DARPA Challenge Prize Money Restored 119
antispam_ben wrote to mention that, some three months later, DARPA has been able to find the money to offer cash prizes once again. The DARPA Urban Challenge will go forward next November with more than $3 Million on the line. From the article: "The race will see as many as 90 teams 'drive' an unmanned robotic road vehicle through city traffic, competing to finish a 60-mile course within six hours. Set for November 3 of next year, the challenge will call on robots to safely obey traffic laws, negotiate busy intersections, merge into moving traffic, avoid obstacles and navigate traffic circles. DARPA has yet to disclose the race location, but has said it will be in the western United States. The government research group didn't unveil the 2005 Grand Challenge location in the Mojave Desert until weeks before that race, in order to avoid giving any team an advantage."
No need for DARPA (Score:2, Funny)
Re:No need for DARPA (Score:4, Insightful)
If you think about it, all the robotic drivers in computer games such as Grand Theft Auto are pretty damn good, and can follow rules and stick to routes much better than their human opponents. So, driving/navigation algorythms have been developed a decade ago, all they need is a good way to recognize their surroundings.
With this in mind, this whole driving challenge is a problem no different from OCR or voice recognition.
Re: (Score:1, Insightful)
Re: (Score:1)
That's not exactly feasible with vehicles moving at 100+ kph. It's not like we can say, "Okay, a school bus just plowed into an oil tanker, let's tweak the algorithm."
Re: (Score:3, Insightful)
Re: (Score:3, Insightful)
In the first challenge the teams, composed fo bright fellows, all failed exactly because it isn't so straightforward.
The difficulty would exactly be adaptive decisionmaking of the robots; would DARPA (a military instance wanting automated vehicles) put in 2mio USD if it were as easy?
Re: (Score:2)
Re: (Score:2)
Re: (Score:1)
Re: (Score:1)
Re: (Score:1, Insightful)
Re: (Score:3, Insightful)
You have a point that this does boil down to the problem of reducing a car's surroundings into meaningful data, much like in OCR or voice recognition, but there is VASTLY more data in the real world than there is in a single image or audio file.
Humans have
Re: (Score:2)
Isn't this DARPA challenge supposed to be looking for novel, revolutionary, out-of-the-box solutions to dealing with moving obstacles, unstable road, and confusing nav clues at 10 mph?
Oh, here is one: how about you let the robots drive a GPS-equipped BULLDOZER!
Spooky (Score:5, Interesting)
Re:Spooky (Score:4, Funny)
Re:Spooky (Score:5, Informative)
Re: (Score:3, Informative)
Re: (Score:1)
Re: (Score:2)
Also in terms of employmen
Re: (Score:2, Funny)
Sure, in the actual competition. But in the individual team practice sessions at their home institutions? Grad students. Don't deny it.
Dean
Go Tech! (Score:2)
Good to see some names I know on the list of people, too!
Good luck!
Re: (Score:2)
How much does the insurance cost for this? (Score:4, Insightful)
Re: (Score:3, Informative)
Yeah! (Score:3, Funny)
Actually, what I meant to say is that I'll be playing San Andreas in the automated vehicle while it safely navigates traffic--something I can no longer do after playing the GTA series. It is just too tempting to run down pedestrians and try to steal nicer and faster cars!
A city in the Western US... (Score:4, Funny)
Will additional points be awarded if they successfully navigate the LA aqueducts, find Sarah Conner?
Re: (Score:2)
(Seriously, there must have been dozens of action movies filmed in that location)
Traffic circles?! (Score:5, Funny)
No American is going to win this one...
Re: (Score:1)
Stupid misconception (Score:1, Flamebait)
Re: (Score:2, Informative)
Nobody said they didn't. But have you ever sat around watching Americans try to figure one out? (Actually new england apparently has enough that new england natives can figure it out as long as there aren't any foreigners screwing things up)
Re: (Score:2)
Only once in my whole entire life I have seen someone do something entirely stupid in a roundabout. You'd have to be an idiot to screw up it but the only time is when someone started backing
Re: (Score:1)
Re: (Score:1, Insightful)
Traffic circles != roundabouts (Score:2)
No, in this case they've also entirely buggered up the fundamental design too!
http://www.alaskaroundabouts.com/mythfact1.html [alaskaroundabouts.com]
Traffic circle is another term for roundabout (Score:2)
Except for the fact that the vast majority of traffic circles are your roundabouts. Legally there is a difference between a roundabout and a traffic circle. Unfortunately, very few people make the distinction.
Re: (Score:3, Informative)
For those of you unintiated to the wonders of British driving, anyone that tells you to get a right hand drive car to "help" you get into things more quickly should be punched in the throat. Drving on the left hand side of the road, in a right hand, manual car, traffic circles, and all the signs being unfarmiliar makes you feel like you are dislexic and sixteen again.
The first week of driving in t
Yay congress. (Score:3, Interesting)
But after much complaint from contestants, Kenneth Krieg, undersecretary of defense for acquisition, technology and logistics, approved the prize money.
