Slashdot Mirror
Grand Challenge 1, Competitors 0
Ivan writes "According to the DARPA Grand Challenge Status Board, 2 bots were withdrawn before the race started and the remaining 13 were all disabled. Red Team and SciAutonics II tied at 7 miles, a bit short of the 142 miles required." CNN has coverage and interviews.
There were engineered obstacles, such as barbed wire and the like. And the deserts out here are not like the Sahara. They have washes and rock formations and various natural obstacles. Finally, a lot of the problems were mechanical or technical-brakes locking up and such. So it isn't as simple as it sounds.
If my answers frighten you, stop asking scary questions.
Hate to break it to you but the desert is far from a "completely barren plan, with very few obstacles".
Even with a previously traveled path and prepared track it's not uncommon for VERY well financed race teams to fail to finish in a desert race. Most desert racers consider it a win just to make it to the finish line and that's with a driver!
Look into the SCORE side of this challenge a bit more and you'll find a LOT of info about just how challenging desert racing is with drivers - let alone trying to do it autonomously.
--- Juggle juggle@hitesman.com
Your assumption that they're crossing a barren plain is incorrect. The Mojave desert is not an easy place to drive. Quite the contrary; it's an area that dedicated off-roaders love because of the challenge of driving there. DARPA chose a test that they expected none of the entrants to be able to beat; my impression is that even making it 7 miles is an enormous accomplishment.
There's no point in questioning authority if you aren't going to listen to the answers.
The course was laid out to the competitors jsut before the race began. There was no time for anyone to make a dry run. Although I don't think there was anything to stop them from picking any spot in the Mojave and playing around with the machines.
If my answers frighten you, stop asking scary questions.
I meant, had to have the ability to be disabled by DARPA. Doh.
The first tanks could only go a thousand yards before breaking down, and they had a 7 man crew.
it didn't take long for things to change.
In 1994, the NAVLAB project at CMU made a vehical that drove itself on freeways at 55 mph across the country. The same vehical has been capable of driving in traffic for about 6 or 7 years as well (at least in Pittsburgh traffic). So that part is already accomplished. So at least the CMU teams are at this level. But the limiting factor on a course like this is building a machine that is more reliable because the number of working parts in one of these cars is very large which means that a lot can go wrong. Seven miles though the desert proves a lot of vision systems are almost ready, but better handling of gyroscope info and the tire sensor information (what a human driver would call "feel of the road") is needed to handle a route of this length and difficulty.
The Washington Post has a good set of pix and video (Flash involved). FWIW, I was figuring that the Red Team's Humvee might make it. What did they do, forget to check the oil? Or perhaps the software went bonkers and left the engine at or over redline with no load?
db
Cig:
ôô
Sure,
Having actually driven and ridden extensively in that exact area for two joyous weeks of my life, I can tell you the terrain is abolutely miserable - even with two humans in a very capable HMMWV, with a map, GPS, night vision, etc, it's a bitch to get around in that area, especially off the beaten path. 7 miles is a pretty darn good showing, in my opinion.
http://dgc.gi.alaska.edu/Overview_2_1_04.htm Section 2.4.1
Don't mod this cut-n-paste troll up anymore.
...
At least against an opponent that can defend himself.
Cruise missiles cost millions per shot. Smart bombs 100,000s. Drones millions.
And a though with a 250$ ak74, and 50$ worth of c4 can do as much damage. Without radar warning.
Trying a full scale high-tech war would ruin any country.
HI O WISE PRINCE. WHT TOOK U SO DAM LONG?
(In fact, the Great Egg Race was probably as tough on school kids as this race was on the engineers who competed... with the difference that the kids usually succeeded.)
The micromouse championship was also notoriously tough... and yet many succeeded there, with finishing times of under a minute to navigate a maze of unknown complexity.
These kinds of contests are generally tough because they stretch the minds. Minds don't stretch easily, without practice.
I would have thought that a good mech eng geek could have reached double or triple-digit distances without killing themselves. The problem is the culture.
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
"I wouldn't make such an analogy anywhere other than slashdot, but I could feel that the load average on my brain was as high as it could be." Such an analogy is actually perfectly appropriate. Cognitive load is a term used by human factors psychologists to describe what you're talking about. As a driving researcher I have a suspicion it's going to be a while before a machine can match a human in handling the cognitive load for a task like driving - particularly in a wartime situation.
Team DAD's vehicle was held in DARPA-controlled pause for two hours, a mile behind CMU's failed vehicle. After the long pause, it was disabled. What's the story there?
You shouldn't discount the value of peripheral vision.
Currently I'm working on a vision system that hopes to tackle the localization & mapping problem in real time, which is basically the system you are describing before the legs/balance portion.
Using a fish-eye lens (like our own), there is a problem of non-constant resolution. The pixels in the edge represent a larger world area than the center. Precise localization of features there is hard, but optical flow helps.
Basically, you see the ground moving under your feet and react to it, though you might not be aware of it.
