though they could pull off the "Dean Martin / Sammy Davis jr." team with ease as well. Bender's an alcoholic, and Hal's only got one eye....
Related link ... (Score:4, Informative)
http://robots.mit.edu/projects/darpa/ (with videos)
CC.
Some poor vehicle platform choices (Score:5, Informative)
From the article:
DARPA won't disclose the exact route of the Grand Challenge until two hours before the race March 13; it has promised a rigorous route that will include rocks, gullies and streams.
Some of the world's best dirtbike riders wouldn't be able to easily cross stuff your average Land Rover or Land Cruiser would laugh at. I think the team with [what looks like] the 6-wheeled ATV stands the best chance, at least from a vehicle-choice perspective. Those things are amazing in terms of what they can cross- some of them even float and can ford -rivers- using the tires as paddlewheels.
Description of the pickup truck entry:Two tons of steel rolled forward and made a jerky left out of a parking lot in Morgan Hill. It gained speed and settled into a lane. It followed a curve to an intersection. It stopped. Then it turned right and continued down the road.
Probably stands a better chance(and has better fuel economy than the 6-wheeler- though a MUCH higher center of gravity), but taking a trip through suburbia hardly qualifies as suitable testing grounds for what DARPA has described...and depending on the truck, it might not stand up to the abuse. A jeep(or, a Land Cruiser, or a Land Rover) would have been a much better idea than a pickup truck, which really isn't designed for off-roading.
Even the guys who do insane things with their jeeps and whatnot come fully equipped. Air suspensions. Winches. Huge tanks of air or compressors to re-seat the giant tires(did I mention giant tires? :-)
I can also think of a lot better things to spend money on than that giant LCD display they put in the truck's passenger side; that thing has got to be what, 21"? The money would have been much better spent on the truck itself. It's all fun and games until that rock takes out your transfer case and your truck's transmission rips itself to pieces.
Re:Some poor vehicle platform choices (Score:2)
I hope they enjoy pulling the LCD display out of what's left of the truck after the desert is done sodomizing it. I'd drop a lot more cash on armor for the unde
Re:Some poor vehicle platform choices (Score:5, Informative)
So that's why the motorcycles always finish the Dakar Rally fastest? I always wondered - I've seen motocross races in which 45 year old Triumph Tiger bikes went up hills at 50 mph that a Land Rover would only cry at.
Yes - there's a big problem with stability (though it's worse at low speeds), but a program that can mimic a motorcycle trials rider is going to be able to go places that a 4wd couldn't even dream of.
Having said that, an unmanne motorcycle is going to be way short on payload capacity - something that DARPS probably care deeply about.
Face it - given the navigation problems, solving motorcycle stability as well is cool - and that has to count for a lot.
Re:Some poor vehicle platform choices (Score:2)
If the bike takes the prize, you may shortly expect to see perhaps house-sized robotic bikes with various military insignia upon them. Which is a pretty weird vision, if you ask me.
Re:Some poor vehicle platform choices (Score:5, Funny)
Now with a little stabilisation, and the Rising Sun emblazoned on the tank, I can just see hordes of kamikaze Gold Wings descending on the enemy and crushing them to death with their armchair seats, or maybe using the included stereo as an acoustic weapon...
agree w/rider skill comment (Score:2)
I'd like to see you ford a 6 foot deep riverbed, at 20mph. I'd like to see you scale a 45 degree rock face.
Point is, there are conditions suited for the various vehicles, and I don't think the darpa trail is going to be set up for motorcycles/dirt bikes. I also think finding a path is a lot easier for a truck or ATV than it is for a motorcycle; the cyclist has to worry about getting his fro
Re:agree w/rider skill comment (Score:2)
As for the stream fording, well, if it's deper than three feet, for the price of one hulking SUV, I will just buy two bikes and leave one on either side of the damned river. For Hummer H2 money, I can purchase several dual-sport bikes and modify them into continent crossing, canyon strafing, stream fording, weather i
Future scenario (Score:5, Funny)
Re:Future scenario (Score:2, Funny)
emergency plan? (Score:3, Interesting)
Re:emergency plan? (Score:5, Informative)
Each vehicle is followed by a manned one. Specifically, one of the team members and a contest official.
