Curiosity may have killed the cat, but will it make for a more intriguing robot? That’s the question researchers are looking to explore through a new initiative called “Curious Minded Machine” from Honda Research Institute USA.
“We wish to explore several questions in our work,” said Allen School professor and team leader Siddhartha Srinivasa, in a story from the UW. “What is curiosity? Can we build a rich mathematical model that makes a robot curious? Will a curious robot be accepted more? Will we be more tolerant of its mistakes?”
PREVIOUSLY: Amazon hires top UW computer science professor as new robotics director a year after he arrived from CMU
It seems that every few months robots, and robot dogs, are wowing us with their newfound physical capabilities. This is especially true if you pay attention to what the humanoid machine from Boston Dynamics is doing.
But creating robots that are more humanlike goes far beyond making one that can run up a flight of stairs or jump over a log.
“Our first step is to better understand curiosity in humans, starting from infants’ constant experimentation with their surroundings, to 4-year-olds asking why everything is the way it is, to adults’ interest in topics completely outside their professions,” assistant professor Maya Cakmak told UW News. “Humans are intrinsically rewarded by new information even when that information is not necessarily applicable, but curiosity has long-term benefits. We would like to give robots similar benefits for being curious.”
The hope is that curious robots will eventually be better at the jobs we task them with. Which should prove especially relevant to Srinivasa in his new job, as director of robotics at Amazon.
The UW will be joined in the effort by teams from the Massachusetts Institute of Technology and the University of Pennsylvania. After the three-year program, Honda Research Initiative will combine the work from all the teams to form the foundation for a future curious-minded robot.