Researchers at MIT are working on a system that would enable robot planes to follow standard hand gestures. The team recorded a series of videos in which several people performed a set of 24 gestures commonly used by aircraft-carrier deck personnel.

The MIT researchers’ software represented the contents of each frame of video using only a few variables: three-dimensional data about the positions of the elbows and wrists, and whether the hands were open or closed, the thumbs up or down. The researchers stored sequences of the abstract representations, and the team used the database to train its gesture-classification algorithm.


Also: Learn about a thrust-control system for emergency control of an airplane.