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 pick up an egg from a plate and place it elsewhere. Without the AI, they might succeed about once or twice in 10 attempts. With the AI assistant enabled, their success rate increased to 80 or 90 percent. The AI also reduced participants’ cognitive load, meaning they had to focus less on hand work.
But we are still far from seamless integration of machines with the human body.
In nature
“The next step is to actually take this system into the real world and have someone use it in their home,” says Trout. So far, the performance of the AI bionic hand has been evaluated in controlled laboratory conditions, working with parameters and objects specifically chosen or designed by the team.
“I want to make it clear here that this hand is not as dexterous or easy to control as a natural, intact limb,” George warns. He believes that every little advance we make in prosthetics allows amputees to accomplish more tasks in their daily lives. However, to reach the Star Wars or Cyberpunk level of technology where bionic prosthetics are just as good, or even better, than natural limbs, we will need more than just incremental changes.
Trout says we’re almost there when it comes to robotics. “These prosthetics are really dexterous, with a high degree of freedom,” says Trout, “but there is no good way to control them.” Part of this is the challenge of getting information in and out of users themselves. “Skin surface electromyography is very noisy, so improving that 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 of 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 Communications, 2025. DOI: 10.1038/s41467-025-65965-9
