Slashdot Mirror
DARPA Grand Challenge 2005
fishdan wrote to mention that the Darpa Grand Challenge is getting underway again. The qualifying rounds started yesterday. National media has picked up on the story, with pieces at the Washington Post and Seattle Times. From the Post: "The autonomous robotic vehicles began competing Wednesday in the first of a series of qualifying rounds at the California Speedway. Half will advance to the Oct. 8 starting line of the so-called Grand Challenge. The grueling, weeklong semifinals are designed to test the vehicles' ability to cover a roughly 2-mile stretch of the track without a human driver or remote control. Participants ranging from souped-up SUVs to military behemoths will be graded on how well they can self-drive on rough road, make sharp turns and avoid obstacles _ hay bales, trash cans, wrecked cars _ while relying on GPS navigation and sensors, radar, lasers and cameras that feed information to computers."
than a soccer mom driving her only child in an SUV it's an SUV driving no one.
Argh.
I had a chance to see the Volkswagen / Stanford entry while getting my VW serviced. That cart is pretty cool. There's a rack and a half worth of gear in the back and the shift knob has been modified to allow a robot arm to be attached. The engine is a 5 cylinder TDI and the VIN says it's a factory prototype. I heard that when the challenge is over the car will have to be destroyed since it certainly isn't US legal. And in a parody of the "Drivers Wanted" slogan it says "No Driver Required" on the side. :-) Seeing it in person certainly made waiting for my oil change fun.
On a side note...I wish they'd let more diesel cars in the country. The chase car is another Touraeg but this one is a Canadian V10 TDI. It has something like 500 lb-ft of torque but gets about the same highway mileage as my small VW does.
"Where quality is like a dead stinking rat - you just can't miss it."
This will be a MUCH more interesting contest if the teams do better than the last time around. (the best team only got 7 miles out of 175 total.) Granted, even that is impressive given the circumstances.
I wish the best of luck to all of those competing.
I for one am very happy to see this technology advancing. It's not gonna take much intelligence to make an autonomous driver better than most human drivers.
End transmission.
Could they dance too?!!
Only in the USA could it say FROM souped-up SUVs :-)
Here in the UK it would probably be FROM a bunch of lego bricks and a clockwork motor UP TO a Sinclair C5 (or possibly an Austin Mini with an Aibo gaffa-taped in)...
3... 2...
The software and use of sensors, as well as the sensors themselves are being driven to places that they probably wouldn't have gone if not for this contest. Sure, the 2 million dollars is a big-ish prize, but bragging rights are bigger.
I've seen some hobby roboticists building smaller robots for a scaled down version of this that are just amazing. Even on smaller scales, this is pushing technology. The good part? Much of the hobby stuff is pretty much shared in an OSS kind of way. That means that the technology behind all this will not belong entireley to the military, and will soon find its way into our vehicles and homes.... THAT is very cool!
Support NYCountryLawyer RIAA vs People
I read the reports once in a while: The winners, or close-to-finishers, are huge SUVs filled with computers and special-purpose sensory equipment. What this tells me is that today's computer technology still has trouble, in many cubic feet of space, and with practically unlimited electrical power, to find realtime solutions for a problem that even severely IQ handicapped humans handle routinely while balancing a McMeal on their knees and keeping up a cell phone conversation. I would wager that, with a fair amount of training and suitable controls, even a dog could handle the task. So...
Did AI research implode for lack of funding, or is it really that hard? Will we need Cray-like computing power to handle the sensory input quickly enough to work a steering wheel, brake and gas pedal? Or has this problem simply never been tackled by sufficiently big money? And, given the obvious military implications and a $400 Billion military budget alone, why not?
All these questions are quite serious, and I'd be interested in hearing answers.
When one person suffers from a delusion, it is called insanity. When many people suffer from a delusion it is called Rel
My money is on the team that spent all of their money on identical twin spokesmodels
Yes I know, shamelessy stolen from Cruel.
If you could be anything you want, I'll bet you'd be disappointed.
I don't care if these vehicles can drive by themselves 2 miles or 20, just make sure they come with a red LED on the front that alternates back and forth and make it say "right away Michael" everytime I get in the car.
This sig is six words long.