No doubt the driving force behind this decision came from the folks at DARPA. First congress tells them to develop autonomous vehicles, then it proceeds to trip up their efforts with the "John Warner National Defense Authorization Act".
What I'd really like to know is why they're pushing this technology so hard and fast. Does it make sense to go straight to an urban environment when only four constestants even managed to finish the last challenge?
Re:Yay congress. (Score:4, Insightful)
They didn't need everyone from the last challenge to have finished it. They only need one.
The fact that they got four finishers last time means the cross-country technology works. Now that removing the remaining bugs and improving cross-country technology is just a matter of time and money they can move onto the next step: urban driving.
Re: (Score:1)
Re: (Score:2)
Re: (Score:2)
Because IEDs are the #1 killer of US troops in Iraq. Normal combat casualties (gunfire, rocket, and mortar attacks) are almost negligible compared to the number of troops that are killed are injured during convoys or patrols due to roadside bombs.
Getting the human soldier out of the equation would
Call me a cynic if you like... (Score:4, Insightful)
I will be impressed when driving automation systems can start with a general idea of where their source and destination locations are and can read the signs to figure out how to get there. They must use perceptive powers to avoid colliding with other drivers or running down pedestrians and following the rules of the road instead of range finders and lasers and GPS-based speed limit adherance and other such nonsense.
Until the system can be boiled down to a pair of eyes and a pwerful set of smarts driving , in my view, it's just an elaborate obstacle course being followed by the likes of this robot [robotroom.com]. I understand "baby steps", but "they" tend to avoid tackling these big challenges and instead continue to focus on these contraptions that just, plain aren't smart enough.
IMHO, of course.
Re: (Score:2)
Re: (Score:1)
If we can make a robot drive a car using gps, maps and lasers, then once the computer vision technology progresses far enough, we will be able to use that input (signs, etc) in place of the maps. Regardless, it may be solving the wrong problem to even WANT robots to do that. If you can hop in an automat
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Yea I looked at your profile hoping to see if you made other insightful comments to this article.
Re: (Score:2)
First, to the above, I've heard of this use for RFID and I've also heard of permanent magnets as invisible "tracks" embedded in the pavement. A quick glance at the CIA World Factbook [cia.gov] reveals that there is about 6.4M km of paved roadways in the U.S. I just prefer the approach of a smarter information processing system that can make decisions as intelligently as a human driver without retrofitting that much pavement with something that, for all it'
Re: (Score:1)
"In My Horseshit Opinion" (Score:2)
Re:Call me a cynic if you like... (Score:5, Informative)
I've posted elsewhere in this story, but again to prefix my comments, I'm a member of the Georgia Tech team, Sting Racing [sting-racing.org].
The course plotting part of the challenge is actually probably the easiest part. It's roughly analogous to you reading a map beforehand -- we're given a file detailing all the aspects of the course (course segments, how many lanes are in the segments, etc., and zones where free driving is allowed) plus a mission file giving the different waypoints we have to reach. This is, relatively speaking, easy.
The difficult part is determining where the edges of the road and its lanes are (GPS is terrible at this; most of the time it's accurate to 10 or so feet unless you're using extraordinarily expensive differential units) which is mostly done using visual scanning. Of course, we also have to detect other vehicles or obstacles in the path (using LIDAR and vision) and also determine the correct "pose" of the vehicle. Then we have to take that information and use it to modify the path we've already decided to take. These problems as it turns out are far, far harder than just plotting courses.
Re: (Score:3, Informative)
And of course, a lot of the purpose of this challenge is exactly what you stated in your post: we have to detect and avoid other cars, use safe and proper driving etiquette for passing others, follow the rules of the road (i.e., four-way stops, etc.), and dynamically adapt our course to the conditions. Chiefly, this last requirement means noticing obstacles (construction, accidents, etc.) and rerouting, but this could also incorporate predicting traffic jams. For instance, if a heavily-traveled section of t
Re: (Score:2)
Looking at the pictures on your homepage you're using something like SICK scanning LIDAR units, right?
I'm curious - what sort of data rate do you get out of those things?
Thanks!
Re: (Score:2)
We are. I haven't worked on that part of the car, but from what I've heard the SICKs combined saturate a 1GB ethernet link. One of the big challenges we're going to have to overcome for the car is data storage. For testing purposes, we'd like to record the output from all the sensors for individual runs. That way software can be tested offline. But with those consuming 1Gbps, the video cameras consuming about 750Mbps each, and other sensors, even storing the data becomes a huge task. We're probably looking
Re: (Score:2)
Impressive! I know most of the SICKs I've encountered (admittedly not very many) have been the yellow/safety ones, and have only had serial I/O - which made me suspect the data rate was pretty low. Any idea what models you're using, or is it just that fast because you've got lots of them?
Re: (Score:2)
Re: (Score:3, Interesting)
Hopefully less of the former and more of the latter, unless you're trying to travel through Canada to get there. NYC is only 2 degrees (~149mi) north of Sacramento. For comparison purposes, LA is 4 degrees (~312mi) south of Sac.
