A new robot aims to safely dress people with limited mobility

To increase efficiency, the robot has tolerance for hitting a person, so long as the impacts are harmless.

An MIT robot assists people with limited mobility. Robots. Robotics.

One of the dreams of robotics is to help people with disabilities lead normal lives by augmenting their limited mobility.

One concern is safety, however. A robot needs to be gentle like a human, and use the appropriate amount of force. You don’t want a robot to yank a shirt over your head too aggressively. But it shouldn’t be so gentle as to be slow.

San Francisco Chronicle/Hearst Newspapers via Getty Images/Hearst Newspapers/Getty Images

To that end, researchers at MIT CSAIL have developed a method for robots to dress people that balances safety with speed.


Alright, it’s not that fast. But the team behind Safe Dressing, as it’s called, says the new method could enable a robot to help complete basic tasks faster.

Whereas most robotics algorithms are programmed to avoid hitting humans altogether, the algorithm CSAIL researchers programmed tolerates some collisions, so long as the impacts are calculated to be non-harmful.

That’s good because if the robots were trained to avoid hitting a person altogether, they might freeze up when a person squirms as they’re being dressed. They need to understand how to engage with a human, like a human.

zoranm/E+/Getty Images

"Developing algorithms to prevent physical harm without unnecessarily impacting the task efficiency is a critical challenge. By allowing robots to make non-harmful impact with humans, our method can find efficient robot trajectories to dress the human with a safety guarantee."

Shen Li, PhD candidate at MIT who lead the MIT CSAIL team.


The research is still in its infancy, but the technology could someday be used in a wide range of assistive robotics applications.

selimaksan/E+/Getty Images

Thanks for reading,
head home for more!