The team member has a "big read button" - which is a mandatory safety device - that is the vehicle is in danger of or actually goes off course can be used to shut it down.
Then you can get disqualified for it, upon the disgression of the cheif judge.
Check out the latest copy of the rules [darpa.mil]
=Smidge=
Re:emergency plan? (Score:2)
any robotics experts? (Score:5, Interesting)
Essentially, an AI problem... (Score:5, Interesting)
The difficulty with autonomous land vehicles is using sensor data to figure out what the environment is like, and using that information to plan what to do next. Both are AI problems, not hardware problems (though, certainly, clever sensor hardware and lots of computer power helps).
Re:any robotics experts? (Score:5, Interesting)
I'm not quite a robotics expert (that's 30 years down the line for me), but I do have a mechanical engineering degree, a lot of robotics experience, and I am involved on a team. One that was a DGC hopeful, but also one involved in the IRRF Open Challenge race this next September. (see my homepage.)
The people involved (such as myself) put in an enourmous amount of time, money and effort into our robots. The components are top of the line, and generally far beyond what we can normally afford. We work mainly from equipment and cash donations, but make up the rest ourselves.
A lot of the difficultly is directly related to funding. This is pioneering work, and it's very hard to establish a reputation and solicit sponsorship when a lot of your work is still on the drawing board. A lot of other teams involved have resorted to the cheapest components, and quickest solutions. Some of these work, other do not. As these races become a regular occurance, things will definitely change.
what will sink this (Score:1, Insightful)
Re:what will sink this (Score:1)
Re:what will sink this (Score:5, Insightful)
For that matter, I read recently about a study done by a couple of psychologists in which they described to schoolchildren about accidents in which seatbelts saved lives, and then about ones in which they caused injuries. The children, after hearing about the first, said, ``oh, then you should wear your seatbelt always.'' After hearing about the latter, they said the opposite. When asked repeatedly by the researcher, ``so, when should you wear it and when shouldn't you?'', one subject replied, ``well, I guess you should wear the seatbelt half the time.''
People aren't rational; one theory is that we interpret probabilities by ``representativeness'', a heuristic in which the situation being judged is compared to a similar situation thought to be probable or frequently heard of. So the more people hear about robotic-automobile-caused deaths (which would certainly be more publicised than the same old same old), they'd assume such vehicles are less-safe than traditional cars.
Many people judge the risk of very rare, unlikely deaths (from rare diseases, freak accidents, and the like) to be far higher than they are, while they judge the risk of death from things like car accidents and other more normal causes to be significantly lower than it really is. This is because they hear about far more of the freak accident deaths--precisely because they are freak accidents--than the ordinary, normal deaths.
Of course, just as with airbags, after the breaking-in period, I think people would probably get used to it. And the economic demand, if great enough, would be enough incentive to let them on the road.
In other news (Score:5, Interesting)
Automobiles should be restricted to 4 mph, and preceded by a man carrying a red flag (an presumably singing the Internationale for good measure).
Machines such as the Spinning Jenny will destroy our way of life.
I salute you, Ned Ludd, for your foresight and insight into the human condition.
another contest (Score:5, Funny)
Re:another contest (Score:4, Insightful)
It's called Tread Lightly. Not everyone who enjoys off-road activity trashes the environment, dude. The responsible ones travel well-known trails, and we pack out what we pack in.
Re:another contest (Score:3, Insightful)
If you *really* want to do something, go after the hordes of people driving SUVs and not carpooling. The air pollution emitted by these does a lot more damage than some faint tire tracks.
"Tractors would harvest crops on their own." (Score:3, Informative)
self balancing moto... (Score:1, Insightful)
No human assistance? (Score:4, Funny)
Of course the simple solution would be to give a monkey a quad bike. But don't give him a full-blown road vehicle, or he will turn it into a V8 intercepter and conquer the post-apocolyptic wasteland...
