Every now and then something in the tech realm makes our eyes light up with excitement. Over the weekend, this happened while watching a video of a robot peeling a banana.
“Oh it’s just a robot peeling a banana, there’s nothing exciting about that,” you might think to yourself. Well, there’s a tonne of reasons why this seemingly simply concept is actually so freaking cool.
The act of peeling a banana without squashing it requires some pretty exceptional dexterity. As Reuters points out, this dual-armed machine is only successful 57 per cent of the time, BUT banana peeling points to a future where robots undertake more subtle operations than what they’re currently used for. It’s learning and, as with everything, the tech can only get better.
In a video uploaded by New Scientist, you can see the insane precision the robot peels the banana with.
Researchers from the University of Tokyo have developed a machine-learning system that powers the robot. The video shows the robot’s arms, each equipped with two ‘fingers’, gently rotate the banana and peel it back. It then manages the dexterity to move the banana so the rest of the peel can be, well, peeled.
To make this feat happen, the researchers manually controlled the robot for 811 minutes and peeled hundreds of bananas, giving the bot the opportunity to learn the art of peeling for itself.
Handling soft fruit is of course a challenge for robots, which often lack the dexterity and nuanced touch to process items without destroying them. The uneven shape of fruit, as New Scientist points out, can also mess with the algorithms, or the robot’s ‘brains’.
While still undergoing more testing, the researchers believe this robot training method can teach robots to do different simple “human” tasks. They hope the better-trained robots can alleviate Japan’s labour shortage problems, for example at food processing factories that are highly dependent on human labour. The possibilities this opens up for everything from medicine and healthcare (and helping a human with limited mobility) through to performing fiddly tasks in an assembly line, from there are incredible.