Robots, in part because they have infinite patience, can make excellent teachers. And Sidney D?Mello, a University of Notre Dame assistant professor in psychology along with his colleagues, have devised a learning program called Affective AutoTutor that could one day make robot teachers even better at the task.
Designed to work via a laptop ? we?re assuming it could be adapted for a tablet toting robot ? the program can not only gauge a student?s knowledge, it can use visual cues to determine the person?s emotional state during learning sessions, according to the Notre Dame News.
The actual learning takes place via natural language. And the program can even synthesize ?emotions via the content of its verbal responses, speech intonation and facial expressions of an animated teacher,? changing its own synthesized emotional state so as to best accommodate the learner.
Used by over 1,000 students, the program was able to improve their knowledge by roughly one grade level, nearly equaling what expert human tutors are able to achieve.
The work by D’Mello and his colleagues parallels research occurring many places elsewhere. Scientists at Computer Vision Center in the Autonomous University of Barcelona in Spain and their colleagues at the Department of Psychology at Princeton University, for example, have devised a program that can determine moods via facial expressions. Using machine learning , the program was tested to see how well it could identify ?9 facial trait judgments (attractive, competent, trustworthy, dominant, mean, frightening, extroverted, threatening, and likable), according to a news release from the online scientific library PLoS.
But the Notre Dame-led effort is significant because the program can adjust how it presents information based on the user?s emotional state, and as the Notre Dame News article noted that fact ?not only offers tremendous learning possibilities for students, but also redefines human-computer interaction.?
It?s not hard to imagine a day when robots, a future Apple OS, and many other intelligent devices from TVs to kids? toys to industrial robots, incorporate some form of the technology, making our dealings with machines more natural and more effective, while creating mammoth opportunities for companies able to work with and design novel uses for comparable programs.