‘BEST LEARNERS ON THE PLANET’
In the second experiment, the team allowed a robot to experiment with pushing or picking up different objects and moving them around a tabletop. The robot used that model to imitate a human who moved objects around or cleared everything off the tabletop. Rather than rigidly mimicking the human action each time, the robot sometimes used different means to achieve the same ends.
“If the human pushes an object to a new location, it may be easier and more reliable for a robot with a gripper to pick it up to move it there rather than push it,” says lead author Michael Jae-Yoon Chung, a doctoral student in computer science and engineering. “But that requires knowing what the goal is, which is a hard problem in robotics and which our paper tries to address.”
Though the initial experiments involved learning how to infer goals and imitate simple behaviors, the team plans to explore how such a model can help robots learn more complicated tasks.
“Babies learn through their own play and by watching others,” says Meltzoff, “and they are the best learners on the planet—why not design robots that learn as effortlessly as a child?”
The Office of Naval Research, National Science Foundation and Intel funded the work.
Republished from Futurity.org under the Creative Commons Attribution 4.0 International license with a new headline and featured image, and some links to additional articles removed.