DARPA Grand Challenge Updates

GraffitiKnight writes "After only 1 team managed to successfully navigate the DARPA Qualifying course, DARPA has rewritten the rules to let almost everyone compete. Wired has the story, which also mentions rumors that the race will run to 150 miles, much less than the original plans of 210 - 300 miles." Here is some earlier Slashdot coverage of the race.

Comments

Frank Dellaert was right

[ayatollah jones]

From the Previous Story

Quoting Frank Dellaert, co-director of Georgia Tech's robotics lab from the article, 'I would have trouble driving some of these roads myself. I think it's beyond the capabilities of autonomous vehicles today.'

I guess he was right after all...

Very bad robots

[Animats]

The Ohio State monster truck rammed a mini-van (picture) on Tuesday. On Wednesday, it was stopped before running down a course obstacle. And DARPA is letting them attempt the actual event?

The QID was pathetic. We spent two days watching vehicles move around at 1MPH and hit big, obvious obstacles. No way can most of those vehicles operate effectively offroad.

The big design mistakes seem to be these:

• Using a laser rangefinder aimed horizontally forward as primary obstacle detection. That doesn't work reliably on either dark or smooth objects. The black mini-van was both.
• Using fixed line scanners. If you miss a data point, you're stuck. There's no way to take a second look.
• Overreliance on vision. Computer vision in unstructured situations has a very poor track record.

Only CMU is doing well. It's not the money, by the way. Their actual cash outlays are only about $300K to date. It's the body count and the fear. They have about fifty people on the project, a slavedriver boss, and the full backing of CMU. CMU has to do well; most of the Robotics Institute funding over the last three decades is from DARPA, and DARPA can turn that money off at any time.

John Nagle
Team Overbot