This year's DARPA Grand Challenge looks like it was pretty awesome. People from work have been sending links to their photos (see below) and it's amazing to me to think that in the year since the inaugural competition there are already five autonomous robotic vehicles that completed the 130 mile course and the $2M prize has been claimed. I'm also happy to see that students from my high school were on a team (ENSCO) that made it two-thirds of the way through the course and finished sixth (highest of the non-finishers).
Yesterday I got to talk with someone who got to drive a chase car in last year's Grand Challenge. The vehicle he was following had been programmed to avoid obstacles and had a general plan for getting to the destination, but it didn't have much else. What happens when you only teach a vehicle to avoid obstacles? It finds obstacles and then avoids them, so instead of driving along the road, it would find two bushes along the side of the road and drive between them.
- Gallery w/ wrecked vehicle photos, the giant 16-ton Osh Terramax vehicle, and a short video of the robo-motorcycle
- Gallery w/ video of a vehicle bowling over a stack of tires
- Gallery of the main contenders starting and finishing
- Official video of Stanley navigating the Beer Bottle Pass portion of the course
Comments (5)
Its interesting RedTeam has yet to post what went wrong with their primary entry. This year they entered two hummers (Sandstorm, and H1lander). Sandstorm was programmed as a back up to go slow and steady and be carefull to garentee a finish. H1lander was supposed to go as fast as possable. Out on the course early in the race H1lander started to faulter and both Sandstorm and the stanford team cought up (time wise).
I was personally pulling for RedTeam. Sandstorm is increadibly impressive. Last year it had an 4way Itanimum main system doing all the heavy lifting. Its too bad they hobled Sandstorm. In their press release they lemented not letting Sandstorm go full tilt since H1lander failed. If they weren't exagerating if either Sandstorm or H1lander were at full capacity either would have won by a much bigger margin then stanford won by.
Posted by pqbon | October 11, 2005 2:24 PM
Posted on October 11, 2005 14:24
RedTeam's first post about H1landers failure. Sounds like something physical, as apposed to software.
http://www.redteamracing.org/index.cfm?method=logs.list&logID=287#287
Posted by pqbon | October 11, 2005 2:27 PM
Posted on October 11, 2005 14:27
I appreciate the "Drivers not required" tag.
Posted by Alex | October 11, 2005 2:41 PM
Posted on October 11, 2005 14:41
I don't know, I think Drivers Wanted would have been pretty funny.
Posted by pqbon | October 11, 2005 3:16 PM
Posted on October 11, 2005 15:16
I was pulling for Stanford -- Sebastian Thrun is one of the best public speakers in the field of AI. My favorite vehicle, though, was the Ghostrider motorcycle. It didn't even make it to the finals, but I thought the fact they were even attempting the race with a motorcycle was interesting because, ignoring stability issues, you cannot carry as much sensing equipment on a motorcycle. Laser range finders are cool and four laser range finders (Stanley) are even cooler, but I like seeing a team trying to do the low budget approach.
Posted by kwc | October 11, 2005 5:03 PM
Posted on October 11, 2005 17:03