Catching flying object is typically thought of as a uniquely human achievement. After all it, takes both split-second brain calculations and rapid physical adjustments to happen successfully. Not anymore. Researchers from the Learning Algorithms and Systems Laboratory at EPFL (LASA) have designed a robotic arm that can adjust to catch all manner of objects thrown at it in five hundredths of a second. The robot may even have applications for warding off debris in outer space.

“Increasingly present in our daily lives and used to perform various tasks, robots will be able to either catch or dodge complex objects in full-motion, said Aude Billard, head of LASA. Not only do we need machines able to react on the spot, but also to predict the moving object’s dynamics and generate a movement in the opposite direction.”

Until now, the problem with machines attempting to perform similar feats was time – most of them are pre-programmed, and any deviation from the plan requires complex calculations that simply take too long. Recalculating the flight arc of an object in three dimensions isn’t exactly a simple task.

The cool thing about this new robot is that it learns and improves much the same way humans do – through trial and error. If an outfielder misjudges the path of a fly ball and misses the catch, he takes that into account the next time a similar situation arises. Like a human, practice makes perfect. In a technique called “programming by demonstration,” the robot receives no specific instructions. Instead, it shows examples of possible trajectories. It then consists of manually guiding the arm to the projected target and repeating this exercise several times.

The research was conducted with a ball, an empty bottle, a half full bottle, a hammer and a tennis racket. These objects were chosen based on their lack of predictability in flight due to unrelated or fluid centers of gravity. Based on a series of cameras surrounding the robot, it’s able to take visual information and eventually process it into equations.

To fully appreciate the robot’s speed, check out the video below: