DARPA Grand Challenge 3 127
Meostro writes "DARPA announced the 3rd "Grand Challenge" today, The DARPA Urban Challenge. "To
succeed, vehicles must autonomously obey traffic laws while merging into moving traffic,
navigating traffic circles, negotiating busy intersections and avoiding obstacles." This year's new twist is two tracks for entry: the first is the same as the previous two challenges (develop on your own without Gov't. funding), but the second involves "submitting a detailed proposal for up to $1 million of technology development funds." Here is the PDF press release ."
My Dissapointment in DARPA (Score:5, Insightful)
Yes, they do research in defense but shouldn't there be a little more than a tiny graphic or blurb about what work they're doing? Couldn't they at least take the time to write an abstract or 1-2 page paper with unclassified information on each project?
Instead, I find the following links in the 'Archives' [darpa.mil]:
- Quantum Computing [darpa.mil]
- Infrared Focal Plane Array/Uncooled Integrated Sensors [darpa.mil]
- Advanced Lithography [darpa.mil]
- Most of the Other Links [darpa.mil]
My alma mater has produced better papers than this in these fields. I know that a lot of this stuff isn't classified and they list their programs on their sites, why can't they do a better job in showing the American public what they've done with our money?The Grand Challenge Forums [darpa.mil] are flooded with only vendors. Where are the designs and reports by the teams from older Grand Challenges? Why isn't this structured more like RoboCup where the learning algorithms are released every year so that future contestants can build on this?
The fact that this contest isn't run in a more open way makes it seems like less of a "contest" and more of a "do our research for us!" kind of thing.
Whilst I understand.... (Score:4, Insightful)
We believe the robotics community is ready to tackle vehicle operation inside city limits. - Dr. Tony Tether, DARPA Director
You can build the safest car in the world but there is always a need to be able to take a very quick decision to avoid some other idiot who might be breaking the rules of the road and not be in an automated car... still, if we all had them...
Re:Whilst I understand.... (Score:4, Insightful)
You would needs some serious AI and pattern recognition to really replace drivers. There is just too much that can go wrong.
Re:Whilst I understand.... (Score:4, Insightful)
I am not sure if you are concerned that they will run the test on the open road (I doubt it) or about the prospect of robots on the open road in the future. Personally I think a degree of automatic control would even now prevent some of the really stupid behavior I see every day riding my bike to and from work.
Robot drivers will be somewhat better and somewhat worse than human drivers. This is true even today. It is nice that somebody is encouraging research.
Too early to go Urban. (Score:2, Insightful)
Its too early to go urban. They should have spent at least another 2-3 years perfecting autonomous navigation in unstructured environments.
I know last year's challange seemed to be won rediculously easily, but I have seen no proof that that dormain has been fully conquered yet. If they wanted a challenge why not move onto wooded or swampy areas.
In this case it seems they are juat setting themselves up to fail.
Surur
Re:Too early to go Urban. (Score:3, Insightful)
In this case it seems they are juat setting themselves up to fail.
No, they're setting a difficult task. Now look up the definition of "challenge". See?
People said the same thing after the first challenge, but people got the hang of that pretty quickly, and from what I've read over the last couple of years, this challenge should be just about doable.
Re:Too early to go Urban. (Score:4, Insightful)
Second, because it's a challenge! Last year's competition was not easy- look at the one two years ago, where most of the contestants barely made it out of the starting gate. (Or didn't) When proposed, it was an absurd reach- no robot had come anywhere close to the Grand Challenge specs; they were all busy managing 5-10 mph on easy courses. Nobody would have been interested if the challenge had been 10mph for 10 miles. Would they get the same number of entrants this year if the challenge was basically the same as before?
I agree, this is a serious reach. But honestly, it's not impossible. You have a *lot* more to navigate by in the city- all sorts of yellow and white paint lines on the road, existing high-detail maps and standardized road signs. Most of the drive will be free of serious obstacles, although I assume DARPA will throw in a some shell holes and road blocks to make it interesting. The radars to track other cars already exist- you can buy a car today with sophisticated cruise control that maintains correct distances. My guess is that robots will be better in city driving than humans very soon- 360 degree radar, much faster reaction times, no Starbucks latte and cell phone...
I suspect the next Grand Challenge will be something like "Start at Depot A, navigate across 300 miles of varying terrain, drop off at city center B". Speaking as that ex-platoon guy, most of the drivers in my unit couldn't *read*, much less read a map. They had to be led the entire way by someone who could. (Or at least, pretended he could- this was in the days before GPS.) Bring on the robots.
Re:readiness? (Score:2, Insightful)
Re:Whilst I understand.... (Score:3, Insightful)
You can build the safest car in the world but there is always a need to be able to take a very quick decision to avoid some other idiot who might be breaking the rules of the road and not be in an automated car... still, if we all had them...
How is it any less safe? If anything, the feature with which human beings far outsurpress computers is our ability to filter huge amounts of information very quickly and only concentrate our computing power on what matters. A motion picture at 30fps has very little informational change between frames and so we are experts at making the correct assumptions about those changes, and identifying the important parts, and "seeing" what is happening... Obviously, if you break those assumptions (think of a power-point slide at 30fps), human beings filters are no longer of use, and we fail horribly.