FYI there is a 5min introductory video clip of the the MITRE entry here:
http://www.mitre.org/tech/meteor/
I saw it a few months ago doing it's thing around the
parking lot. It will be interesting to see how they
do on a live course.
I know my money is on Austin Robot Technology. Vehicle "(Not Available)" sounds like it'll be a real winner. lol!
-robyn
Did AI research implode for lack of funding, or is it really that hard?
None of the competitors are doing true AI. They are not using learning systems as far as I know. This is just good old fashioned programming where the designers/programmers try to think of all possibilities in advance. I don't see how this contest is advancing our understanding of intelligence. I think that the qualifying rules should have been more stringent and should have prohibited non-learning systems. Otherwise it's the same old traditional stuff.
There's a hell of a lot less obstacles in the sky.
Remember, it takes 42 muscles to frown and only 4 to pull the trigger of a sniper rifle.
Holy shit! Someone actually submitted a story with a well-written summary, a few good links that can withstand a slashdotting, and most amazingly, they didn't assume that we've all heard about tihs before! This is surely a sign of the apocalypse!
The driverless busses are coming!
http://www.popsci.com/popsci/science/09a7dd9a0cc36 010vgnvcm1000004eecbccdrcrd/3.html
"So Thrun pioneered what's known as probabilistic robotics. He programs his machines to adjust their responses to incoming data based on the probability that the data are correct. In last year's DARPA race, many derailments occurred when a 'bot's sensors provided faulty information, causing it to, for example, mistake a tumbleweed for a rock and stop in its tracks. Thrun's car didn't go off the cliff mentioned above, because its software ignored the bad GPS data (which it judged to have a significant probability of error) and responded instead to the more accurate laser readings. (If the car hadn't made the right choice, Thrun or a colleague would have hit two giant red buttons next to the wheel to disable the AI.)
By early July, Thrun's car had navigated 88 miles of last year's route. It would have logged more, but the pace car got a flat tire after its (human) driver failed to avoid a bump in the road."
I don't see why it would have to be destroyed. Even if it's not street legal, it could be carried around on a trailer, and when it's done with the challenge it'll probly end up being put on display somewhere. They may have other reasons for destroying it (especially if they lose) but I can't think of a legal reason.
Has any of the contestents overcome the obstacle of negative space (i.e. a cliff, a sudden drop, a crater)?
Its easier to detect something that is there like a bale of hay by radar, but what about something that isn't there (isn't an object sticking out of the ground, in y+ axis)? If not, I can see alot of Wile E. Coyote incidents with these cars flying off cliffs.
(**poof**)
~ slashdot.org - Where some of the world's greatest minds come together to scrutinize grammar.
www.teamensco.com
Good luck to my former co-workers who are working with Ensco on the project. From what I hear, they're loving being out there and having a great week!
Yes, but it's also because the government REALLY wanted Autonomous air vehicles. Humvees don't make the best spy vehicle. A plane that can fly for 36 hours over a location taking pictures on the other hand is *very* handy.
"We need a fourth law of Robotics: Stop Fingering My Wife"
es, but it's also because the government REALLY wanted Autonomous air vehicles. Humvees don't make the best spy vehicle. A plane that can fly for 36 hours over a location taking pictures on the other hand is *very* handy.
But a Tank or Hummer that can drive up to the enemy and shoot them isn't?
-nosebreaker.com
If the car has IP/trade-secret technology the company needs to protect -or- technology that would violate somebody else's IP, then destroying the car may be legally necessary to protect the company. Having said that, I can't think of any IP that they could cash in on that they'd need to protect, and nobody in their right minds would risk putting unlicensed tech on something like this - the scandal if a story like that broke would far outweigh the prize on offer.
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)
The problem is noise (and not in just a white sort of way). The real world partialy gets around this by using the redundency that's inherent in the world to pull out useful patterns.*
The other way is limiting the scope of the problem by confining the problem to the essentials. This is partially why you have a kneecap. It makes solving the walking problem easier.
I for one am very happy to see this technology advancing. It's not gonna take much intelligence to make an autonomous driver better than most human drivers.