Re:No human assistance? (Score:4, Informative)
Re:No human assistance? (Score:3, Funny)
Re:No human assistance? (Score:4, Funny)
One word: zombies!
bat country... (Score:4, Funny)
Sweet Jesus! That's bat country. I suppose the poor bastards will figure that out soon enough.
? [imdb.com]
short on details (Score:3, Insightful)
What about driving down a suburban street? (Score:3, Interesting)
How does i know which side of the road to drive on?
How do you tell it that half of it's obstacle-free passage is actually not allowed to be driven on because that's for traffic going in the other direction ?
The view from Team Overbot (Score:5, Informative)
Sadly, we (Team Overbot) aren't going to be ready in time. We lost five members in January. Two got better jobs, and two were Stanford students who needed to get their grades back up. This left us with too few people to finish in time. We have all the hardware, and most of the software, Most of it is working, but it hasn't been integrated and tested. We'll finish the vehicle, and we'll have some public demos at some point, even if we're not at the Grand Challenge.
It's up to DARPA whether anyone wins this year. They're going to provide 5000 GPS waypoints, and if you can drive the route described by connecting the dots, somebody will probably win. If the vehicle has to find its own gully crossing, it's unlikely that anyone will win, unless somebody figured out, by hand, in advance, where the crossing is. It's all up to DARPA. As one of the DARPA people put it, "This is turning into a breadcrumb following exercise". If somebody wins by connecting the dots, this whole thing was a waste of time.
Several teams are using aerial photographs and manual planning. The general route leaked weeks ago, and it's since been oveflown by Airborne 1 in San Diego. High-resolution photos and depth maps from LIDAR scans have been obtained. Still, you won't see a fence in those depth maps. The emphasis on preplanning surprised us. The whole point of the Grand Challenge was originally that preplanning was made impossible by the large area to be covered and the release of the waypoints only two hours before the race. That all changed when the route leaked.
Nobody seems to be deploying anything new in the sensor area. Everybody with a laser rangefinder that we know of is using an off-the-shelf line scanner. Nobody has a true 3D scanner, although several teams have line scanners on tilt heads. It's quite possible to build a true 3D LIDAR depth measurement system. But it's hard to make money doing it, as the five companies that exited the field learned the hard way.
We hear talk of new vision algorithms, but no details yet. Stereo vision doesn't work well on dirt or sand; there aren't enough edges for the stereo algorithms to register the images properly. Optical flow doesn't work well for the same reason. If somebody can do good stereo from motion in this demanding environment, that will be an achievement.
Still, the Grand Challenge has done quite a bit to get autonomous vehicle work moving again. Just getting CMU off the dime (DARPA's real intent, we hear) was worth the whole effort.
If DARPA does this every year for the next decade, with a tougher course every time somebody wins, we will have battlefield robotics that works within ten years.
Re:The view from Team Overbot (Score:2)
They realize that the gov't doesn't have to keep coming to the established contractors or research universities to get the same things done.
But I agree that the leaked route changes the key approach to the concept: responding quickly to a new task without the opportunity for a great amount
Turing Test 2004 (Score:2, Funny)
Behind The Scene of Our GC Team (Score:5, Interesting)
Re:Behind The Scene of Our GC Team (Score:4, Interesting)
DARPA doesn't want a winner. They want to make sure that the REAL promising technologies lose, but can be copied by the defense conglomerates that they're going to award all the contracts to, anyways.
Don't be a sloppy programmer for these (Score:2, Funny)
Red Team will take the Million (Score:3, Interesting)
Work and Fun Graduation [cmu.edu]
Televised? (Score:3, Interesting)
Re:FP (Score:2, Funny)
Re:FP (Score:3, Interesting)
(Hmm, "userless modding" maybe?)
Ahh well. As for the driverless car/truck/bike - this sounds quite cool, what makes this harder than pilotless planes? (We already have those, the drone things... I am missing something?)
