Anyone who has shared a laugh with a friend knows how deeply bonding humor can be, so it makes sense to consider our future robot companions they have a better chance of winning our trust and affection if they can laugh with us. But only because a a robot tells jokes doesn’t mean he can answer them appropriately. Did the comment call for a polite robot giggle or a total bot laugh? The right answer can mean the difference between an affordable android and a metal bastard.
That’s why Japanese researchers are trying to teach humorless robot geeks to laugh at the right time and in the right way. It turns out that teaching an AI to laugh isn’t as simple as teaching it to respond to a desperate plea on the phone tree to cancel a subscription. “Systems that try to mimic everyday conversation still struggle with knowing when to laugh,” it says study published Thursday in the journal Frontiers in Robotics and AI.
Erica the humanoid robot is in the lab and is getting a sense of humor.
Osaka University, ATR
The study details the team’s research into developing an AI conversational system focused on shared laughter to make chatter between humans and robots more natural. They envision it being integrated into existing conversational software for robots and agents that are already learning emotion detection and dealing with unlimited complexity like vague human commands.
“We think one of the important functions of conversational AI is empathy,” Koji Inoue, assistant professor of computer science at Japan’s Kyoto University and co-author of the study, said in a statement. “Conversation is, of course, multimodal, not just answering correctly. So we decided that one way the robot could empathize with users is to share their laughter.”
The key is that the system not only recognizes the laugh, but also decides whether to laugh back and then chooses the right type of laugh for the occasion. “The most significant result of this paper is that we have shown how we can combine all three tasks in one robot,” Inoue said. “We believe that this type of combined system is necessary for proper laughter behavior, not just laughter detection and response.”
To collect training data on the frequency and types of laughter shared, the team tapped Erika, an advanced humanoid robot designed by Japanese scientists Hiroshi Ishiguro and Kohei Ogawa as a platform for studying human-robot interaction. Erica can understand natural language, has a synthesized human voice, and can blink and move her eyes when listening to people talk about their problems.
The researchers recorded dialogue between students at Kyoto University, who took turns talking to Erika face-to-face, while amateur actresses in another room controlled the bot via a microphone. The scientists chose this setting knowing that there would naturally be differences between how people talk to each other and how they talk to robots, even those controlled by another human.
“We wanted, as much as possible, the laughter model to be trained under conditions similar to real human-robot interaction,” Kyoto University researcher Divesh Lala, another co-author of the study, told me.
On the left, a man talks to the robot Erica, who is controlled from a separate room by an actress.
Kyoto University
Based on the interactions, the researchers created four short audio dialogues between humans and Erica, who was programmed to respond to conversations with varying levels of laughter, from none to frequent laughter in response to her human conversational friends. The volunteers then rated these interludes on empathy, naturalness, human-likeness, and understanding. Shared laughter scenarios performed better than those in which Erica never laughed or laughed whenever she detected human laughter without using the other two context and response filtering subsystems.
Kyoto University researchers have already programmed their common laughter system into robots other than Erica, although they say a humanoid howl may still sound more natural. Indeed, even as robots become more realistic, sometimes disturbingroboticists recognize that infusing them with their own distinctly human traits poses challenges that go beyond coding.
“It may be more than 10 to 20 years before we can finally have a casual conversation with a robot like we would with a friend,” Inoue said
Needless to say, Erica isn’t ready for the standing round just yet. But it’s intriguing to think that the day may soon come when you’ll actually feel like she gets your jokes.
https://www.cnet.com/science/scientists-enroll-humorless-robots-in-laughter-class/#ftag=CADf328eec