Slashdot Mirror
CMU First To Qualify For DARPA Grand Challenge
Anonymous Coward writes "As of 18:00 March 9th, Carnegie Mellon's Red Team is the only entry to successfully complete DARPA's Grand Challenge Qualification Inspection and Demonstration (QID) before the main event on March 13th. The NY Times has this article detailing this first step towards winning the Grand Challenge."
No reg needed!
Join the Free Software Foundation
One of the other competitors is from my university. Looking at the relative sizes, I hope the hummer in the article doesn't get in TerraMax's way.
Prospective station wagon buyer: "I know what you say is true...but...er...I don't know how to maintain a tank!"
I can't be the only one who questions motives when the $1M prize is being sought after by a team with more than $2M already invested. What is the eventual payoff?
Linux: Free if your time is worthless.
The real prizes:
the knowledge gained throughout the project
getting one's name published for taking an active role in the project (which can lead to further opportunities)
the overall experience, i.e. 'Hey, I did that"
The pursuit of intellectual challenge is not about money...
I want to drag this out as long as possible. Bring me my protractor.
they divided your time by the cost of your machine.
its impressive when you build a mega$ robot, but a minimal robot that manages to finish is way cooler
TAIWWP :(
Does anyone know of anywhere hosting pictures of these unmanned robot vehicles?
... doesn't this basically lead directly to the US military dropping off Robo-Tanks in foreign countries as they please? We know that a steady diet of wars figure heavily in the plan for the forseeable future. The Robo-Tank cuts down on friendly casualties, thus making conflicts more palatable to the public.
Now I find this as cool as anyone else, from a technological standpoint. And it definitely has civilian applicability. But let's face it, this contest isn't about finding cheaper ways to haul cargo or reach remote locations.
I would sure hate to be a geologist, prospector, or hermit in the desert that day.
Gelogist: [mumbling to himself] Finally! Proof that the formation of this arroyo was caused by--
[Geologist is flattened by an army of driverless cars driving at upwards of 60 mph, one of which detects the collision too late and actually backs up, running over him again, as failing avoidance mechanisms kick in]
Any generalization is a stupid one.
Seeing as DARPA wants to turn this technology into a military robotic transport, I don't know how valuable it's going to be if it has to be pre-programmed with terabytes of data just to move. What about if they invade somewhere they don't have good maps of? Somewhere with a dynamic landscape (desert, rocks etc)?
I'm all for innovation, but exploiting poorly-worded rules just to win for winning's sake is an empty victory at best.
The whole point behind an SUV is that, under current regulations, it's classified as a light truck, and so doesn't have some of the environmental restrictions that come with sedans, etc.
tasks(723) drafts(105) languages(484) examples(29106)
Pretty well, except for the speed thing, and the distance covered. From what they say, an average speed of 25 miles per hour will be needed to even complete the course in time. The rovers can presumably plod along and if it gets stuck it stops and asks for human intervention. The rules of the competition designate that no communication is allowed. From a piece that I read somewhere like New Scientist, it seems that with 4 Itaniums and 4 Xeons they're still not computing obstacle avoidance fast enough. For the qualification the team ran the vehicle at a walking paced 5 miles an hour. There's gonna be a lot more work needed until they can manage to finish in time.
The Qualification Inspection and Demonstration was rumored to be the state's Driver's License Test.
The vehicles had been fretting about the dreaded parallel parking portion of the test.
They're not all that functional either - unless a mountain should suddenly spring up on the way to the kids' soccer practice. Obviously a few people have a need for those sorts of vehicles, but I question the volume of them I see on the road.
Ita erat quando hic adveni.
Nice to know 3 million dollars buys you a roll over and placement. What the hell did they do to the HUMVEE that made it roll over? I know HUMVEEs and HUMMERS, they don't roll easily.
Actually it DARPA specifically required that no government agency help allowed. (though universities are quasi government, but you now..) Anyways I heard that the university that developed software that went on the mars rover also has a different team that worked on this project, but wasn't allowed to use the software. Though it probably wouldn't have worked as the rover goes real slow and spends a lot of time analysising the environment to get the safest path. This project will require real time calculations that picks the best route given the time, but not nessesarly the perfect route.
All competitors are given the actual route as a series of GPS waypoints a few hours prior to the race. Red Team is going to send those waypoints back to CMU, have the big iron there figure out the best course based on all the map data, and then download that course to the robot prior to the start. In a way this is cool, but it seems like they are using a loophole. A much more interesting problem would be to navigate a course that you know nothing about other than the waypoints.
The other teams are using techniques that require more onboard intelligence and route finding. The most interesting vehicle is from Cal. They have a motorcycle. Even though I went to Stanford I am rooting for the Cal motorcycle to do well since they have the most unique vehicle. Hopefully the team of Stanford alums (already dropped out) can come back next year and beat them.
Lasers Controlled Games!