Re:FP (Score:1, Informative)
Re:FP (Score:3, Interesting)
Anyway, is navigating a desert so hard? You can use GPS to plot position, and if you're on the ground you can't hit it! There aren't any significant drops that can't be detected by satalite are there? (I know the dunes move, but a significantly large rover isn't going to have a problem there is it?)
Sure you the device was to be deployed in a non-desert setting things would be harder.
Re:judgement can't be avoided (Score:2)
Re:DARPA's usage of this technology (Score:2, Insightful)
Anyway, sure accidents happen, but the sole purpose of these machines aren't to kill civilians. So you have a picture of a dismembered child, do you have any story saying "The army tested it's new X10 remote planes today by blowing the limbs off of small children"? Maybe the US army didn't even do that (well they might have, I mean it's not like it never happens) it's just some random picture with nothing describing what happened. When civilians are ki
Re:DARPA's usage of this technology (Score:4, Interesting)
Look at the statistics from Iraq. They basically had no army worth fighting. They were crippled by 10 years of UN sactions. They were a few small steps away from being armed with rocks and sling-shots.
The US army was far superior technologically. But 10,000 civilians died, and millions more are going to die because of Depleted Uranium [bushflash.com] poisoning.
Pumping yet more money into the US military will certainly not save any lives.
Re:DARPA's usage of this technology (Score:3, Insightful)
> rocks and sling-shots.
First time I hear a T72 being described as a rock. And yes, these did see action, in case you missed it (if with little success, except against the Bradleys).
> But 10,000 civilians died
For comparison's sake, what are the civilian death figures for other hostile takeovers of countries with a population of about 20 million (say the non-Vichy part of France in World War II)?
> millions more are going to die because of
> Dep
read the bbc (Score:3, Interesting)
Re:DARPA's usage of this technology (Score:2, Interesting)
This page [fas.org] by the Federation of American Scientists [fas.org] has a nice summary of depleted uranium related research. After taking a look through the links, it seems that several studies have been undertaken into the toxicity of DU and it's affects on veterans.
This page [http] looks particularly in
Re:DARPA's usage of this technology (Score:3, Insightful)
You can't excuse yourself from killing 10,000 people by pointing to another point in history where you killed 2,000,000 people. Instead of getting away with the 10,000, you are in fact now being held responsible for both .
Re:DARPA's usage of this technology (Score:2)
Re:DARPA's usage of this technology (Score:2)
No, they were crippled by Saddam diverting the funds from the UN's "Oil for food" programs to build up his own affluent palaces.
But 10,000 civilians died
Guess what, hippie! That's what happens when you have a psychopathic dictator embedding military targets within heavily populated civilian centers. It's a tactic used to stir up outcry when the death toll starts rolling in, and you bought it; hook, line, and sinker. It doesn't matter how "smart" your weapo
Re:DARPA's usage of this technology (Score:4, Insightful)
I see a picture of a child missing a limb. Though emotionally charged, there's very little useful information.
The parent poster may be making an honest claim, and he may not. I note it was posted by an Anonymous Coward, which doesn't help. Could have been an unmanned vehicle that did it. Could have been a landmine, too. Might have been a US vehicle, might have been Chinese. Was this a grisly industrial accident? Horrifying though the thought may be--was the child armed?
Context, please? It seems to be an awfully tenuous link to autonomous vehicles...
All we have here is a picture that suggests that military conflicts are bloody, grisly, destructive things, with wretched consequences. Well, duh. We knew that.
Thought experiment: Can the use of unmanned vehicles reduce this type of civilian casualty? Expendible vehicles might be less likely to be used to shoot innocent civilians, because they're not going to be frightened, or have an itchy trigger finger. Just a thought.
One possible alternate perspective: this sort of technology will further the perspective that war is a sort of video game--one that can be entered into more readily if there are no (ahem) friendly lives at risk. Just a thought.
Re:DARPA's usage of this technology (Score:2)