Robot Learning Companion Offers Custom-tailored Tutoring
March 14, 2016 | NSFEstimated reading time: 4 minutes
Parents want the best for their children's education and often complain about large class sizes and the lack of individual attention.
Goren Gordon, an artificial intelligence researcher from Tel Aviv University who runs the Curiosity Lab there, is no different.
He and his wife spend as much time as they can with their children, but there are still times when their kids are alone or unsupervised. At those times, they'd like their children to have a companion to learn and play with, Gordon says.
That's the case, even if that companion is a robot.
Working in the Personal Robots Group at MIT, led by Cynthia Breazeal, Gordon was part of a team that developed a socially assistive robot called Tega that is designed to serve as a one-on-one peer learner in or outside of the classroom.
Socially assistive robots for education aren't new, but what makes Tega unique is the fact that it can interpret the emotional response of the student it is working with and, based on those cues, create a personalized motivational strategy.
Testing the setup in a preschool classroom, the researchers showed that the system can learn and improve itself in response to the unique characteristics of the students it worked with. It proved to be more effective at increasing students' positive attitude towards the robot and activity than a non-personalized robot assistant.
The team reported its results at the 30th Association for the Advancement of Artificial Intelligence (AAAI) Conference in Phoenix, Arizona, in February.
Tega is the latest in a line of smartphone-based, socially assistive robots developed in the MIT Media Lab. The work is supported by a five-year, $10 million Expeditions in Computing award from the National Science Foundation (NSF), which support long-term, multi-institutional research in areas with the potential for disruptive impact.
The classroom pilot
The researchers piloted the system with 38 students aged three to five in a Boston-area school last year. Each student worked individually with Tega for 15 minutes per session over the course of eight weeks.
A furry, brightly colored robot, Tega was developed specifically to enable long-term interactions with children. It uses an Android device to process movement, perception and thinking and can respond appropriately to children's behaviors.
Unlike previous iterations, Tega is equipped with a second Android phone containing custom software developed by Affectiva Inc. -- an NSF-supported spin-off of Rosalind Picard of MIT -- that can interpret the emotional content of facial expressions, a method known as "affective computing."
The students in the trial learned Spanish vocabulary from a tablet computer loaded with a custom-made learning game. Tega served not as a teacher but as a peer learner, encouraging students, providing hints when necessary and even sharing in students' annoyance or boredom when appropriate.
The system began by mirroring the emotional response of students - getting excited when they were excited, and distracted when the students lost focus - which educational theory suggests is a successful approach. However, it went further and tracked the impact of each of these cues on the student.
Page 1 of 2
Suggested Items
Raymond E. Pritchard IPC Hall of Fame Award: Peter Bigelow
04/04/2025 | Nolan Johnson, I-Connect007IPC’s most prestigious award honors an individual’s long-term distinguished service and contributions to IPC and the electronics manufacturing industry. Peter Bigelow is president of FTG Circuits in Haverhill, Mass., focusing on the military, RF/microwave, and aerospace markets. He also has extensive experience in general management, marketing, operations, and sales with large publicly traded and privately held manufacturing companies in the printed circuit, electronics, and instrumentation industries.
It’s Only Common Sense: The Danger of Overthinking
03/24/2025 | Dan Beaulieu -- Column: It's Only Common SenseWe’ve all had those moments when we find ourselves endlessly analyzing a decision, cycling through every possible outcome, and trying to anticipate every potential obstacle. It’s not just frustrating; it’s paralyzing. Overthinking is a timewaster, a progress-stopper, and a productivity killer. For many of us, it’s become a habit that keeps us from reaching our full potential.
Just Because You Can, Doesn’t Mean You Should
03/20/2025 | Tony Plemel, Flexible Circuit TechnologiesDecisions are usually made by gathering information and differing opinions, then making the best choice based upon that information. The same process is used when designing flexible circuits and rigid-flex circuits. For example, when designing a flex circuit or rigid-flex circuit, we consider some basic factors.
Speaking the Same Language as Your Fabricator
03/12/2025 | Andy Shaughnessy, Design007 MagazineWe do indeed have a failure to communicate; designers and fabricators often seem to be talking past each other, which can lead to jobs being put on hold. We asked Jen Kolar, VP of engineering for Monsoon Solutions, and columnist Kelly Dack to share their thoughts on ways that we can break down the communication barrier between design and fabrication. As they point out, a design kickoff checklist and a solid review process can be invaluable tools in a designer’s toolbox.
Hannah Nelson: The Inspiring Journey of an Emerging Engineer
03/11/2025 | I-Connect007 Editorial TeamAt last year’s IPC APEX EXPO, former IPC Emerging Engineer Hannah Nelson had the opportunity to reflect on her inspiring journey into the world of engineering, from her education at Valparaiso University to her internship and her first job at Texas Instruments. From pivotal moments and the unexpected turns that helped shape her early career and passion for electrical engineering, her story highlights the importance of interdisciplinary collaboration, taking opportunities that arise early on, finding confidence in one's voice, and the rewards of pursuing one's passions within the engineering field.