University of Tokyo engineers have built a machine-learning system that enables a robot to peel a banana without mushing it. Demo video below! The robot learned to do the task on its own after almost 14 hours of practice under human control. As of now, the robot can peel the banana successfully about 57 percent of the time, which is actually a huge accomplishment. It takes around three minutes per banana. From New Scientist:
For broad movements that are unlikely to damage the banana, the machine-learning model maps out a trajectory, mimicking what a human does without much thinking. But when the arms are required to precisely manipulate the banana, the system switches to a reactive approach, where it responds to unexpected changes in its environment[…]
[Researcher Heecheol Kim] Kim says his approach is data-efficient because it uses 13 hours of training data rather than hundreds or thousands of hours. "It still requires quite a lot of expensive GPUs [graphics processing units], but by using our structure, we can reduce the large amount of computation [required]," he says.
