Lab turns commercial robots into rehab therapists
As the healthcare system becomes overburdened, budgets are denied, and employees leave in droves, there is a growing need to develop solutions that will enable the expansion of human capabilities – without humans being involved.
Consider, for example, a person undergoing surgery. The surgeon will operate for a few hours, but later the patient may need several hours of physical therapy to achieve the desired results. Due to lack of staff and funding for physiotherapy, patients are sent home to exercise on their own. There they encounter obstacles, ranging from boredom to performing exercises incorrectly in the absence of professional guidance.
Professor Shelly Levy-Tzedek believes home robots can take on some work tasks, and is gradually proving it in her lab at Ben-Gurion University.
Levy-Tzedek, a biomedical engineer by training with a Ph.D. from MIT, focuses on developing social robots to aid in effective self-training. She uses commercially available robots and programs them according to her needs. The term “social bots” refers to bots that can chat, demonstrate actions, remind people of tasks, help with app usage, and more. Social robots are gradually becoming more and more popular in the public space. “We worked with Pepper, for example, a humanoid robot that you sometimes see in hotels in Asia and in airports. It’s mainly used for marketing purposes.”
Levy-Tzedek programmed Pepper to help post-stroke patients, where physical therapy might look something like this: the patient reaches out for a cup, sensors tell the robot the location of the cup, it’s i.e. the degree of success. The robot can then give the patient instructions on what to do: put the cups in order, invert them, etc., at increasing levels of difficulty. There are other physiotherapy modules, such as hanging keys on a rack, and a memory exercise to recall the names of objects.
“It should feel like playing a game, increase motivation. It should be fun. Boredom, frustration and lack of feedback are major factors why people fail to do physiotherapy at house. One of our tasks is designed as an escape room. You have to find an ID card, type four numbers, open a drawer and find keys. In fact, you perform a series of motor functions and cognitive skills of daily life.Another task is designed as a game of poker or blackjack.
Not all robots need artificial intelligence
In one experiment, Levy-Tzedek examined how the relationship with the robot affects long-term rehabilitation care outcomes. “Usually academic robot experiments test one-time encounters, but the advantage of robots is their ability to encourage persistence,” she says.
In the experiment, the subjects were divided into three groups: one trained with a physiotherapist and received exercise recommendations, but without a robot; the second received the same recommendations with the possibility of exercising with a robot; And the third received recommendations with support in the form of instructions on a computer screen.
“We observed that despite physiotherapy – for hand functionality – the control group did not improve at all. The group that received instructions via a computer screen improved by 63% and the robot group s improved by 90%. This experiment was carried out as part of the doctoral thesis of Dr. Ronit Feingold-Polak, advised by Levy-Tzedek.
Somewhat surprisingly, Levy-Tzedek’s robots do not have a high level of artificial intelligence (AI). “In the future, robots are expected to have limited levels of artificial intelligence capabilities; they will be able to detect and respond to compensatory movement patterns,” she says. What is missing in the lack of self-training is feedback on those compensatory movements that cause patients to make incorrect movements in an exercise by reaching for an object, for example. The lab is writing an algorithm that will allow the robot to detect compensatory movements, offer suggestions and also say “Well done” if a compensatory movement is not performed.
If the robot is not compatible with AI, does this ruin the illusion that it is intelligent?
“Not necessarily. We had patients who treated him like a human being. For example, in our early trials, he sometimes made mistakes, and there were people who said, ‘I’m human and I make mistakes, so, okay, he can make mistakes too. Others said they loved him and enjoyed meeting him. People said, “He’s not judgmental,” even though the physical therapists weren’t judgmental either. comments, it will be perceived as a judgement. This is something we will have to check.
Judgement can also be positive. If you’ve made an effort, you might want an intelligent being to see it and appreciate it.
“We record each event and relay the information to the physiotherapist so that he can praise the patient for his perseverance.”
A dedicated room has been set up for the system (robot and peripheral equipment) at the ADI Negev-Nahalat Eran rehabilitation village near Ofakim. Levy-Tzedek’s lab is currently working on a smaller, simpler, and cheaper home-use version. “My vision is that the product will also be available for rental from Yad Sarah [the national non-profit that loans medical and rehabilitative equipment and other services at nominal or no cost].
