To test their AI 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 put it somewhere else. Without AI, they might succeed about once or twice out of 10 times. When the AI assistant was turned on, their success rate jumped to 80 or 90 percent. The AI also reduced the participants' cognitive load, meaning they had to concentrate less on using their hands.
But we are still far from seamlessly integrating machines with the human body.
Into the wild
“The next step is to actually bring this system into the real world and have someone use it in their home,” Trout says. So far, the effectiveness of the AI bionic arm has been assessed in controlled laboratory conditions, working with settings and objects that the team has specifically chosen or designed.
“I want to make a disclaimer here: this hand is not as dexterous or as easy to control as a natural, intact limb,” George warns. He believes that every small step forward in prosthetics allows amputees to perform more tasks in everyday life. However, to reach the technological level of Star Wars or Cyberpunk, where bionic prosthetics are as good or better than natural limbs, we will need more than just incremental changes.
Trout says we're almost there in robotics. “These prosthetics are really dexterous, with a high degree of freedom,” Trout says, “but there’s no good way to control them.” Part of this comes down to the problem of getting information from the users themselves. “Skin surface electromyography is very noisy, so improving this interface with things like internal electromyography or using neural implants could really improve the algorithms we already have,” Trout states. That is why the team is currently working on neural interface technologies and looking for industry partners.
“The goal is to combine all these approaches into one device,” says George. “We want to create a robotic arm with artificial intelligence and a neural interface, working with a company that will bring it to market for larger clinical trials.”
Nature Communications, 2025. DOI: 10.1038/s41467-025-65965-9
