Researchers have developed a new robot that can mimic the movements of care workers hands as they dress a person.

So far, assistive dressing robots designed to dress an elderly or disabled person have been created in the laboratory as a one-armed machine, but research has shown that this can be uncomfortable and impractical for the person being cared for or cared for.

To solve this problem, Dr. Jihong Zhu, a roboticist at York University’s Institute for Safe Autonomy, proposed a two-handed assistive dressing scheme inspired by the movements of real caregivers to reduce the discomfort and stress of the person being cared for.

It is believed that this technology could be important in the social care system, allowing care workers to spend less time on practical tasks and focus more on people’s health and mental well-being.

Dr Zhu collected information about how the care workers moved during the dressing exercise, allowing the robot to observe and learn from people’s movements and then use artificial intelligence to create a model that mimics the helpers’ own tasks.

This allowed the researchers to collect enough data to illustrate that dressing requires two hands, not one, as well as information about the angles of the hands and the need for the person to intervene and stop or change certain movements.

“We know that practical tasks like getting dressed can be done by a robot and that allows the human worker to focus more on monitoring the overall well-being of the person being cared for. It’s been tested in the lab, but to make it work outside of the lab, we really needed to understand how the care workers are doing this task actually did,” noted Dr. Zhu.

“We adopted a method called learning by demonstration, which means that you don’t need an expert to program the robot, the person just has to demonstrate the movement that is required of the robot and the robot learns the action. It was clear that the care workers needed two hands to satisfy those with different abilities people’s needs.”

Source: Science Daily