Employees of the Laboratory of Personal Robotics at Imperial College London taught a robot to put on
Researchers and engineers continue to integrate robots into the healthcare industry, with a focus on helping partially paralyzed patients in hospitals.Teaching the robot to dress patients has proven challenging due to the nature of the soft materials used to make the clothes.Because tissues take on an infinite number of shapes, it's difficult for engineers to teach a robot how to handle them.To solve this problem, Zhang and Demiris took a new approach.
They put the robot in a simulated hospital roomroom with a mannequin lying face up on the bed. Attached to the wall was a hook that held a hospital gown. The task of the robot was to remove the gown from the hook, move it to the optimal position, approach the bed, determine the “patient” and its position in space. And then put the gown on the patient, raising each hand in turn and pulling the gown over each in a natural way.
To teach a robot to perform a series of tasks,the researchers broke down the sequence of actions into a series of unrelated steps. They also created several models to use as training elements that showed the robot how to distinguish between colors and textures. Then they taught the robot to choose between different options for action.
When testing the new approach, engineers found that they could teach a robot to dress a mannequin correctly about 90 percent of the time.In total, they conducted 200 tests.
Read more:
There is another “planet” inside the Earth: how it saved nascent life
Nuclear fusion no longer needs millions of degrees: how the new method works
New study refutes light energy transfer theory