Years ago, a robot arm that can peel a banana would’ve seemed like such a ludicrous notion, like something out of a sci-fi story.
But thanks to advancements in technology, scientists at the ISI Laboratory which is in the University of Tokyo, have done just that.
They have used AI learning technology in order to teach robots how to peel a banana. But what is most impressive is that they have managed to teach the robots how to do it gently enough so as to avoid smashing the fruit itself.
But why is this such a big deal? As researcher Heecheol Kim explained in the video below, “Handling soft fruit is tricky for robots, but after training with hours of data from a human operator, a machine learning algorithm developed the motor skills needed to peel a banana 57 percent of the time.”
Kim further added that they did so by developing a machine that uses a learning mimicry system in order to train the robots in tasks related to manual dexterity. While the machine is helpful, there is still a requirement for human training, which can take several hours.
Kim said, “First, a human operating the robot peeled hundreds of bananas, creating 811 minutes of demonstration data to train the robot to do it by itself. The task was divided into nine stages, from grasping the banana to picking it up off the table with one hand, grabbing the tip in the other hand, peeling it, then moving the banana so the rest of the skin can be removed.”
According to the footage shown, it is clear to see that when tasked with peeling, the robots enter a reactive mode. They actually hold the fruit at better angels that allow them to complete the task without harming the banana.
Kim added, “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.”
Check out the precision of the banana peeling robot arm in the video below:
What do you think of technology’s advancements? Would you want a robot arm that can peel bananas for you? Let us know!