If you pull apart all of the tech bro spin, the idea behind the metaverse is to allow interaction in a virtual world between two or more people when they can’t be physically present together. It opens the possibility of ‘being’ with someone over the other side of the world, or even in a different LGA, if we think back to lockdowns last year.
As detailed in Scientific American, Stanford University graduate student, Millie Salvato, alongside colleagues of hers, have used machine learning to recreate touch.
For a new study detailed in IEEE Transactions on Haptics, Salvato and her team demonstrated a wearable sleeve that can simulate human touch, and convey abstract social messages sent electronically.
During social interactions, people use auditory, visual and haptic cues to convey their thoughts, emotions and intentions. But, due to weight, energy and other hardware constraints, it is difficult to create devices that completely capture the complexity of human touch.
The study explores whether a sparse representation of human touch is sufficient to convey social touch signals.
To test this, Salvato and her colleagues collected a dataset of social touch interactions (from 37 people, a total of 661 touch movements such as squeezes, strokes, shakes and pokes) using a soft wearable pressure sensor array. They then developed an algorithm to map recorded data to an array of actuators, then applied that algorithm to create signals that drive a number of ‘normal’ indentation actuators placed on the arm.
The final step was programming a wearable sleeve to simulate these movements using eight embedded disks that vibrate when electronically signalled.
“Using this wearable, low-resolution, low-force device, we find that users are able to distinguish the intended social meaning, and compare performance to results based on direct human touch,” the study explains.
“It doesn’t feel like an actual human hand … but it doesn’t feel like these discrete motions either,” Salvato is quoted as saying. “It feels nice, honestly.”
According to the report, 30 study participants correctly matched the simulated touches to the six scenarios 45 per cent of the time. While this doesn’t seem too good, it actually is – it’s about 2.7 times more than by chance.
“As online communication becomes more prevalent, such systems to convey haptic signals could allow for improved distant socialising and empathetic remote human-human interaction,” the study explains.
It might seem a little creepy, but for those of us longing to cuddle a loved one far away, the possibilities for this tech are incredible.
The Cheapest NBN 50 Plans
It’s the most popular NBN speed in Australia for a reason. Here are the cheapest plans available.