The benefits of having cars that drive themselves will be enormous. First, these cars can be programmed to drive in a manner that conserves gasoline (e.g., no jack-rabbit starts, limit speeds to 55 mph, time their accelerations between stoplights so they don't have to come to a complete stop at every one). Second, cars that drive themselves in a rational manner -- instead of the emotional, irrational manner that people drive them -- can significantly reduce traffic jams. There is an insightful analysis of traffic jams at this page which explains that jams are larely the result of people not letting other people merge into their lane coupled with the relatively-slow reaction time of humans. Cars that can synchronize their motion in relation to nearby traffic could make traffic jams a thing of the past.
Not to mention that if the car drives itself, I can read slashdot on the commute home (or watch Natalie Portman movies).
GMD
watch this
Remember the famouse automaton Mephisto from the 19th century that claimed to be a chess playing robot.h tml
http://www.angelfire.com/games/SBChess/automaton.
I think I could hide a midget inside an SUV with enough computer looking doohickies to make a cool $2mill.
my company is sponsoring a team and happened to book some extra hotel rooms, so i'm going off to watch the race (instead of gambling away my soul in vegas). bunch of other guys are going from work as well -- should be a blast.
The military wants autonomous vehicles. The Grand Challenge is designed to prod the private sector into trying to accomplish that task. As long as the vehicle can meet the military objectives, I don't think they care if it's as dumb as a brick. Of course, it will need significant real-time processing capabilities to succeed, that's not the same as a learning system. No AI required.
RETURN without GOSUB in line 1050
"In short, the classical AI part (most folks seem to use D* + reactive controls) is not where 90+% of the processing bandwidth is used, you need that power for sensing and for guaranteeing that your control loops cycle at at least some minimum frequency to guarantee safe operations."
The solution to the problem is going to be the adoption of a holistic approach. Remember the human body isn't just a bunch of parts all flying in formation, but one of the most integrated systems around. Everything is going to have to be considered, right down to the role that the frame plays in solving all the other problems.
--
The "are you a script" word for today is distills.
In comparison, the world's fastest supercomputer (BlueGene/L) is rated at a maximum of 183,500 gigaflots, which is about 0.2 peta flops, or one fiftieth of the maximum speed of the human brain.
Now, you don't NEED the full processing power of the human brain in order to drive. That's not my point. My point is that a car-load of computer parts, at the current level of technology, is probably going to drive about as well as a Horseshoe Crab. I'm actually very impressed that developers have actually got as far as they have, as they're very unlikely to be using state-of-the-art technology for this, most are probably using pile-of-PC architectures, not much more than some webcams for vision and basic motors for the robot linkage, most likely continuous for power - steppers have vastly superior accuracy but have no force behind them.
You also have to look at the power cleaning systems they need - car batteries are NOT smooth and car electrical systems are typically pretty rough. On the other hand, computers need power that is spike-free and ADCs (analog-to-digital converters) rely on a steady reference voltage to be able to do anything useful. A noisy power system would be Bad News for a self-operating vehicle. Oh, and computers don't do well when hot, but air conditioning units - particularly if they switch on and off - are going to add some serious noise to the power.
Whoever builds a car that can go a decent distance is worthy of vast respect and awe, because there are some massive technical problems that require ingenious hacking of mechanical, electrical and microelectronic systems to operate in some pretty harsh environments.
I do think DARPA would be foolish to end the contest if there is a winner this year - rather, they should extend the challenge. Have the vehicles go through a wider range of terrains, as a multi-stage rally, perhaps, with cars who succeed in the desert then having to navigate through a forest, swamps, along the tops of snow-covered mountains - pretty much any terrain that a vehicle could realistically encounter if used for military missions.
If DARPA did that, and the contestents succeeded, then (and pretty much only then) would DARPA have a general-purpose robotic vehicle they could throw into any arena that would be hazardous for humans under combat conditions. Why stop when you have something that could have made things easier three years ago had it existed, but which may be useless in a scenario three years from now, when the dangers may be completely different?
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)
Forget about all those relatively static conditions and consider this one: a 5 year-old girl runs out from behind a parked van right in front of the self-driving car. Until a lot of people are 99.99999999% sure that the car will A) stop as bloody fast as it can, B) swerve to avoid the child, or C) 'realize' that slamming into the van is actually preferable to running over the kid, nobody will let these things loose anywhere but a war zone.
RETURN without GOSUB in line 1050
Tomshardware is posting daily updates live from the Fontana Speedway http://www.tomshardware.com/hardnews/20050929_1259 19.html
They have UAVs that shoot the enemy. Moot point.
