As everyone knows, a robot needs two cameras for depth perception. Right? Well, almost. "Many people have said that depth estimation from a single monocular image is impossible," says Andrew Ng of Stanford. That was before Ng and a team of graduate students developed a new vision algorithm. This algorithm can determine depth from up to 50 feet away within 35 percent.

See the press release (Robots can travel more safely with new software) for more information, and keep an eye on Andrew Ng’s page for the upcoming paper.