So what you (and just about everyone else, myself included) REALLY need is a map and/or some signs, rather than some supposed "inherent sense of direction" that you seem to believe we possess. What you believe you know (tra
Re: (Score:2)
Re: (Score:1, Redundant)
Not. Sorry...
The word/acronym Radar means: RADio detecting And Ranging.
Re: (Score:2)
The BBC made a great show about it [bbc.co.uk] which is well worth watching. Even if only for the onboard footage of Stanley cat
Re: (Score:1, Informative)
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
not a cynic, but not right either (Score:1)
Re: (Score:2)
but, while as a software engineer and electromechanical hobbyist I fully appreciate all the challenges involved with these robotic drivers, I'm just not impressed [...] I will be impressed when driving automation systems can start with a general idea of where their source and destination locations are and can read the signs to figure out how to get there.
So, you will be impressed by next year's challlenge winners, then?
Personally I'll be impressed when I see production cars with a built-in survival instincts (sensors reacting to dangerous situations, preventing collisions despite human error, incompetance, drunkeness, etc.).
Re: (Score:2)
The fact that no cars finished the first year, and only three the second, prove that the challenge difficulty was perfect - difficult but achievable by taking the few next technological steps. Whether it impresses you is more a measure of your preconceptions of the field than of the field itself. If you're so sure it's easy, I encourage you to step
Re: (Score:2)
Team Stanley's tactic differed from the way their main challenger, Red Team, handled the course. Red Team manually entered step-by-step driving instructions into both of its vehicles (Highlan
Western cities unite! (Score:2)
Robust policy needed (Score:3, Funny)
But after much complaint from contestants, Kenneth Krieg, undersecretary of defense for acquisition, technology and logistics, approved the prize money.
Policy that is so prone to failure is about as ridiculous as a system that cuts off funding to an entire branch of the military if someone tweaks some minor policy somewhere.
These prize awards aren't just some minor toy program -- they are the future of technology development which means defense preparedness. Maybe there are some radical Muslim cleric moles posing as policy makers. Oh well... Islam isn't as bad as some theocracies.
Re: (Score:1)
Re: (Score:3, Funny)
Well then, we should be easily able to cure Muslims by finding the gene that makes them turn to Islam. A little genetic engineering and *bam*! No more Muslim gene.
Please look up the word "Racism" before you embarrass yourself any further.
Re: (Score:2)
Re: (Score:2)
I'm old fashioned. If I want to know the meaning of a word, I use a dictionary.
3. Anthropology.
a. any of the traditional divisions of humankind, the commonest being the Caucasian, Mongoloid, and Negro, characterized by supposedly distinctive and universal physical characteristics: no longer in technical use.
b. an arbitrary classification of modern humans, sometimes, esp. formerly, based
Televised (Score:1)
Re: (Score:1)
(Yes, I've played Carmageddon far too many times).
Part of the test needs to include an accident. (Score:2)
Does it recognize a human laying in the road?
Big difference (Score:2, Informative)
I know... I know... they did put 'drive' in semi-quotes, but it's still misleading to a reader who is unfamiliar with the Challenge.
I've said it before and I'll say it again: The robots will be driving themselves.
This type of design is worlds different from a system to be 'driven' using a joystick or by some guy monitoring the robot's progress. Amazing leaps and bounds in artificial intelligence, software image recogniti
Re: (Score:1)
I sure hope these bots have some system aboard that allows a real human driver to assume control and pull over the moment something is about to go wrong.
Re: (Score:1)
Stay away from this one! (Score:2, Funny)
is it really ready? (Score:2)
I realize part of this challenge is to force the evolution of the technology and give it a push, but there are limits, and I think this next o
Re: (Score:1)
Re: (Score:2)
Personally, I was going avoid Iraq and Afghanistan too, but not because of robot drivers.
Nobody should get a penny of prize money.. (Score:1)
secrecy = fairness? not! (Score:1)
The government research group didn't unveil the 2005 Grand Challenge location in the Mojave Desert until weeks before that race, in order to avoid giving any team an advantage
.
Openness about everything is actually much better for avoiding any advantage to any team! Keeping it secret just opens up the possibility that one team will get an advantage through a backdoor channel. Openness = fairness.
Of course if you win this race you will spend the rest of your life doing things in secret in our secret underground laboratories.
Women Drivers??? (Score:1)
Re: (Score:1)
Future Robot cars will drive on robot-roads (Score:2)
New DARPA Project (Score:1)
The plan is to set up a course in downtown Detriot or Cleveland and challenge entrants in two categories: the total number of convenience store robberies and the average take per robbery.
They have yet to decide if the automated cars can use weapons of force in this competition.
Re: (Score:2)
I think this is more along the lines of eastern Queens/Brooklyn traffic. You know, those suburbs that like to think they're part of the city.
Hell, if DARPA wants a robot that can replace New York cabbies, it better offer a hell of a lot more than three million.