They don't want autonomous spy HMMWVs, they want autonomous 5 ton truck convoys to run supplies without worrying about casualties.
Coding with assembly is like playing with Legos. Coding an application in assembly is like building a car with Legos.
I realize that. My point was, one of the contributing factors for the push for UAV's was a replacement for the aging U2. Not only were its capabilities fading, you had to rely on a human to endure horrible lengths of time up in the air over hostile territory. The UAV allowed that requirement to disappear. The government has a huge Christmas list of the stuff they want/need. They only have enough money to do a small subset of them. My only point was that the government needs an effective spy vehicle, the UAV provided that. My post was to be taken in jest, obviously. No one would think that the Humvee would be a good spy vehicle, the point was to say that a good spy vehicle was higher on the Christmas list than a unmanned ground vehicle to prevent casualities. The OP was most right in saying that UAV's are somewhat more simple because they don't have objects to run into. I do argue though that ground vehicles can *stop* when they are confused about something, a UAV doesn't have that luxury. The best it can do is circle over a location until it becomes reaquainted with its mission.
"We need a fourth law of Robotics: Stop Fingering My Wife"
Comment removed based on user account deletion
Once the military has truly autonomous vehicles it won't be that much longer before we cede our control of cars to a computer.
Just make sure it isn't using an MS operating system. Otherwise a BSOD will take on a whole new meaning.
My home team, Cornell, is currently in second place at the qualifiers, knocking only over one cone on the obstacle course.
You can read their blog here, or find their website (with technology writeups) here.
Austin Robot Technology's Entry is an Isuzu Vehicross based robot named Marvin.
It's a race, so there's sport.
It's for research, so there's a utility aspect.
They transport things, so they're vehicles.
One could argue that every one of the competitors is an SUV.
He doesn't know the mean of the phrase AI.
AI doesn't mean "Learning", it means Artificial Intelligence. Said poster is probably a stage in his life where his visual system is relatively stable from day to day. Whether it got there by being hard wired by his designer or through learning is irrelevant. His intelligent behavior (barring perhaps said post) on a moment to moment basis is the result of his pre-wired system, not some kind of fabulously amazing learning algorithm.
Some of the engineers attacking this problem are using machine learning, others are using pre-fab algorithm, most are using a combination of both. They're all true AI by any stretch of the definition.
Murphy and the Dessert.
Ooo man the floppy drive is broken. No wait. The computer is just upside down.
I am in one of the team, every team are using the same technology, same sensor and processing, there are truly not much AI in these since AI technology is too naive at this point that complicated system like this is not applicable at all. Regarding the price tag for each team, equipments are well over 1 Million for each car. DARPA is making a out of this contest, at least the total spending helps the economy.
I for one, welcome our new autonomous driver overlords! ;-)
I thought it was going to take place in Athens, Greece.
The safety expectations for a self-driving car will be exponentially greater than we demand of our own stupid selves. Even if self-driving cars kill people in only 5% of the situations where a human driver would, it will be too much liability for the market to bear. I'm not saying it makes sense. We accept (out of necessity) that human drivers are fallible, and expect profound remorse (as well as prison time) if they make mistake that takes a life. If a machine kills, it can't be remorseful and we can't punish it. Human nature will push us to -find- somebody to punish, and out of fear and frustration, the punishment will be extreme.
RETURN without GOSUB in line 1050
Don't kid yourself... this stuff is hard. Let's take just one specific example: Detecting an obstacle such as barbed wire at a distance far enough away to avoid it.
.25 seconds instruct the vehicle to stop you've traveled 7.5 feet. At least another 20 feet will pass before the vehicle comes to a stop. That means you need to detect any obstacles at least 30 feet ahead of you, and really, that's cutting it close, since the course may be off road. I'd be uncomfortable with my sensors if they didn't have a range of 50 - 70 feet.