Regardless of what you thought you were doing, don't make computer vision researchers' problems for granted: unlike our cognitive capabilities that rely of reason and judgment, vision is a black box. We have very little understanding for what humans do to solve this problem.
I personally think that recognition and vision will need to be used to solve the Grand Challenge. This is how humans do it after all.
Robo-Blogs of the world: UNITE!
Sharing doesn't create innovation, competition does. If everyone shares, every does the same thing and no innovation is produced.
it was called an engine failure when the Red Team hit an obstacle. the cause of a mechanical failure isn't always benign.
Robo-Blogs of the world: UNITE!
I was lucky enough to have a press pass. We had to get to Barstow at 5:00am (driving up from LA) which was rough. Driving in the dark along the highway leading to the start, we topped a rise and in the valley below portable lights had been strung up creating an oasis of light. As we got closer we could see the satelite uplink trucks, grandstands, police, and military.
After registering and getting our fancy orange safety vests, we went to the starting line and were able to get some great pictures as the bots prepared to start the race. Red Team (from Carnegie Mellon) had the best qualifying time so they were first out of the gates. Their 3 million dollar hummer started off fast and was quickly out of sight. The four helicopters filming from the air were flying dangerously close to each other trying to get a good shot so it was easy to track where the vehicle was.
SciAutonics II was the next bot out of the gate, the also had a good start and proceeded out of view. About this time we heard the good news, Team Red was seven miles down the course. Soon after we got the bad news, Red Team's vehicle had died. The odds on favorite was eliminated by a mechanical failure after only 7 miles.
Several of the rest of the bots failed to get past the first turn, and the rest either withdrew or failed within a few miles. The six wheeled ENSCO lost control, ran up the embankment, and overturned. Of the 100+ teams who built bots, 25 were invited to qualify, 15 of those were allowed to race, and only 7 of those made it more than a mile.
All in all it was an excellent experience. My suggestions for next year (or for the openchallenge, etc) would be to do the race in segments like the WRC does. Divide the 200 mile race into 10 mile segments, teams get points based on their performance for the stage. If you fail a stage you're not eliminated, you just fall in the rankings. Teams are allowed an hour of maintenance between stages to fix any problems they think they can fix. This would make it both a lot more interesting, and a lot more satisfying.
Here's a very good
Read the DARPA rules. Wheels must be the primary motion mechanism for this contest.
From http://www.grandchallenge.org/gallery/Day6.html
.5 miles, the vehicle was disabled.
Preliminary Data from DARPA Grand Challenge
As of 11:00 a.m. PST, March 13, 2004
Vehicle 22 - Red Team - At mile 7.4. Vehicle went off course, got caught on an obstacle and rubber on the front wheels caught fire, which was quickly extinguished. Vehicle has been disabled.
Vehicle 21- SciAutonicsII - At mile 6.7. Vehicle went into an embankment and became stuck. Vehicle has been disabled, and the team is recovering it.
Vehicle 5 - Team Caltech - At mile 1.3. Vehicle went through a fence, and couldn't come back through. Vehicle has been disabled, and the team is recovering it.
Vehicle 7 - Digital Auto Drive - At mile 6.0. Vehicle was paused to allow a wrecker to get through, and, upon restarting, sensors were not able to determine the proper route. After sensors tried unsuccessfully for three hours, vehicle was disabled.
Vehicle 25 - Virginia Tech - Vehicle brakes locked up in the start area. Vehicle has been removed from the course.
Vehicle 23 - Axion Racing - Vehicle circled the wrong way in the start area. Vehicle has been removed from the course.
Vehicle 2 - Team CajunBot - Vehicle brushed a wall on its way out of the chute. Vehicle has been removed from the course.
Vehicle 13 - Team ENSCO - Vehicle flipped in the start area, experienced a fuel leak, and the team needed to shut off the fuel. Vehicle has been removed from the course.
Vehicle 4 - Team CIMAR - At mile 0.45. Vehicle ran into some wire and got totally wrapped up in it. Vehicle has been disabled.
Vehicle 10 - Palos Verdes High School Road Warriors - Vehicle has been removed from the course - it hit a wall in the start area.
Vehicle 17 - SciAutonics I - At mile 0.75. Vehicle went off the route. After sensors tried unsuccessfully for 90 minutes to reacquire the route, without any movement, vehicle was disabled.
Vehicle 20 - Team TerraMax - Got to mile 1.2. Vehicle then started backing up and after
Vehicle 15 - Team TerraHawk - Withdrew prior to start.
Vehicle 9 - The Golem Group - At mile 5.2. Vehicle stopped. Vehicle had a throttle problem while going up a hill. After trying for 50 minutes, the vehicle was disabled.
Vehicle 16 - The Blue Team - Withdrew prior to start.
The preliminary results have been posted on the day 6 media gallery. Since it is a word document I'l post it in full.
.5 miles, the vehicle was disabled.
Preliminary Data from DARPA Grand Challenge
As of 11:00 a.m. PST, March 13, 2004
Vehicle 22 - Red Team - At mile 7.4. Vehicle went off course, got caught on an obstacle and rubber on the front wheels caught fire, which was quickly extinguished. Vehicle has been disabled.
