DARPA Grand Challenge Finalists Announced

Xerotope writes "DARPA announced today the 23 finalists[pdf warning] of the DARPA Grand Challenge at the closing ceremonies of the National Qualifying Event. Carnegie Mellon University's Red Team will start on Saturday with the first and third positions, with 'H1ghlander' taking the pole position and 'Sandstorm' following 10 minutes later. Stanford's 'Stanley' will start second. Of the 43 semi-finalists, 23 robots managed to finish the 2.2 mile course at least once. 5 robots (Stanford, Red Team, Red Team Too, Axion Racing, and Team Teramax) completed all of their runs. CMU's 'H1ghlander' and 'Sandstorm' finished the four runs with an average time of 10 minutes, 20 seconds each. Stanford's Stanley average time was 10:43."

Ghost Rider

[Anonymous Coward]

Too bad Ghost Rider did not make it. :( Check it out http://www.ghostriderrobot.com/ [ghostriderrobot.com]

Go ENSCO!

[JMUChrisF]

Go Team Ensco! Great job so far guys! Keep it up!

www.teamensco.com

More information and Video coverage here

[rayver]

Video coverage here (there's a whole bunch. The overview, stanley and ghostrider ones are awesome!):

http://www.cartv.com.nyud.net:8090/content/researc h/channels/index.cfm/channel/cartv_video/action/sh owvideo/vid/e_0145/vcat/Event/ [nyud.net]
NQE final paper:

http://www.darpa.mil/grandchallenge/NQEfinal1.pdf [darpa.mil]

And more announcements can be found on:

http://www.grandchallenge.org/ [grandchallenge.org]

Also, a good summary of things that have been happening can be found in the discussion forum:

https://dtsn.darpa.mil/grandc/forum/topic.asp?topi c_id=1636&forum_id=30&Topic_Title=NQE&forum_title= Grand+Challenge+Event&M=False&S= [darpa.mil]

=====
A post by Espina reads:
Hi! ...stopped by the NQE last week and this whole Tuesday and I must say that all the work accomplished on all the AGVs was very impressive. ...for those who couldn't be there the following bots all had runs in the morning session: "Mojavaton, DAD, CIMAR, Insight Racing, Golem Group, ENSCO, Princeton, MonsterMoto, Team Jefferson, UCF,, AION, Cajunbot, Banzai, Gray Team, Mitre Meteorites, Virginia Tech Grand Challenge Team, Austin Robot, Desert Buckeyes." All had full runs except five. Majavaton and Insight Racing which both collided with a vehicle/obstacle within 100 yards of the finish line. Aion decided to skip the course and circle back directly to the finish line but a K- rail barrier refused to co-operate. The UCF bot went walkabout on the back 40 towards the NASCAR track and Austin Robotics got sulky in the first loop when the crowd left for lunch during its run. MonsterMoto was given a restart because a chase truck encroached on the route near the start. ...according to some team members from Ensco, the afternoon session was a chance for the teams "on the cusp" to improve their standings. Austin Robotics, CajunBot, VT, Team Banzai, Mojavaton, the Mitre Group, and the Gray Team all had additional runs. ...Mojavaton, VT, Mitre (had two) and the Gray Team all had full runs. The Gray Team had two runs but was unable to to get GPS back after the tunnel on the first run so they made a few adjustments and had a stellar 2nd run. It seemed like a time/constelation problem. CajunBot made it to the last Obstacle/vehicle to the chagrin of the crowd. Team Banzai froze contemplating a witch's hat on a downhill transition at the end of the first loop and Austin Robotics lost GPS (and its way) after the tunnel... ...after that the best of the rest ran (Autonosys, Blue Team, Overbot, Indiana Robotic NAV, BJB Engineering, Team Juggernaut, Autonomous Vehicle Systems, Team Tormenta, Indy Robot Racing, Terra Engineering, PVHA Road Warriors, CyberRider, AI Motorvators, Team Underdawg. )with most of the teams wiping out the first barrier, and/or re-arranging the hay bales at the tunnel entrance, colliding with the tunnel entrance and losing GPS after the tunnel. However, IT, from AI motorvaters had a full run on the shortened RDDF and TerraHawk made it thru most of the hard parts. Overbot ran very thoroughly and cautiously but froze on the downhill transition. ...if any of this information is incorrect please feel free to fix...I could be suffering the effects of sunstroke... ...anyhow, good luck all and I admire dedication of all of the teams on completing an AGV. ...see y'all in Primm, Espina

well if the summary isn't going to explain it...

