by Tim Oren
I'll start this with a big tip of the hat to DARPA and its director, Dr. Tony Tether (who has one of the world's best jobs). Not only do they push the bleeding edge and come up with clever ways to engage the research community in their endeavors, but they run well-managed events with a flair for showmanship that belies their status as a government and military agency. As an example of the latter, they had arranged for the Urban Challenge webcast and on-site video to be co-hosted by Jamie Hyneman and Grant Imahara of cable's Myth Busters, the current favorite show of the techie crowd.
They also have the guts to invite in the world press and the general public while trying something new to the world: Turning multiple autonomous vehicles loose on city streets at the same time, interspersed with human drivers. As Tether said at the start of the program, "If anyone tells you he knows what's going to happen, he's lying."
Since that test could likely take every bit of a short November day, the teams, staff and press assembled for their briefings at a chilly and dark 0600.
The Robots at Dawn
It was a day for old rivals to face off again. The Carnegie-Mellon 'Red Team' had been narrowly defeated in the 2005 Grand Challenge desert race, and were back as Tartan Racing, with their bot 'Boss'.
The victors of 2005, Stanford Racing, were also back with 'Junior', based on a Volkswagen Passat.
Processions
But first, perhaps to remind the assembled technology and automotive junkies that there is a serious mission underlying this effort, there was ceremony. The armed forces' oldest form of autonomous transportation met the newest.
A fleet of dozens of human-driven Ford Tauruses paraded through the start area and populated the streets of 'DARPA Town', in reality an abandoned housing area in the former George Air Force Base.
3-2-1...
And then they were off. After the problems caused yesterday by lining up all eleven bots at once, no more than three were staged in the chutes at any one time. 'Odin' from Virginia Tech led off the launch.
Followed by all ten of the other bots, from the smallest, Pennsylvania's 'Little Ben' Prius...
To Oshkosh Truck's 12-ton Terramax, the monster truck of the bot world and a crowd favorite...
Mission One
The day's course for the robots was divided into three missions, each consisting of 6 or 7 subtasks. After each complete mission, the bots would return to the start area to have a new mission file loaded and its sensors cleaned off by the team's pit crew.
The first mission quickly began to take a toll on the bots. I headed from the start area towards a press zone that overlooked a four-way stop which was going to force the bots to interact with one another. By the time I reached it, the DARPA staff's radios were already reporting that the vehicles from Team Annieway and IVS, the two most tentative in their movements in yesterday's practice runs, had already been removed from the course for going too slow and impeding traffic.
At the intersection, Boss soon appeared around a curve, with its chase vehicle behind.
The old housing in the background is in bad shape even for a ghost town. It's been used for urban warfare training that may have featured live demolition charges and flash-bangs, judging from the many blown out windows and walls. The heavy equipment is waiting to take it down as soon as the DARPA show departs.
Bot Jams
Sure enough, the four-way forced the bots to intersect on their courses. Several of them dealt with the traffic correctly, but then the UCF entry froze at one of the stop signs, with its chase car parked close behind. The Cornell bot approached the stopped vehicles from the rear, paused, probably decided they were just obstacles, and pulled out to pass. Then it froze as well.
With one road into the intersection choked, the MIT bot rounded a curve and headed for the opposing stop sign. At the same time, Little Ben rolled up from the right, and the press and DARPA staffers watched in anticipation, with no idea where the bots were supposed to go, or what was about to happen. (Little Ben in the foreground, UCF stuck in the center, Cornell barely visible over Little Ben's roof, MIT out of view left.)
MIT's Talos paused, successfully turned right away from the jam (and then seemed to stop for a bit to think about what had happened.) Little Ben had apparently also been tasked with a right turn, which would take it right into the jam of bots and chase cars. It began to roll, turned... (MIT turning, Little Ben beginning to roll).
...and threaded perfectly through the stopped bots and chase cars, and disappeared up the street. A cheer went up from the humans.
