The robot, trained through imitation learning similar to ChatGPT’s architecture, performs needle manipulation, tissue lifting, and suturing with human-level precision, the university’s research shows.
This breakthrough could potentially eliminate the need for complex programming and opens doors for innovative business solutions in medical training and implementation.
“It’s really magical to have this model and all we do is feed it camera input and it can predict the robotic movements needed for surgery,” said Axel Krieger, assistant professor at Johns Hopkins’ Department of Mechanical Engineering.
The team overcame the system’s inherent imprecision by training the model to perform relative movements instead of absolute actions. The robot demonstrated unexpected adaptability, such as automatically retrieving dropped needles without specific programming.
The ultimate goal is true autonomy in robotic surgery, where machines can perform complex surgeries without human help.
The advancement’s timing coincides with increasing demand for automation in medicine, including surgery. In 2021, around 644,000 robotic surgeries were performed in the US. By 2028, that number is expected to reach a million.
Success in this emerging field requires a deep understanding of both healthcare operations and AI capabilities, but entrepreneurs don’t necessarily need technical expertise in robotics. Instead, it might be wise to focus on solving practical implementation challenges and bridging knowledge gaps. In other words, it’s about making advanced technology accessible and practical for medical professionals.
