|NTT Corporation is now working in making robots more attractive to humans / Photo by: Lombroso via Wikimeda Commons|
Yasunori Ozaki, a researcher at NTT Corporation, is part of an industry-wide effort to make robots friendlier and attract more passersby’s attention in a way that is neither intrusive nor might make people feel uncomfortable.
Ozaki, who talked to TechXplore about his research, said he was inspired to incorporate the methods of barkers in a marketplace. These barkers are those who encourage people to eat at or at least checkout restaurants and stores with services that people could choose from. By observing them, he noticed that most of the approach that these barkers do depend on who they perceive as someone who is interested in the items for sale or the services offered.
Although robots are far from being able to determine interest as well as humans can, Ozaki is at least working on equipping robots with the training needed to understand people’s interests. Ozaki then worked with that goal and found a way to program robots to be capable enough to adapt their mannerism to a situation.
This will allow them to be better in interacting with humans, as they will then have the necessary information to discern which are well and truly interested in the advertisement.
There are only really two ways that a person might react to being called: respond accordingly by approaching or ignore it because of feelings of discomfort. So that the latter scenario doesn’t happen, Ozaki built the robots with sensors on their backs that help them determine whether a potential customer’s reaction is of interest or repulsion, thereby prompting it to act accordingly to either.
"My method allows a robot to find combinations of actions that do not cause discomfort to passersby," Ozaki said. "Many researchers have examined user experience (UX), including discomfort, in human-robot interactions. However, they did not train robots based on this UX. I believe that we need to teach robots some manners related to UX and the human world. This would then allow the robot to tailor its actions to different situations and users, based on the manners it has acquired."