A new algorithm helps robots predict the paths people take in structured environments like the factory floor, which may further enable close collaboration between humans and machines.

On a factory floor, robots are programmed to stop momentarily if a person passes by. The robot often freezes in place long before a person crosses its path. While robots can predict where a person is headed, they can’t anticipate how long the person spends at any point along their predicted path.

A new algorithm accurately aligns partial trajectories in real time, allowing motion predictors to accurately anticipate the timing of a person’s motion. When applied on a factory floor, instead of freezing in place, the robot simply rolled on and was safely out of the way by the time the person walked by again.