Robots as Tools and Partners in Rehab
August 30, 2018
In future decades, the need for effective strategies for medical rehabilitation will increase significantly because there will be an increase of patients who survive diseases with severe functional deficits, such as a stroke. Socially assistive robots (SARs) are already being used in rehab for this reason.
Dr. Shelly Levy-Tzedek, head of the Cognition, Aging and Rehabilitation Lab in BGU’s Department of Physical Therapy and a member of the University’s Zlotowski Center for Neuroscience, and BGU doctoral student Ronit Feingold-Polak, along with Dr. Philipp Kellmeyer of the Freiburg University Medical Center and Prof. Oliver Müller of the University of Freiburg, analyzed what measures would be necessary to take in order to improve human-robot interactions and make SARs valuable for medical therapies. The findings were published in the Science Robotics journal.
The researchers concluded that in order for SARs to work they must be deemed trustworthy by the patient.
Robots and patients can only interact well when they have shared goals, which they pursue through their joint therapy. To achieve this, aspects of philosophical and developmental psychology must also be taken into account when upgrading and improving SARs.
For instance, the frustration felt by patients, as a result of physical or linguistic limitations, would be avoided if the robots were adapted to the specific needs and vulnerabilities of the patient in question.
“Patients during rehabilitation, after a stroke, for example, are in a vulnerable and emotional state,” explains Dr. Levy-Tzedek. “To a great extent they rely on the feeling of trust that they have established with their caregiving professionals. For this reason, we have to carefully analyze the advantages and disadvantages of using SARs with stroke survivors.”
According to Dr. Levy-Tzedek, SARs can assist with exercises the patient has to do, but it should be taken into consideration the difficulties that could arise between the person undergoing rehab and the robot.
“For example, the patient could demand certain unrealistic expectations from a robot because of its human-like behavior,” says Dr. Levy-Tzedek. “This could lead to disappointment and a failure to complete the exercise altogether.”
Furthermore, if a robot is unpredictable, it will again make it very difficult for the robot to be considered a successful partner in the rehab project.
In the article, the researchers suggested a few ways in which a robot can build trust with a human patient. This included, the ability of a patient to trust that the interaction with the robot is safe and that the movements being carried out are beneficial to the overall treatment. Also, patients should be able to identify and predict the intentions of the robot during treatment, and the robot should be aware of the mental and physical state of the patient.