Carnegie Mellon grabs robot car racing flag, $2 million

Carnegie Mellon's Tartan Racing team won first place and $2 million in the DARPA Urban Challenge this past weekend. The field of 11 autonomous vehicles was pitted against each other on a course of suburban/urban roadways.

After reviewing judges' scorecards overnight, DARPA officials concluded that Carnegie's Boss, a robotized 2007 Chevy Tahoe, followed California driving laws as it navigated the course and that it operated in a safe and stable manner.

Surprisingly, many of the robots made good decisions, said DARPA Director Tony Tether. That meant speed became the determining factor, Tether said, and Boss was the fastest of the competitors by a large margin.

Boss averaged about 14 MPH over approximately 55 miles, finishing the course about 20 minutes ahead of the second-place finisher, Stanford. Virginia Tech took third.

According to a report in The Register, in two years, the university teams have been the ones to show the most progress in these DARPA contests. Boosted by millions of dollars in government and corporate aid, the academics have crafted systems that can share the road with human drivers.

The robots know how to take their turn at a four-way stop. They know how to follow traffic laws such as flashing their indicators when passing a slower car, and they can, for example, mimic the task of taking off from a garage to pick up a jug of milk and then return home.

Would these robots fare well on the busy streets of a real city? No. In fact, even the winning teams suffered from the repeated stops and starts generated by confusion. Some cars would perform great, weaving through one way streets and intersections only to come to a complete halt in the middle of an open road, the Register stated.

While an urban application may be attractive, DARPA says its third-annual Urban Challenge program has the goal of developing technology that will keep soldiers off the battlefield and out of harm's way.

The Urban Challenge features autonomous ground vehicles maneuvering in a mock city environment, executing simulated military supply missions while merging into moving traffic, navigating traffic circles, negotiating busy intersections, and avoiding obstacles. The machines must also handle parallel parking and intersections with two- and four-way stops - situations that can confound many human driven vehicles.

Join the Network World communities on Facebook and LinkedIn to comment on topics that are top of mind.
Related:
Take IDG’s 2020 IT Salary Survey: You’ll provide important data and have a chance to win $500.