German Researchers Create Bot with Attitude to Improve Communications

In the near future, we may not have SIRI to kick around anymore. That’s because researchers at the University of Augsburg, Germany have created “Irony Man,” a robot that responds with a slight edge to its witty repartee with humans.

According to tests with a dozen students, talking to the robot was more enjoyable than with the typical virtual assistant voicebot. According to a story in New Scientist, the robot can interact with the opposite meaning of what it intends. For instance:

In a conversation about the weather, the phrase “I hate raining. I usually have a bad mood when it rains” becomes “Super! I utterly love raining”, with, say, unusual elongated stress on the word utterly and a smile. …Think of a robot in the role of a lifestyle advisor that feels the user should be more active and has to convey this message without appearing rude,” said engineer Elisabeth André. “Presented with a message like “traffic is frustrating,” Irony Man would say “I love being stuck here,” emphasizing the word “love.”

The robot, however, isn’t quite smart enough to know when to hold off on the irony, because it can’t read people. So it could wind up being more irritating than not.

A story on, explores the robot’s flaws further. Described as less than a foot tall, with a “goofy” look, Irony Man is meant to improve the experience humans have interacting with robots:

“That’s right: Now there’s a robot who can sass you as well as any teenager.”

The research presented at the International Conference on Autonomous Agents and Multiagent Systems in Montreal is the first step toward creating a more nuanced form of communication with personal assistants.

Irony Man makes facial expressions to emphasize his points. (credit: University of Augsburg)