To test their AI-powered hand, the team asked intact and amputee participants to manipulate fragile objects: pick up a paper cup and drink from it, or take an egg from a plate and put it somewhere else. Without the AI, they might succeed about once or twice in ten attempts. With the AI assistant enabled, their success rate increased to 80 to 90 percent. The AI also reduced the participants' cognitive load, allowing them to focus less on making the hand work.
But we are still far from seamless integration of machines with the human body.
Into the wilderness
“The next step is to actually bring this system into the real world and have someone use it at home,” Trout says. Until now, the performance of the AI bionic hand has been assessed under controlled laboratory conditions, working with settings and objects that the team specifically chose or designed.
“I would like to make a caveat here that this hand is not as dexterous or easy to control as a natural, intact limb,” George warns. He thinks that every small step we make in prosthetics will allow amputees to perform more tasks in their daily lives. But to reach the level of technology of Star Wars or Cyberpunk, where bionic prosthetics are as good or better than natural limbs, we need more than just incremental changes.
Trout says we're almost there in robotics. “These prosthetics are very useful, with a high degree of freedom,” says Trout, “but there is no good way to control them.” Part of this comes down to the challenge of getting the information in and out of the users themselves. “Skin surface electromyography is noisy, so improving this interface with things like internal electromyography or using neural implants can really improve the algorithms we already have,” Trout argued. This is why the team is currently working on neural interface technologies and looking for industrial partners.
“The goal is to combine all these approaches in one device,” says George. “We want to build an AI-powered robotic hand with a neural interface, in collaboration with a company that would commercialize it in larger clinical trials.”
Nature communication, 2025. DOI: 10.1038/s41467-025-65965-9
