Robots have been taught to laugh at jokes to make them more human.
Researchers at Kyoto University in Japan are using artificial intelligence (AI) to train robots about appropriate laughter — and to differentiate between chuckles and chirps.
Writing in the journal Frontiers in Robotics and AI, they describe working with a robot named Erica with the hope of making interactions more natural.
“We think that one of the important functions of conversational AI is empathy,” said lead author Dr. Koji Inoue, an assistant professor at Kyoto University in the Department of Intelligence Science and Technology.
“Conversation is, of course, multimodal, not just responding correctly. So we decided that the only way a robot can empathize with users is to share their laughs, which you can do with a text-based chatbot. Can’t do with.
Creating a “shared laugh” model, the researchers used AI to help detect laughter, decide whether or not to laugh and what kind of laughter would be best.
Four short two- to three-minute conversations between real people and Erica were used to test the system, which performed well.
However, experts say more work remains to be done to create a natural state of laughter.
Dr Inoue said: “Robots really must have a distinct character, and we think they can show this through their interactive behaviours, such as laughter, eye gaze, gestures and speaking style.
“We don’t think this is an easy problem, and it may take more than 10 to 20 years before we can have a casual chat with a robot with a friend.”
Credit: www.independent.co.uk /