Then everything stopped. The race control had called an 'all pause', which froze all the bots and the human driven vehicles in their places. Word came down that the Terramax vehicle had appeared to go catatonic for twenty minutes while attempting a parking task, then suddenly accelerated, jumped a curb, and headed straight for the old post exchange building. It was apparently shut down before beginning demolition work, but Terramax's confident appearence yesterday did not hold up under stress, and its humans arrived and drove it away.
Pauses struck several more times during the first mission, and after too many inappropriate movements or blockages were caused, the bots from both UCF and Team CarOLO were removed from the course as well. By then the faster bots were returning to the start for their new mission assignments. But with five down and six left, the rate of attrition might end the race early.
Cranking It Up
With the weaker bots out of the way, and with confidence growing in their own performance, several teams appeared to be turning up the maximum speed of their vehicles during their second missions. The number of problematic interactions also dropped dramatically, and there were no further disqualifications during the second mission.
Here MIT's Talos gets a bit of body lean rounding the traffic circle.
By the start of the third mission CMU, Stanford and VT were building up a lead. Cornell and Little Ben had never turned up the speed, and MIT's increase seemed to be getting its bot into troubles. I overheard one CMU team member on the radio saying something to the effect of 'let them hit us for aggressiveness, just turn it up.' The top three were now running close to the posted limit of 25 (which doesn't seem like much until you've had a driverless car doing 25 zip past you ten feet away - on the other side of a K rail, fortunately). Stanford's Junior is pursued by Virginia Tech's Odin down the back straightaway of the traffic circle, with Tauruses chasing.
Making History
Then one of the slower bots, Cornell, pulled onto the traffic circle and stalled (due to a bug in a throttle controller, a team member told me later). MIT's Talos approached from the rear, regarded the stopped bot and chase car, and pulled out to pass the obstacles. As it cut back into the right lane, the Cornell vehicle suddenly moved forward, and the first bot-to-bot contact of the event occurred as bumpers met. This could have been disastrous, as the Cornell team had mounted many of their sensors inside the bumper of their Tahoe. Fortunately, neither vehicle suffered critical damage and they were backed off and restarted. The scuff on the bumper below is one half of the world's first bot-on-bot body shop work.
While Junior had been paused to allow the accident to be cleared, the other bots continued to run, and from that point on none of the three leaders appeared to have substantial delays in completing their tasks. Watching them round the circle to start the next part of the mission started to seem almost routine, and soon the announcer said that all three were on their final laps, and the viewing stands refilled. A cheer went up as Stanford's Junior appeared on the circle first, turned into the finish chute, and took the checkered flag, wielded by Dr. Tether.
Team Tartan's Boss was not far behind.
All four of the other bots still in the running also finished the course, a remarkable achievement for the world's first attempt at such an event. Note again that Stanford's crossing the finish line first does NOT make it the winner. Times will be adjusted for the staggered start, stoppages not the fault of the bot, and for 'moving violations' recorded by the judges on the course. We'll find out the actual winner tomorrow (Sunday) morning.
Update: The results are here.























COOL! Celebrate antiquated technology! Praise the automobile!
Remember, the only goal of engineering is to help already-rich corporate entities earn EVEN BIGGER profits. It never should be about trying to help mankind transition from one stage of its existence to another. It never should be about trying to reduce international friction based on resource disparity; it never should try to reduce the amount of resource theft that occurs when a larger nation spots some plentiful resources within the lands of another nation. No, we wouldn't want to use engineering for that. Because it may interrupt Manifest Destiny, and we all know how that principle is immutable and eteranal.
(Lack of proof and justification notwithstanding)
I'm so proud of our junior industrialists! They see the key to success is to palliate the corporate masters! To expand the gulf between rich and poor, to "level the playing field" through economic and political power disparity being used to flatten the competition!
BRAVO!
Leave no cliche unturned, Wendigo! You go!!
A.L.
Behold the barking moonbat in full cry.
