Current iterations of assistive dressing robots, which are designed to help elderly populations or those with disabilities to get dressed, typically feature just one arm. However, the team at the University of York's Institute for Safe Autonomy have devised a two-armed assistive dressing robot to potentially reduce discomfort and distress to patients.

Source: University of York

To develop the two-armed robot, data was collected about how care workers moved during a dressing scenario. The researchers explained that they initially allowed a robot to observe and learn from human movements and then, using artificial intelligence (AI), create a model that reproduces how human care workers perform such tasks.

Based on this data, researchers concluded that two hands were necessary for dressing to avoid having the patient do too much work or to experience much discomfort.

Further, such a development promises to enable care workers to spend less time performing these tasks and instead turn their attention to the health and mental well-being of patients.

"Human modeling can really help with efficient and safe human and robot interactions, but it is not only important to ensure it performs the task, but that it can be halted or changed mid-action should an individual desire it. Trust is a significant part of this process, and the next step in this research is testing the robot's safety limitations and whether it will be accepted by those who need it most," the researchers added.

The team’s findings are detailed in the article, “Do You Need a Hand? — A Bimanual Robotic Dressing Assistance Scheme,” which is published in the journal IEEE Transactions on Robotics.