AI-powered surgical robot learns by watching

Editor's Note

Kinematics-based AI similar to the technology behind ChatGPT enabled a multi-armed robot to learn new surgical techniques by watching video of human surgeons, according to a November 12 report in Healthday.

“The robot is powered by the same AI that underpins ChatGPT, but instead of words and text, the program focuses on kinematics – a language that breaks down robotic motion into math,” the outlet reports, citing a news release from Johns Hopkins University. “After analyzing hundreds of surgical videos, the AI became as skillful as human doctors at performing a handful of key tasks.”

The research team, led by Axel Krieger and Ji Woong “Brian” Kim, equipped the AI with video footage from wrist-mounted cameras on da Vinci robotic arms, Healthday reports. By feeding the AI visual input alone, the system was able to interpret the necessary robotic actions autonomously, resulting in a robot that can carry out a range of critical tasks. Specifically, the AI was trained to manipulate a needle, lift tissue, and suture, learning these procedures within a few hundred demonstrations. The model demonstrated the ability to generalize its skills to new, previously unseen surgical environments. The John Hopkins researchers reportedly presented their findings at the Conference on Robot Learning in Munich, Germany.

According to Healthday, the robot’s adaptability and capacity for improvisation—for example, independently retrieving a dropped needle and continuing without additional programming—impressed researchers. Although the technology is still in early stages, it represents another step toward fully autonomous robotic assistance in the operating room.