Robots Can Now Defend Themselves Against Our Flying Kicks

Youtube/Alebotics

Humanity seems to be intent on teaching robots how to destroy us.

Humanity seems to be intent on teaching robots how to destroy us. We’ve taught them to keep steady when they get knocked and to keep going when they get damaged. Now scientists are teaching them how to stay upright when we jump kick them in the back.

A group of researchers from the Italian Institute of Technology and Carnegie Mellon University have been working on teaching human-shaped robots how to keep their balance when they get hit from behind. As you can see in the video above, researchers hit their robot in the back with a pole, a weight suspended from the ceiling, and then just flat out started jump kicking it in the back. In each instance, the robot interpreted the force of the hit on its back, and braced itself on a wall in front of it.

At some point, researchers for some reason placed what appears to be a figurine of WWE wrestler John Cena atop the weight. Perhaps the researchers had some anger issues they needed to work out. Or they are in the early stages of prepping for a robot fighting league.

The researchers’ work addresses one of the hurdles that needs to be overcome if we’re ever to have humanoid robots in our lives: These heavy, mobile hunks of steel and complicated circuitry fall over very easily. That was perhaps most obvious at last summer’s DARPA Robotics Challenge, where robots competed to finish a obstacle course that featured problems they might face in a disaster situation. The robots fell over a lot, inspiring the research team to try to find a solution.

The researchers said they hope in the long term to have the robot be able to balance without bracing itself against something—a skill that would be useful in disaster response situations, which often involve debris-littered environments.

This isn’t the only work being done on robot balance. Researchers at Georgia Tech are also teaching robots how to brace for impact when they get knocked down. The idea behind the research is that when we eventually have humanoid robots in our lives, they’ll want to be able to protect themselves from damage in our environment in the same way that we would. But when the robots rise up, this ability to protect themselves could well be our undoing.