Weird title, seeing how they showcase the CMU entry, a high-school entry running in an Acura (donated by a parent who works for Honda) and a single-member "team" trying to do a motorcycle entry.
Here's a size comparison from the Oshkosk website... their truck is 9 feet tall, a hummer is 6 feet.
HIV Crosses Species Barrier... into Muppets
That's another thing - they only look the part - if a mountain popped up you'd have more chance getting over it by foot than a humvee. They use Tacoma or Silverado chassis and engines, with a much larger body shell (resulting in the insanely low mpg and silly look). Range Rovers are the complete opposite, however. Efficient and excellent offroaders. Why won't people learn? :-P
I feel kinda priveleged to be part of this. DARPA is working with SCORE International Off-Road Racing (http://www.score-international.com) to do the "checkpoints" and road crossings for this event, of which I am a part of.
Basically it means sitting around all day waiting for these things to show up, but it will be fun nonetheless.
I have a feeling that this event will not have a finisher, but from what I have heard DARPA plans on carrying out this challenge for about five years anyway.
I'm somewhat surprised that so many young people would work on a project that will help our military develop unmanned hunter-killer vehicles. Isn't this why DARPA's funding this project? I'm not against the project, just curious if there are any conscience issues involved here.
Speaking of automatic tanks, did any of the teams name their entry Ogre?
with this is simply how cheap the US military is getting away with this. Instead of setting forth a proposal, taking bids, working in tandem with one of the big development houses, they offer up a rediculously small prize. If they had gone through someone like Lockheed Martin, they project would have easily cost them into the 100 million dollar range. Oh well. Hopefully the military will get what they paid for.
Yup, those are some pretty cool prizes. But we gotta remember other prizes, like bragging rights. I'm already sending this article all over to my fellow CMU almuni friends, to other non-geek friends, etc. All this, and I have nothing to do with robotics and graduated almost ten years ago. Woohoo! I love bragging rights...
"He uses statistics as a drunken man uses lampposts...for support rather than illumination." - Andrew Lang
It's all about CAFE. Dodge's PT Cruiser is listed as a light truck too -- it's got a flat-load floor between the rear wheels. Dodge puts a four cylinder in the PT, which gets 30 MPG. This allows them to make even more fuel-hungry trucks and SUVs because their combined average is offset by the relatively high efficiency PT.
From http://www.darpa.mil/grandchallenge/media_feeds.ht m
On Saturday, March 13, DARPA will provide same-day coverage via satellite of the Grand Challenge start and highlights at the following times:
Live coverage of the start: 6:30 - 8:30 Pacific/9:30 - 11:30 a.m. Eastern
Video news release: 11:00 - 11:30 a.m. Pacific/2:00 - 2:30 p.m. Eastern
Coordinates for both feeds:
Satellite: AMC 9, Ku, Transponder 03
Space is: 36 MHz
Downlink Frequency: 11760.000
Downlink Polarity: Vertical
Hopefully someone will record these feeds and make them available online for all of us without satellite
Rapidly approaching the Zener knee...
That's another thing - they only look the part - if a mountain popped up you'd have more chance getting over it by foot than a humvee. They use Tacoma or Silverado chassis and engines
Whoa. Only half true.
The original Hummer/Humvee (Hummer is the civilian version, HMMWV is the military) is a serious off-road vehicle and far surpasses most SUVs and other off-road vehicles in capabilities. It also costs around $125k (civilian version). It'll keep going long after that Range Rover gets stuck or busts its oil casing.
The H2, aka Hummer2, however, is another story entirely. It is, as you say, merely a Tacoma with a different body shell. The original Tacoma wasn't particularly off-road capable and the reshelled version is even less so. But it's only about $60k.
IMO, neither the original nor the bastardized step-son is particularly well suited for general civilian use. But that's me.
Attendance was about the same today except it didn't appear that there was as many media representatives present. Again temperatures were in the 90's. I acquired a media pass today and was allowed access to almost every area of the speedway including the pits and the start line. This will allow me to film each entry up close and interview members of the teams. DARPA is also publishing the daily events here and here.
Vehicle inspections on the rest of the field were performed today. DARPA is reacting as fast as they can to modify the rules and give every opportunity to each of the teams in hopes they will be able to qualify. DARPA is now allowing the teams as many appearances on the Q&D course as requested by the teams. The Q&D that was scheduled today became an opportunity for teams to iron out their problems on the track.
The Blue team with the CyberRider (the motorcycle entry Web Site) was the first on the Q&D course. It traveled about 20 feet when it fell over and exposed it's greasy side.
Team ENSCO Web Site traveled to the first major turn and failed to navigate the first sharp turn. This is also the same place Team TerraMax web site failed today and the Sci Autonics web site team.
The first turn appears to be difficult for the vehicles that make it there.
The ASI/Florida State Web Site had two more runs today. They disabled all of the perception systems and successfully ran about 1/3 of the course. The first run, the vehicle was driving like a "drunk sailor" according to a member of the team. Florida State took the recoded path data to tune their vehicle controller. ASI reported the vehicle tracked much better on the second run. I get the impression that a few more Q&D course test runs will be performed before the vehicle is ready to qualify.
Team Caltech Web Site made two more runs on the Q&D course. Well, both runs were consistent, but not as good as yesterday. Both times, cleared the start line and banked hard left as if it were going to the last way point. I hope to find out today what happened.
There were several other teams that attempted the Q&D course today with similar or worse results.
The highlight of the day was CMU's Red Team web site. As anticipated they made it to the finish line of the course and electrified the spectators and increased pressure to the rest of the field.
That's the highlights of the second day of Q&D testing.
You might be interested in knowing that, according to AW&ST, the army/air force in Iraq has found in many cases that it is more efficient to transport cargo within Iraq via C-5, instead of 12 large trucks.
The reason was because the loading and unloading areas could be secured but not the highways in between.
Check out the February 23rd Issue.
myke
Mimetics Inc. Twitter
I suppose that the Internet (former DARPANet) is some insidious hunter killer commmunications device?
The point of the Darpa project is to advance technology for driverless military vehicles, primarily for convoy work. To my mind, creating a computer system to quickly plan out routes based on intelligence is an important part of a practical solution.
Not only does it more accurately reflect the technology's intended use-case in the military field (convoy operators would lilely be given a general route a couple hours before a mission, instead of simply told, 'get it to this point and leave right now') but it also means that more of the technology is outside the vehicle.
A cost-effective solution would need to have as cheap a vehicle as possible. While a fully autonomous system might be nice for a science fiction 'technology run amok' film, in reality it's more effective to have sparse mobile systems with an ops center capable of planning routes for several vehicles.
It also costs less when one goes 'wheels up' or is captured by the enemy.
Kevin Fox
I could have saved them $250,000 in sensors by installing a $100 roll bar!
The only thing that is yours, is your soul; everything else is borrowed.
I went by the event yesterday as a spectator and got to see Red Team do their run. Of the 23 teams who made it this far, they're the only one that has completed the qualification course so far. People complain that they have a more accurate map and that they're not doing real AI, but based on their performance on this surprise course, they have a real obstacle avoidance system.
In one section there was a minivan parked in the center of the GPS path. Of the eight vehicles I saw run, only three made it past the car. Three hit it, and the rest failed before making it that far.
It seemed that the biggest problems teams had were getting GPS right. Several drifted off course or turned the wrong way, going off course. One got the next GPS coord inside of its turning radius so it kept circling a spot until they turned it off.
Lots of great designs though, and some really impressive engineering.
Caltech manages JPL, the NASA lab that developed the rovers and their associated software.
Originally, the Caltec team was using rover software. However, when DARPA changed contest rules a couple months ago, it went back on its earlier ruling and said that Caltech was no longer allowed to use the rover software because that software was not commercially available.
This led to Caltech redoing much of the work on their vision software. They are now using the modified version of a commercial vision package.
I personally think that DARPA could have done better by asking JPL to make the software available to ALL teams instead of taking it away from Caltech.
You can look at the latest pictures, the teams' relative positions, and status charts.
http://www.grandchallenge.org/
I dno't konw whcih stroy you are tnalikg aubot, but as lnog as you lavee the fsirt and lsat ltertes anole it wrkos qitue wlel.
Be faithful to your obsessions. Identify them and be faithful to them, let them guide you like a sleepwalker. JG Ballard
Is it too late for me to enter my Roomba?
Towards the end of this year, PCI-Express and next generation graphics cards using them will come to market.
How is this significant for the DARPA race?
Well, newer generation graphics cards with highly programmable graphics pipelines can act as very powerful SIMD processors. Up until now, their capability has not seen much use outside of graphics because the AGP bus allows data to travel at full bandwidth in only one direction at a time. This meant that every time you need to download data from the video card, you had to flush the AGP bus, loosing or delaying the uploaded data.
With PCI-Express, data could travel both ways concurrently at full bandwidth, so there's the potential for using the graphics card as a specialized SIMD processor.
I bet much of the processing for the vision and obstacle avoidance could be done on a GPU. If that's the case, instead of having a 1.5 gigaflops CPU per pc, you could have 10 or 20 gigaflops (IIRC) of processing power at your disposal for little over $1000, thus making the necessary computing hardware much cheaper.
Currently, the CMU team, for example, has multi-itanium servers aboard their Hummer, which is NOT something doable on a shoe string budget.
Man, these teams are using the wrong military vehicles. Humvees? Supply trucks? What the hell is that? Seriously man, strap a GPS system onto an M1 Abrams and open that baby up.
I say screw collision avoidance. Go for collision dominance. Any obstacle capable of stopping a 65 ton tank travelling at 45mph is gonna show up on the mother f**king map.
Here are some photos:
DARPA Grand Challenge Photos
Enjoy!
I will pay $100 for the name and address of the person responsible for that posting.
John Nagle
nagle@overbot.com