Adults feel connected – children, not so much
The Levy-Tzedek laboratory studies human-robot interactions to learn how to build them. “It’s very important that the robot doesn’t repeat sentences too often,” says Levy-Tzedek, “but randomness isn’t ideal either. For example, a joke shouldn’t be repeated multiple times. That’s boring or in poor taste., and reinforces that the robot is not human. So maybe partial coincidence, and humor very rarely.
“We also observed that body movements had to be culturally appropriate. For example, a robot from Japan made a movement that was supposed to indicate joy, and Israelis asked, ‘Why is he angry? What did I do wrong??'”
Levy-Tzedek also points to intergenerational differences. “In fact, the adults accepted it as an independent entity and said they felt connected to it. Some young people did, but others said it was ‘scary’. We don’t know. not exactly why. After all, these young people grew up with technology and with people they only know through a screen, and yet they were the ones who said it was too weird for them. When asked how they would like to tell the robot that they had completed a training session – by pressing a button or stroking its hand – adults preferred stroking the hand, and younger children, pressing a button.”
A fur seal to reduce pain
In another experiment, Levy-Tzedek used a robot sold as a toy in the shape of a stuffed seal. “We looked at pain endurance in healthy volunteers, with or without the presence of the robot. We found that they felt less pain and fared better when the robot was present and talking to them, and the situation improved even more when they caressed him or hugged him.”
What makes some people feel like they’re making a real connection with a robot? Is it related to the personality of this person?
“We found no difference in the measurements we know of. We speculate that specific measurements can be developed for a willingness to accept the illusion of humanity in inanimate objects.”
The robotic seal was also not compatible with the AI. “It’s very complicated to develop a reliable artificial intelligence,” admits Levy-Tzedek. “On the other hand, the illusion of attachment, as we have demonstrated, does not necessarily depend on it, and can even destroy it. The AI speech recognition for Hebrew is really bad. ability to understand spoken Hebrew is almost non-existent. certainly exists when it comes to understanding different accents, or stroke-affected speech. The day a robot will understand our patients, and they will be able to hold a conversation with it , is still a long way off.
In the short term, even robots with an understanding of the English language will not convince anyone to suspend disbelief. said Levy-Tzedek. “I don’t know of any robot that can really hold a conversation that could deceive us.” Therefore, she says, it is important to manage expectations. “At the end of the day, the patient knows it’s a training tool and not a friend, so there’s no disappointment here. We don’t expect to have a real conversation with our medical device, even if the the fact that he’s humanoid is part of what does the job. This duality is something we don’t fully understand.
Which is better: virtual reality or robots?
Levy-Tzedek’s lab also studies rehabilitation in virtual reality conditions. “We investigated people’s preferences for cognitive training. Today, this is done using software that shows you, for example, a series of shapes in different colors, and you have to click when you see a certain sequence. So we divided the subjects into three groups. One performed the task like this, the second received instructions from a social robot – including comments, conversation, pause from meditation and empathetic comments like “Yes, that exercise was difficult”. collect shapes.
“In previous experiments we’ve run comparing VR with robots, the robots usually won, but we suspected this might have happened because VR couldn’t show its true abilities. We wanted to let each tool demonstrate its maximum capabilities, then compare. And in fact, in this experiment, we got opposite results: 66% preferred virtual reality, even if there were also complaints, like nausea, or the helmet being uncomfortable. We believe that in the future it may be possible to combine elements, sometimes robots, other times virtual reality, to keep things interesting.”
Today, Levy-Tzedek is designing a robot for patients who have suffered from illnesses other than stroke. “Our lab team comes from different fields – clinical, engineering, psychology and cognition. Our partners come from education and philosophy. I also believe in cooperative planning. When we design a robot, we include patients and their families from the start. We ask clinicians what they see in their clinics that is important, and through this ongoing conversation with all stakeholders, we build very positive interactions.”
Published by Globes, Israel business news – en.globes.co.il – on March 13, 2022.
© Copyright Globes Publisher Itonut (1983) Ltd., 2022.