First realize that if you're traveling at 20mph (the average speed you need to maintain in order to complete the course and be competitive) that means you're traveling at 30 feet per second. If the sensors detect an obstacle and within
So, how do you detect barbed wire from a range of 50 feet? First of all, it's hard for our eyes to see barbed wire at that range. The primary way we can do this is to spot the fence posts. However our eyes are better than any optical sensor you can equip a robot with. Since the fence posts can be 30 feet apart you'd need aproximately a 30 degree field of vision. However, a simple web cam will not cut it... you'll need high resolution, which means lots of graphics processing power. If you can't process 10 frames per second then you're going to increase your stopping distance and therefore you'll need to increase the range at which you detect obstacles.
And that's just to spot the fence post! How does the computer equipment know the difference between a fence post holding a string of impassible barbed wire and some ordinary obstacle that the vehicle can merely avoid?
Let's go a step further... how do you detect any object at 50 feet? Keep in mind the economics... the prize is $2mil. That's if you win. That's if you finish. Who can afford to invest $1mil on sensors and computer equipment just for a *chance* to win? No one. There are no promissed govt. contracts, no special deals for the winner. This automatically precludes spending $50,000 - $100,000 on a single sensor capable of detecting obstacles at that distance.
Even having a chance at winning this contest will require a team of brilliant individuals each specialized in a certain area. Plus, you'll need brilliant fund-raisers. I'll be surprised if anyone completes this course with less than $150,000 invested in equipment. You'll need programmers, someone who knows the mechanics of the vehicle, someone who knows the sensors. You'll need to deal with the heat (the vehicle will probably spend a lot of timing traveling under 10mph which is not ideal for cooling), rugged terain. This is a challenging assignment. Hats off to the folks who cross the finish line, if anyone makes it. (last year no one came close)
Some people have suggested that this sort of behavior should happen anyway (i.e., regardless of computer-controlled cars).
The idea is that when drivers come to an intersection and see other drivers coming, they slow down, figure it out on their own, and it seems to be more efficient than arbitrary stop sign rules. (Heck, no one seems to understand the "in the case of a tie, the driver on the right goes first" rule.) And at least where I've lived in the US, no one quite understands 4-way stops -- there's just a pile of "after you" handwaving.
Anyway, in the case of good computer control, I doubt you'd have to do much planning before those 12 cars get to the intersection. Self-organization seems to work just fine for birds and ants, and there are rarely ant traffic jams that I've seen.
Cars that can synchronize their motion in relation to nearby traffic could make traffic jams a thing of the past.
Would that work if some cars were not automated? Also, even if all cars were automated, they would have to share common strategies. If some cars were programmed to be more aggressive than others (by design or by chance) then you'd be back to your traffic jams. Also, you'd have to allow for breakdowns & erratic behavior in the automated paradigm.
I've seen your driving. Birds are scared shitless.
Get a room!
"A great democracy must be progressive or it will soon cease to be a great democracy." --Theodore Roosevelt
First, every entry this year is far, far better than anything last year. Everybody has something that really can drive itself. Last year, only 7 of 20 entries made it out of the start area. This year, a big fraction of the teams are getting clean runs. So many are succeeding that tomorrow, DARPA is making the obstacles harder.
Most of the technology is not that innovative. But there are some very clever entries. The self-balancing motorcycle actually works this year.
The price of entry is going up. Last year, it looked like Battlebots. This year, it's starting to look like NASCAR. Several teams have large custom-built trailers. Sometimes I feel like we brought a knife to a gunfight.
No time for much more tonight; we're scheduled for the track at 0715 tomorrow.
John Nagle
Here's my idea: There are already robotic camel/horse jockeys. These jockeys are operated by remote control. Simple solution:Camel Intelligence ( CI ). Instead of a remote control, equip one with a gps, and maybe a compass. Then the jockey could signal the animal to go to whatever the coordinates of the finish line were.
Sure, this would require some training efforts, you'd start having the jockey guide the Camel across the paddock towards a treat, and soon you'd have an animal willing to cross the sahara for a sugar cube.
And Camels are big animals, you could easily strap a tactical nuke to one and blow up a few caves.
And maybe a camel is more than neccessary. Maybe rhesus monkeys or rat brains could be trained to drive robo-tanks over the mountain pass into the camps of the enemy...
Because Americans can't drive for shit.
Manuals still perform far better than auto in anything but rush hour traffic. Try controlling the weight transfer of an automatic through a corner, it sucks. Until that automatic transmission is plugged into your brain, it's not going to work better becuase it does not knwo what you are trying to do with the car.