[fanblade]

If you're wondering what the DARPA Challenge is, you have to scroll to the bottom the their flash website [grandchallenge.org]:

"The DARPA Grand Challenge is an unprecedented government effort to accelerate research and development in autonomous ground vehicles to help save American lives on the battlefield. DARPA will award $2 million to the autonomous (robotic) ground vehicle that can successfully navigate a challenging desert course of approximately 150 miles the fastest (in less than 10 hours). The vehicles must find and follow a prescribed course route, avoid obstacles, and negotiate turns, all while travelling at militarily-relevant rates of speed. The ground vehicles are fully autonomous - not remote-controlled."

Re:More information and Video coverage here

[rayver]

oops.. didn't realize the NQEfinal paper and the grandchallenge links were already provided. Anyway, some more links (to articles):

http://www.tgdaily.com/2005/10/06/darpa2005_featur e_update/ [tgdaily.com]

"Blue Team" runs self-righting motorcycle at darpa Grand Challenge
http://www.tgdaily.com/2005/10/03/darpa2005_featur e_update/ [tgdaily.com]

DARPA Grand Challenge update #3: Interview with Team Cornell
http://www.tgdaily.com/2005/10/02/darpa_cornell_in terview/ [tgdaily.com]

DARPA Grand Challenge update #2: A chat with Team Mojavaton
http://www.tgdaily.com/2005/10/02/darpa_grand_chal lenge_update2/ [tgdaily.com]

DARPA Grand Challenge Update #1: Qualification Day 1 results
http://www.tgdaily.com/2005/10/02/darpa_grand_chal lenge_update1/ [tgdaily.com]

Gearing up for the DARPA Grand Challenge:
http://www.tgdaily.com/2005/10/01/darpa_grand_chal lenge_introduction/ [tgdaily.com]

Re:Still too slow

[not5150]

Due to the speed limits imposed at the qualifications, the vehicles could not get much better times.

At the qualifications, there were mandatory speed limits imposed in most (if not all) the areas. In the RDDF file, there are the GPS coordinates and a speed limit number. For example, the straight away was 40mph while some of the obstacle strewn areas was 5 mph. The vehicles are capable of going faster and in fact a couple vehicles maxed out the 40 mph on the straight away.

DARPA officials at the media press conference on Wednesday said that if they stick to the race speed limits, then they will finish in about 6 1/2 to 7 hours. In the real race, there are hard speed limits and then there are suggested limits (which a team can break). The suggested speed limits are in low obstacle areas, but are suggeseted so that the chase vehicle doesn't lose sight of the robot. Remember that this race is being held in the desert, so the dust kicked up could obscure it from view.

Quirky fact, the BLM (Bureau of Land Management) mandates 25 mph or less in desert tortoise areas. You gotta love beauracracy.

Some of this is explained in my article on tgdaily.com

http://www.tgdaily.com/2005/10/06/darpa2005_featur e_update/ [tgdaily.com]

Re:Still too slow

[Mockingbird]

There were hard speed limits set on various sections of the qualifier course. The best performing vehicle, H1ghlander, executed the course within a few seconds of the best possible time given the constraints. Performance on the NQE course has about as much to do with race-success as grating cheese does with belly dancing.

At least three of the vehicles that qualified for the race have performed 170 mile runs at race-success pace on mixed road/off-road courses that should simulate race conditions very closely. Many of the vehicles have code in place that allows top speeds over forty miles per hour when long, straight, smooth sections of course are detected.

I know that the CMU teams pre-plan their runs in the two hour period between receipt of the course waypoint file and the beginning of the race. They will not load a plan designed to execute in more than ten hours and, given the quality of the competition this year, I betcha they'll be aiming at eight.

A hot issue this year that I haven't seen discussed on public forums is intent-to-pass. My understanding is that DARPA will force a vehicle into 'pause' mode if it is being overtaken by a faster competitor. I'm willing to bet there will be some post-race howling around that dynamic.