Nope, can't invent our way out of having people run their cars off the road, waste energy stuck in stop and go traffic, or having our troops blown up by roadside bombs while running supply convoys. Better get ready to climb back into the trees, because it's all hopeless and toxic besides.
Pathetic.
If they built a tree obstacle course where you had to swing from branch to branch 60 feet off the ground, and made Wendigo do it, I'd buy tickets....
Don't think much of Wendigos for conversation, but they sure are good eating.
I wonder if Wendigo is as good at avoiding trees as the DARP-funded unmanned vehicles I've seen footage of. (No human drivers or intervention, just a Jeep under fitted out with sensors and under software control.)
Of course what Wendigo misses is that the unmanned ground vehicle, while having obvious auto/truck/military convoy uses, is just one robotics mobility application. The work that went into these systems will also be useful in helping paraplegics live and work with greater ease, in cleaning up toxic wastes and finding survivors in the rubble from natural (or unnatural) disasters.
I guess the junior industrialists should pack it up and quit before those awful applications become reality.
Nice pictures, Tim - thanks.
Sorry about the typos - premature click.
I was in AI back in the 80's (grad school and first job) and did some work on vision in grad school. The progress made in the last few years has been stunning. You really just don't realize how incredibly difficult the problem of 3-dimensional image parsing and the deeper problem of world modeling is until you try to write the algorithms. Bravo to all teams involved!
Oh, and thanks for the laugh Wendigo.
I was seriously disappointed in Terramax. Evidently, Team Oshkosh is trying to create a bolt on kit that could be used on current military vehicles. Once the bugs are worked out, we add a CROWS turret with .50 cal or a Mk19, hook that baby into the AI, and when Skynet becomes self aware, launch them after the fleeing meatsacks....BWahahahhaha! Sorry, my inner-mad scientist ran away with me. Makes me wish I'd stuck with that engineering program in college. Thanks for the great pictures and write up.
Wendigo, bro, take a prozac, you're spazzing...
Regards
Nice chatting with you there in the stands in the sun, Tim.
I was pleased to learn when I got home that despite my fears the default settings for my borrowed camera are more than adequate for print.
But I didn't know that on Saturday. I spent much of the afternoon on Saturday scurrying around to get more shots. So now I have over 400!
A blogger for The Register who covered the event casts aspersions on the character of DARPA Director Tether, stopping just short of accusing his ancestors as well. Easier to throw stones, I guess, as with this fellow Wendigo.
Ashlee Vance said "Seriously though, and I don't say this light (sic), I've never met a single person with anything positive to say about Tether."
You seem to like him more. I have a feeling Ashlee has talked to very few people who have even heard of Tether. Is this what you mean by overconcentration in the media?
I am also a devoted alumnus of MSU by the way, school of Communications, 1976. Shame seeing them get beat by U of M yet Again.
Jim
I've never met Tether in person. I can only judge the results, and (as an old research manager myself) I've been impressed. I suppose for some folks he got onto the 'evil' list since it was under his regime that the (in)famous TIA (Total Information Awareness) program and the so-called 'terrorism market' were spawned. Since I consider those to have been commendable edge pushing that was grossly distorted by both the MSM and opportunistic politicians, that doesn't bother me. Not sure I'm going to bother with the referenced post, but The Register has a well deserved rep for muck raking and generally seeing what kind of trouble they can stir up.
Snowflake, I assume you're joking, but just in case: If there's one thing these 'bots' are not, it's a general purpose artificial intelligence. You're probably better off thinking of them as really fancy signal processing and control systems. Lots closer to cars that park themselves than to HAL or 'I, Robot'. So there's actually nothing there to hook up to any offensive functions.
At any rate, I don't think anyone's about to put mobile weapons into full autonomous mode. Even the fanciest programs out there - look up UCAV/UCAS - have a human finger on the 'weapons free' button. Check out this collection of nasty incidents and cautionary tales for some good reasons why it's likely to be that way except when there's no alternative (e.g, Phalanx point defense systems).