What do robotics, manufacturing and stroke rehabilitation have in common? Stefanos Nikolaidis, assistant professor of computer science at Viterbi’s School of Engineering, has worked on these problems before, integrating a different aspect of humanity with robotics.
In July, Agilent, a life sciences company that brings technologies to laboratories around the world, presented the Agilent 2022 Early Employment Professor Award to Nicolaides for his work on human-robot collaboration in manufacturing. This award comes at a time when the links between automation, manufacturing and the supply chain are more important than ever as a result of the pandemic, Agilent said in a press release.
Nikolaides’ journey into robotics began much earlier, despite being an undergraduate in Greece, where he studied electrical and computer engineering at the National Technical University of Athens.
“One of my professors was a professor of robotics, but he was also in a wheelchair because he had [a] “The surgery that didn’t go well,” said Nikolaides. “So, his mobility was very limited, but he was also doing research in robotics as a way to improve not only his life…but also to improve the lives of others who are in a similar situation. I found that very inspiring.”
From there, his journey spanned across many countries and continents, eventually taking him to Los Angeles, where he’s currently studying how robots can be integrated into a human team—particularly in manufacturing.
“There has been a lot of work in robotics that has focused on how to make robots more and more autonomous — for example, how we can fly a drone alone, how we can drive a car alone,” said Nikolaydis. .
But Nikolaides argues that the fact of integrating robots into a human team is very different from the sci-fi horrors of robots taking over the world.
“The robot needs to be able to adapt to the preferences of its human teammates and have a common mental model with other teammates to be able to be a productive member of the team. This is where the primary research question in robot interaction is,” he said. Nikolaides. “[We are researching] How can we develop algorithms that enable a robot to be productive and efficient, but at the same time behave in a way that is acceptable and in a way that is seen as trustworthy by human operators.”
This idea of trust has been an integral part of Nicholas’ work since his time at Carnegie Mellon University under the guidance of his doctoral advisor Siddhartha Srinivasa.
“[Nikolaidis] I particularly looked at two aspects of algorithmic robot interaction. “One of them specifically is about trust,” Srinivasa said. “What does it mean for a human to trust a robot? I think we all kind of know what it means to trust someone, but how do you turn that into a mathematical model?”
Nikolaides’ work focuses largely on solving real-world problems in manufacturing and other industries. When he first arrived in Los Angeles, he visited stroke patients at Rancho Los Amigos National Rehabilitation Center to see how he could use robots to make an impact.
“I asked the stroke patients out there, ‘If you had a robotic arm like this — I showed them some videos, some slides — what would you want the arm to do?’” “People have said things like assisted eating – something I’ve worked on in the past – but what really made the impression was that a woman said, ‘I really have messy hair and that affects my feeling and my self-image. I would really like the robot to help me comb my hair’,” said Nikolaydis. “We have developed a hair-combing system and have replicated this over the years.”
Nikolaides’ effort to speak with the affected was particularly noteworthy to his college teacher, Maja Matari, professor of computer science, neuroscience, and pediatrics.
Engineers have come up with many ideas about what stroke survivors might need. For example, engineers might think, “Well, they need a robot to get to things for them.” But in fact, these are ill-considered guesses. Unless you’re a member of the stroke survivor community, you really don’t know what it’s like and what’s really needed, so you shouldn’t assume.” “It’s really great to see a young researcher like Nicolaides not assuming, but taking the time to learn firsthand. .”
Matarich understands the difficulty of these robotics problems, and said they resonate strongly with Nikolaydis’ willingness to tackle them.
Very few robotics researchers are working on real problems in the real world. Instead, researchers often find it easier to work on simulations or in game evaluation domains, but Nicolaides is willing to take on challenging issues, such as post-stroke rehabilitation, with real stroke patients.”
With human-robot collaboration still a relatively new field, there are many new niches to explore, particularly the unpredictability of human nature. Srinivasa understands the difficulty of managing this mercury in areas such as self-driving vehicles.
“The problem is with these pesky humans, because we drive and do things, like one [piece] Our intentions and cost functions are hidden, hidden and highly personal. I guess the second piece is that we’re sub-optimal agents, right? “It’s not like we’re calculating Nash equilibriums and acting accordingly,” Srinivasa said.
This challenge of finding a solution and linking the variability of human nature with the predictability of robots is what makes the work satisfying for both researchers. Nikolaides sees the potential for robots to help out in the home, due to his original inspiration to pursue robotics.
“If we want to bring bots into the home, … by definition, a human environment where everything is chaotic and there are many users, I think this is a very difficult application,” said Nikolaydis. “I think that is now … one of the main goals in robot interaction, which is how can we have a robot in the home and be able to help with everyday tasks and especially how it can help people with different types of disabilities and people with limited mobility “.
Although he is now at the University of Washington, Srinivasa said he cherished the time Nikolaides spent with him.
“have found [Nikolaidis] Being brave and committed to doing user studies, studying cognitive psychology papers, … to do whatever is needed to make sure that humans and robots work together effectively. You have to be very selfless and accept the fact that in order to get a robot to do anything, you have to do everything. I suspect [Nikolaidis] He’s one of the best I’ve worked with when it comes to acknowledging that,” Srinivasa said.
#Humans #Robots #Stefanos #Nikolaides #Promotes #HumanMachine #Collaboration #Manufacturing