Vehicle 21- SciAutonicsII - At mile 6.7. Vehicle went into an embankment and became stuck. Vehicle has been disabled, and the team is recovering it.
Vehicle 5 - Team Caltech - At mile 1.3. Vehicle went through a fence, and couldn't come back through. Vehicle has been disabled, and the team is recovering it.
Vehicle 7 - Digital Auto Drive - At mile 6.0. Vehicle was paused to allow a wrecker to get through, and, upon restarting, sensors were not able to determine the proper route. After sensors tried unsuccessfully for three hours, vehicle was disabled.
Vehicle 25 - Virginia Tech - Vehicle brakes locked up in the start area. Vehicle has been removed from the course.
Vehicle 23 - Axion Racing - Vehicle circled the wrong way in the start area. Vehicle has been removed from the course.
Vehicle 2 - Team CajunBot - Vehicle brushed a wall on its way out of the chute. Vehicle has been removed from the course.
Vehicle 13 - Team ENSCO - Vehicle flipped in the start area, experienced a fuel leak, and the team needed to shut off the fuel. Vehicle has been removed from the course.
Vehicle 4 - Team CIMAR - At mile 0.45. Vehicle ran into some wire and got totally wrapped up in it. Vehicle has been disabled.
Vehicle 10 - Palos Verdes High School Road Warriors - Vehicle has been removed from the course - it hit a wall in the start area.
Vehicle 17 - SciAutonics I - At mile 0.75. Vehicle went off the route. After sensors tried unsuccessfully for 90 minutes to reacquire the route, without any movement, vehicle was disabled.
Vehicle 20 - Team TerraMax - Got to mile 1.2. Vehicle then started backing up and after
Vehicle 15 - Team TerraHawk - Withdrew prior to start.
Vehicle 9 - The Golem Group - At mile 5.2. Vehicle stopped. Vehicle had a throttle problem while going up a hill. After trying for 50 minutes, the vehicle was disabled.
Vehicle 16 - The Blue Team - Withdrew prior to start.
Just back in the door from watching this fantastic event. I was at the start and then at Daggett - but no-one made it that far. Although it was, in fairness, highly amusing when three vehicles in a row came out of the starting gates and plowed directly into the opposite wall without hesitating, overall these were amazing machines, and the fact that they even drove ten feet alone was a brilliant feat by itself.
But one with the mean-spirited fun-poking. I think the best moments (that we could see) were clearly the nice clean Palos Verde Acura hurtling into the wall wthout hesitation, the mostly-reversing although tremendsouly impressive TerraMax from Ohio State (well done chaps for frightening the rest of the pack), and the erratic go-stop-go-stop freakout from the Caltech crew. Most entertaining. Watching the TerraMax reverse s-l-o-w-l-y back down the course, only a mile out, at the oncoming Team Golem (who did very well indeed, thank you very much), was excellent, although I wonder if that helicopter it found itself close to had anything to do with its confusion.
This is pretty late--I just got back from the race--and probably no one will notice but I feel like adding it anyway...what I found most striking was that of the four entrants that made any substantial progress, two (CMU, SciAutonics) were big teams, well-organized, lots of resources, etc, and two (DAD, Golem) were, if not exactly homebrew, definitely down toward the lets-just-get-this-shit-together end of the scale. Go hobbyists! DAD was particularly interesting because one, their pit consisted of a robot sitting there waiting to go out, rather than the trailers, RVs, computers, antennas, jump-suited techs, and so on that filled most of the other ones; and two, the end of their race only came after they were stopped, deliberately, by race officials, in order to let a tow truck get up to one of the disabled vehicles up ahead. They weren't able to get it started again in the field. Now of course that's something your autonomous vehicle ought to be able to handle, but still you have to wonder, if they'd had a free course...? The Golem guys get mad props for their enthusiasm, which dwarfed anyone else I saw out there...their vehicle had been totally flailing in the quals, and one guy I talked to said they were hacking away til ten minutes before they got the route (around 4 am). They were totally thrilled when it got through the first gate and across the road, and it was quite infectious, especially since no one had even gotten that far since DAD in the fourth position (Golem was fourteenth, second to last).
I was disappointed not to see TerraHawk (the other Terra) run...it was intriguing but I didn't find out much about it cause I was hanging around while they were really busy trying to fix something (which I guess didn't happen--they scratched themselves before start). Ghostrider was unfortunate too, I was really interested to see it run and the crowd was too. And it ran...a foot. And fell over. Technical letdown, but points for drama. Rumor I heard was, though, that it failed for some really silly reason--wire not plugged in, switch not switched on, something like that. I don't know if they tried another run (a number of vehicles did second, non-competing starts later in the day), but if it was something like that I hope they took another shot.
Really cool overall, though of course it would have been nice to see a bit more performance on the field. Even if everyone failed, strictly speaking, there was a lot of impressive stuff in everything from mechanics to AI. I have no doubt everybody learned a lot and that they'll all kick ass next time around.