Teacher Robots may become the future in elementary schools

We’ve been promised for years that robots will soon move from factories into our everyday lives and yet so far, nothing.

In addition to dexterity and the ability to walk, one of the biggest hurdles to personal robotics has been human-machine interaction.

For a machine to enter human space, it has to understand certain niceties and if a robot with social skills can be built, it could have a huge effect on our classrooms.

An ideal social robot responds not just to what you say, but to how you say it, factoring in social cues like intonation, gestures, and facial expressions.

The robot can then respond with appropriate body language. We take this kind of interaction for granted in science fiction.

In reality, it looks like Leonardo, a robot built by MIT’s Cynthia Breazeal that smiles and reaches for a puppet that he’s told is good, or Kismet, who hangs his head in shame when scolded.

We like treating robots as though they are people. Even with today’s simplest robots, researchers have seen study participants give their machines names and carry on one-sided conversations with them.

Compare that to the ambivalence people feel about their computer screens and it’s easy to see the potential for robots to keep people engaged.

Our affinity for robots also appears to affect how we learn from them. Researchers at Yale recently found that people doing cognitive tasks like logic puzzles (in this case nonograms) learn more effectively when guided by a physical robot than they do with the same help from an on-screen avatar.

The study doesn’t draw conclusions as to why the physical robot was a more effective teacher than its on-screen version, but one guess is that the physical presence of a teaching robot lends it a degree of authority that participants didn’t sense from the digital instructors.

The way we divide the world between animate and inanimate objects plays a major role in how we learn, says Yale professor Brian Scassellati, who worked on the study.

We’re used to identifying computers as inanimate and teachers as animate, but social robots don’t fit neatly into either category.

Their physical presence and interactivity make them seem animate without actually being alive, and they can respond to people and social cues, but often only in fixed and superficial ways.

A National Science Foundation project led by Scassellati, Breazeal and USC professor Maja Mataric aims to push these limits.

The team is working to develop robots that can help children with disabilities learn social and cognitive skills.

To carry out meaningful interactions, though, these robots have to be able to learn on their own so they can understand an individual’s personality traits and social cues.

Juyang Weng, co-founder of Michigan State University’s Embodied Intelligence Laboratory, is studying how robotic learning and cognitive development can look more like human learning in order to strengthen the connection between children and robot teachers.

Traditional robots, even ones used in education, aren’t really interactive, he says, but are often just a new interface for familiar computer programs.

Creating artificial intelligence based on learning and social skills, though, will set a new standard for interactive educational technologies.

“Eventually if a robot can develop its mind, then the robot can be a very close friend of a child,” Weng says. “The robot can be a teacher in a very fundamental way.”

Yes, it may still be a long time before children learn their ABC's in the robotic classroom but moving social robots from science fiction to reality promises to be a powerful force for education.

Human or robot? Part 2

"Babies look to us for guidance in how to interpret things, and if we treat something as a psychological agent, they will, too," Andrew Meltzoff says.

"Even more remarkably, they will learn from it, because social interaction unlocks the key to early learning."

The finding offers clues to how babies decide whether a new object, such as a robot, can think and feel. Details are reported in the October/November issue of Neural Networks.

“Babies learn best through social interactions, but what makes something ’social’ for a baby?” says Andrew Meltzoff, lead author of the paper and co-director of the Institute for Learning and Brain Sciences at the University of Washington.

“It is not just what something looks like, but how it moves and interacts with others that gives it special meaning to the baby.”

“Babies look to us for guidance in how to interpret things, and if we treat something as a psychological agent, they will, too,” Meltzoff says. “Even more remarkably, they will learn from it, because social interaction unlocks the key to early learning.”

Meltzoff and colleagues hypothesized that babies would be more likely to view the robot as a psychological being if they saw other friendly human beings socially interacting with it.

During the experiment, an 18-month-old baby sat on its parent’s lap facing study coauthor Rechele Brooks, a research assistant professor. Sixty-four babies participated in the study, and they were tested individually.

They played with toys for a few minutes, getting used to the experimental setting.

Once the babies were comfortable, Brooks removed a barrier that had hidden a metallic humanoid robot with arms, legs, a torso and a cube-shaped head containing camera lenses for eyes.

The robot—controlled by a researcher hidden from the baby—waved, and Brooks said, “Oh, hi! That’s our robot!”

Following a script, Brooks asked the robot, named Morphy, if it wanted to play, and then led it through a game. She would ask, “Where is your tummy?” and “Where is your head?” and the robot pointed to its torso and its head. Then Brooks demonstrated arm movements and Morphy imitated.

The babies looked back and forth as if at a ping pong match, Brooks says.

At the end of the 90-second script, Brooks excused herself from the room. The researchers then measured whether the baby thought the robot was more than its metal parts.

The robot beeped and shifted its head slightly—enough of a rousing to capture the babies’ attention. The robot turned its head to look at a toy next to the table where the baby sat on the parent’s lap.

Most babies—13 out of 16—who had watched the robot play with Brooks followed the robot’s gaze. In a control group of babies who had been familiarized with the robot but had not seen Morphy engage in games, only three of 16 turned to where the robot was looking.

“We are using modern technology to explore an age-old question about the essence of being human,” says Meltzoff. “The babies are telling us that communication with other people is a fundamental feature of being human.”

More news from the University of Washington: http://uwnews.org/uwnhome.asp

Human or robot? Ask the baby

Babies who watched a robot interact socially with people were more willing to learn from the robot than babies who did not see the interactions, a new study shows.


The finding explores the age-old question: What makes us human?

“Babies learn best through social interactions, but what makes something ’social’ for a baby?” says Andrew Meltzoff, lead author of the paper and co-director of the Institute for Learning and Brain Sciences at the University of Washington.

“It is not just what something looks like, but how it moves and interacts with others that gives it special meaning to the baby.”

More.......

Learning Difficulties - Robotic Teachers in the Class

An English-teaching robot stands in front of children at a primary school in Daejeon, South Korea

Picture: AFP/GETTY