The team behind the laughing robot, which is called Erica, say that the system could improve natural conversations between people and AI systems.
“We think that one of the important functions of conversational AI is empathy,” said Dr Koji Inoue, of Kyoto University, the lead author of the research, published in Frontiers in Robotics and AI. “So we decided that one way a robot can empathise with users is to share their laughter.”
Inoue and his colleagues have set out to teach their AI system the art of conversational laughter. They gathered training data from more than 80 speed-dating dialogues between male university students and the robot, who was initially teleoperated by four female amateur actors.
The dialogue data was annotated for solo laughs, social laughs (where humour isn’t involved, such as in polite or embarrassed laughter) and laughter of mirth. This data was then used to train a machine learning system to decide whether to laugh, and to choose the appropriate type.
It might feel socially awkward to mimic a small chuckle, but empathetic to join in with a hearty laugh. Based on the audio files, the algorithm learned the basic characteristics of social laughs, which tend to be more subdued, and mirthful laughs, with the aim of mirroring these in appropriate situations.
“Our biggest challenge in this work was identifying the actual cases of shared laughter, which isn’t easy because as you know, most laughter is actually not shared at all,” said Inoue. “We had to carefully categorise exactly which laughs we could use for our analysis and not just assume that any laugh can be responded to.”
The team tested out Erica’s “sense of humour” by creating four short dialogues for it to share with a person, integrating the new shared-laughter algorithm into existing conversation software. These were compared to scenarios where Erica didn’t laugh at all or emitted a social laugh every time she detected laughter.
The clips were played to 130 volunteers who rated the shared-laughter algorithm most favourably for empathy, naturalness, human-likeness and understanding.