Let me bring my little tagent back to the point... human beings filter things based upon our experiences... we "zone out"... unexpected things surprise us... and catch us by surprise... an "idiot" coming out of nowhere takes a huge amount of reaction time for an unsuspecting human "in the zone" to identify, process, and react to. If anything, this is a place where computers should be able do to better because of it's inherent ability to process everything, everytime. You don't surprise computers, you just confuse them.
Re:readiness? (Score:4, Insightful)
When you boil it down, they're the exact same thing -- this is just a couple orders of magnitude more difficult. The previous challenge didn't have them dealing with any dynamic variables -- no passing vehicles, no being passed by vehicles, no boulders rolling off a mountain, etc.
And if you're going to solve those problems, why not do it for real? A boulder falling off the side of the road is reasonably uncommon. A car cutting you off is not (n.b. -- the challenge doesn't actually talk about this as an issue, and it may not be; we'll know more after May 20).
It's still all about road detection, object detection, and avoidance. And you're asking what they have to do with each other technically?
Are they going to give the robots the GPS location of all the stop signs and traffic circles?
Again, we won't know until after the Participant Conference on May 20, but I'd actually suspect they will, along with info on what speed limits apply in different areas (as they did last time). This is not unreasonable -- GPS mapping a city is pretty trivial when it comes down to it, and I doubt that the challenge is geared toward being fully dynamic -- e.g. you'll still follow a predetermined route, there won't be sudden changes in traffic rules (no road crews), and so forth.
That said, even if you have full GPS info on stop signs and so forth the most that's useful for is that you need to be watching out for a sign coming up soon. GPS isn't accurate enough (at least on a moving vehicle) to rely on it for road signs -- coming to a complete stop 3m beyond the stop sign doesn't work so well. So they'll still have to visually recognize a lot of traffic signage.
In some ways this will be easier than the previous challenge -- this is all low speed, so the issue of not being able to process the incoming data in real time will be reduced. On the flip side, you'll have to process a lot more data this time -- as you said, you must be able to recognize the difference between a boulder and a bush for this challenge.
I'll be impressed with no crashing into each other, before they worry about compliance with all traffic laws.
I'll be absolutely stunned if anyone succeeds this year, and moderately surprised if anyone succeeds at the one after.
But once this is complete, on to the next challenge -- mixed mode driving (urban, suburban, highway, maybe offroad). Then you can't tailor your algorithm toward a specific goal.
Re:This will be easy ... (with caveats) (Score:1, Insightful)
Yeah - there's lots of information, and that's the problem. You're not just concerned about finding the road and avoiding obstacles as in the desert challange, but rather are in the middle of a rapidly changing environment that's presenting an information overload (unpredictably moving cars, people on sidewalks, traffic lights, road signs, other signs) that needs to be correctly sensed, interpreted, prioritized and reacted to (predict path of other dynamic objects, which are operated by intelligent agents vs on predictable trajectories), all in real time while at the same time trying to follow a high level plan such as traversing a traffic circle while staying in lane and trying not to kill anyone. The AI component is at least an order of magnitude more complex, probably much more.
The hardest part of GC1 was finding the road! When it's layed out for you nice and easy.... man thats a cakewalk.
Staying on the road is probably one of the easier tasks, but I don't think it's a cakewalk unless it's so tightly controlled as to avoid all the real-world things that add difficulty such as nightime driving, rain, old road markings, confusing exits/on-ramps, etc, etc. Remember also that all the nice clues such as road markings and curbs may be obscured by traffic, and follow the car in front only works when the car in front isn't switching lane or swerving to avoid hitting something, etc, etc.
True AI (Score:3, Insightful)
This is the Grand Challenge I was really waiting for. I believe that the experience gained in the previous Grand Challenges is practically useless for this new one. This new challenge will involve true AI, that is, AI that has true general learning capabilities and the ability to adapt to new situations. A true autonomous vehicle will need to have common sense understanding and the only way it can have this is by learning through trial and error, imitation/observation, the capability of being trained via communication (with a trainer) and the well known principles of operant and classical conditioning. In addition the AI will need robust and sophisticated perceptual (visual and auditory) system in addition to sound motor control/learning mechanism. This AI will forcibly be based on some sort of neural network or a integrated collection of neurla networks.
What Darpa is asking for is none other than the solution of the AI puzzle. I'm afraid this is worth much more than a few million dollars.
Re:My Dissapointment in DARPA (Score:3, Insightful)
You'd rather find out DARPA has handed out a $10B contract to a "regular" defense contractor to solve this particular problem in ten years, only to find out at year #9, they will need a seven year extension and have cost overruns of another $8B?
A couple of years, a few million dollars as one carrot, the other two are establishing legitimacy in a captitalistic market looking for established technology, and finally, chest thumping in the geek world is a very, very tiny investment by comparison.
Wouldn't you think?
I spent last Summer & Fall headed via an eight mile drive to the "Yellow House" practically every night (plus weekends), knowing I was going to get to see new friends who were working on the same fun things and no matter how boring world was, I was going to get to challenging stuff and watch te jeep run around like a madman. I'd do it project after project if I got the chance.
I'm salivating to find out there's another swing of the bat and am waiting to find out what's going to happen locally.