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.
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)
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.
Basicly, it took a turn too fast.
a picture.
this page is the running log put out by the group, and includes a description of the accident.
WRCT Pittsburgh, 88.3FM
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.
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.
Look here.
The University of Louisiana team is updating their journal regularly.
www.cajunbot.com
www.cajunbotjournal.com
Emperor Skull
This is no different from you getting in your car, looking at a map to find out the best route to get from point A to point B and memorizing what turns you have to take at certain key points. But the map doesn't show every little bend in the road, every little obstacle, elevation changes, etc. You have to do all that while you're driving the roads. The autonomous vehicle has to do the same things. You don't think that's impressive?
The point of the competition is not to come up with a route. It's to simulate a battlefiled scenario where the commander gives his troops the location of the enemy two hours to plan how their going to get there and kill the enemy.
The vehicle will still have to do some midcourse corrections to stay on track, but the overall course will already be programmed into it.
+1 Insightful, -1 Troll. What can I say, I'm an Insightful Troll.
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 can look at the latest pictures, the teams' relative positions, and status charts.
http://www.grandchallenge.org/
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.
Here are some photos:
DARPA Grand Challenge Photos
Enjoy!