In a major development in surgical robotics, researchers at Johns Hopkins University have announced that an autonomous robot successfully performed a complex portion of a gallbladder removal procedure on a lifelike model without human control. The breakthrough, published this week in Science Robotics, marks the first time a robot has demonstrated real-time decision-making and adaptability in a surgical setting comparable to a trained human surgeon.
The robot, named Surgical Robot Transformer-Hierarchy (SRT-H), was able to carry out 17 sequential surgical tasks, including identifying ducts and arteries, applying clips, and cutting tissue, with what researchers described as 100% accuracy. Unlike previous systems that relied on rigid pre-programmed instructions, SRT-H was trained using a machine learning model similar to the one powering ChatGPT. It learned by watching video footage of human surgeons performing the procedure on pig cadavers, aided by descriptive captions.
“This advancement moves us from robots that can execute specific surgical tasks to robots that truly understand surgical procedures,” said Axel Krieger, a medical roboticist at Johns Hopkins and senior author of the study. “This is a critical distinction that brings us significantly closer to clinically viable autonomous surgical systems that can work in the messy, unpredictable reality of actual patient care.”
The robot responded to spoken instructions such as “grab the gallbladder head” or “move the left arm a bit to the left,” adjusting its actions in real time and learning from verbal corrections. The system was also tested in scenarios with altered visual conditions, such as the introduction of blood-like dyes and changes to starting position, and maintained high performance throughout.
Lead author Ji Woong “Brian” Kim, a former postdoctoral researcher at Johns Hopkins now with Stanford University, said the technology overcomes several key barriers in surgical automation. “Our work shows that AI models can be made reliable enough for surgical autonomy—something that once felt far-off but is now demonstrably viable,” Kim said.
The team previously developed the Smart Tissue Autonomous Robot (STAR), which performed the first autonomous robotic surgery on a live pig in 2022. However, that system operated under tightly controlled conditions. In contrast, SRT-H can adapt to a variety of anatomical differences and surgical challenges.
The study suggests a potential future in which autonomous robotic systems could assist or perform surgeries in emergency situations, underserved regions, or locations lacking skilled surgeons. Johns Hopkins researchers plan to expand the system to other types of surgeries and eventually aim for full procedure automation.
The full findings are available in Science Robotics.
Your support brings the truth to the world.
Catholic Online News exists because of donors like you. We are 100% funded by people who believe the world deserves real, uncensored news rooted in faith and truth — not corporate agendas. Your gift ensures millions can continue to access the news they can trust — stories that defend life, faith, family, and freedom.
When truth is silenced, your support speaks louder.
