The secret to robots with good balance? Shakira-level gyrating hips

As much as we might worry about what robots are going to do to humankind, they’ve got plenty of their own to be concerned about when it comes to how they are treated by members of the public. Whether it’s mean-spirited shoves or kicks or simply just the odd accidental bump, robots are going to have to get better at retaining their balance when they’re suddenly faced with an unexpected force without warning.

That’s where Mercury, a new bipedal robot created by roboticists at the Cockrell School of Engineering at the University of Texas at Austin, comes into play. Mercury is designed to exhibit an impressive dynamic, human body-inspired ability to stay balanced when encountering these scenarios. It does this using a smart system that lets it quickly work out the best possible move to make following a collision. Unlike other attempts to solve this problem, it reacts by adjusting its whole body — including some Shakira-style hip wiggling — rather than just readjusting its feet.

“What we’ve developed is a computational process by which bipedal robots can quickly recover from continuous disturbances, like those endured by people walking in crowds, without ever falling,” Luis Sentis, associate professor in the Department of Aerospace Engineering at the University of Texas at Austin, told Digital Trends. “Such technology opens up the possibility that humanoid robots [can] walk and operate nimbly alongside us — for instance, during crowded sport events, getting inside transportation vehicles, holding groceries while shopping, or even dancing salsa with us.”

The team next plans to continue testing Mercury under additional experimental conditions to see how it copes under situations like carrying furniture, guiding a person by holding hands, or potentially playing soccer. Given that even the smartest robots can easily lose their balance, a more robust method for keeping robots upright would certainly be welcomed by the robotics community.

“One of the key questions we are considering is what capabilities and morphologies will allow robots to increase human comfort and productivity,” Sentis continued. “We believe that in addition to nimble locomotion and dexterous manipulation, endowing anthropomorphic attributes to robots increases our understanding of their behavior, much in the same way that we require artificial intelligence to respond to our questions in human-like ways.”