PSYONIC: The world's first touch-sensing bionic hand trains industrial robots

[00:00:00]It might sound like science fiction, but US tech company Psyonic has developed a bionic hand that's being used to train robots. Our reporter Michael Morilia spoke to Psyonic CEO to find out how it all works.

[00:00:14]>> So I'm using these two buttons to move it right now, but that's the equivalent of having muscle sensors. So if you're missing your hand, we can place muscle sensors on your arm, and then you can use that to open and close the hand in different ways. So I can give you like a thumbs up, right? I can switch that over and make a pinch, I can go back and forth like that. But what's um especially interesting about this is that we have up to 30 touch sensors throughout the entire hand. So one on the fingertip, one on the finger pad, two on the outside, two on the inside.

[00:00:42]And our users can feel that through a vibration. So when they pick something up on the table, um they can actually feel the amount of force because of the touch sensors that are in the hand and the vibration that they feel on their skin. Our hand currently has six different uh movements that it can do.

[00:00:58]So it can uh flex and extend all five fingers and then rotate the thumb as well. So compared to like, you know, parallel jaw grippers that robots have been using for the last like 30, 40, 50 years, right? Um it's a lot more dextrous now. But the problem was is that you didn't know how to control all those movements in the hand because the the amount of compute you would need for that was way too expensive, way too complex. But with the breakthroughs that have come through with physical AI, it's unlocked this level of dexterity that now we can actually do all these more complicated tasks.

[00:01:32]>> Now you've collected data from the people who've actually used the bionic hand, and you'll share some of that data with the robotics firm ABB.

[00:01:41]How will that data help them to train their robots?

[00:01:45]>> Yeah, so when our humans are doing tasks, right? We can get information generated by the ability hand that I'm holding here. So for example, if I'm doing that pinch, we know exactly how much the fingers have moved, how much force the the the motors are producing as well as how much pressure is being applied on the fingertip right now. And what we can do is we can actually sync that to Meta Ray-Ban glasses, for example. And so while they're doing the task, we can actually see what that task is, and then they know exactly when they grab the object, how hard they're grabbing the object, and have it synced to what the object is from the camera data as well. So with ABB, we're actually taking the the teachings from what we've learned from our human users doing those same tasks and using that data to train AI models to have the robots do the exact same thing.

[00:02:39]>> I think this is really the crucial question. Will this partnership help reduce costs for people who really need these bionic hands?

[00:02:47]>> Yeah, absolutely. And And the thing is, there's more than 10 million people with hand amputations around the entire world, and less than 3% of of them have access to affordable rehabilitative care. And in order to reduce that disparity, by having a a beachhead market, right, that like the the robotic side, the volumes help reduce that cost so it can become like affordable for all these people across the entire world who need them.

[00:03:16]And so what we build for humans benefits robots in the sense that the the data can help train the robots to do all sorts of different things. But what we build for robots benefits humans because the volumes on those sides subsidize the cost for the humans, so that more human users can get access to affordable bionic limbs.

[00:03:34]>> Dr. Aydin Aktan, thanks so much for talking to us.

[00:03:37]>> Thank you for having me.