In a recent video, Willow Garage researcher Eitan Marder-Eppstein describes the open-source navigation stack they've released as version 1.0. The code, available at http://ros.org/wiki/navigation, was designed to be flexible and cross-platform, he says, and could be used in anything from a small iRobot Create-based bot to a large multi-sensor robot like Willow's own PR2 (which Spectrum has covered in detail here and here).
The stack lets users configure different sensors, change the footprint of the robot, integrate SLAM systems, and use a 2D or 3D view of the world. Says Marder-Eppstein:
"In particular the three-dimensional view of the world enables the robot to avoid obstacles like tables, chairs, and people's feet."
And a guy trying to hit it with a two-by-four.
"This is a significant improvement over navigation stacks that view the world as purely planar," he says.
I like Willow because their work is practical and promising. And because they have a sense of humor. They really put their bodies on the line.