Robots haven’t taken over the world just yet and may still be a product of sci-fi movies, but there’s no denying the fact that humanity will be more exposed to them over the next few decades.
Although machines are constantly evolving and picking up new skills, many people remain sceptical of the role they’re going to play in the future. And getting humans to like them is challenging.
However, a team of scientists may have found a solution. They claim that by creating robots that are awkward and clumsy, humans will feel more confident around them.
Flawed robots win
That may sound bizarre, but scientists from the Center for Human-Computer Interaction, University of Salzburg, Austria, Bristol Robotics Laboratory, University of the West of England, UK, and the Center for Technology Experience, Austrian Institute of Technology, claim they have found proof that people are more likely to prefer and get on with robots if they behave awkwardly and make mistakes regularly – much like many of us humans.
This research, published in the Frontiers in Robotics and AI journal, shows that humans aren’t convinced by robots that act flawlessly. In fact, this is something people can fear. And there have been countless examples of imperfect robots.
Recently, a robot managed to escape from a research facility in Russia, and a security robot drowned itself in a fountain last month. Events like these hardly strike confidence in the hearts of the sceptics.
Mistakes are normal
Nicole Mirnig, who’s a PhD candidate at the Center for Human Computer Interaction at the University of Salzburg in Austria, said this research proves a theory that claims humans are more attractive if they make mistakes.
“Our results showed that the participants liked the faulty robot significantly more than the flawless one. This finding confirms the Pratfall Effect, which states that people’s attractiveness increases when they make a mistake,” she said.
During the experiment, the researchers encouraged robots to interact with humans and complete several LEGO building tasks. Following this, they asked the humans to rate the robots on their likability, anthropomorphism and perceived intelligence.
The scientists took care to note the participants’ reactions when the robots made mistakes. When mistakes were made, laughter was the most common emotion elicited from the candidates, much like humans do when we see our friends and family do something clumsy.
Mastering social intelligence
However, while robots making mistakes aren’t exactly suitable for practical tasks, the researchers claim that they could be taught to master these errors to develop social intelligence skills. At the end of the day, humans aren’t perfect, either, but maybe robots can learn from their mistakes. Just like we do.
“Specifically exploring erroneous instances of interaction could be useful to further refine the quality of human-robotic interaction,” Mirnig added.
“For example, a robot that understands that there is a problem in the interaction by correctly interpreting the user’s social signals could let the user know that it understands the problem and actively apply error recovery strategies.”