Fully automated surgical robots are gradually becoming a reality.

Researchers have made a true breakthrough by introducing a surgical robot training system based on mimicry learning. This achievement marks a significant milestone, opening up limitless possibilities for the application of robots in the medical field and promising a revolution in surgery.

A robot underwent intensive training, learning from thousands of hours of video recordings of surgical procedures performed by leading experts. Thanks to advanced machine learning algorithms, the robot was able to simulate and perform surgical procedures with astonishing accuracy and dexterity, gradually approaching the level of a real surgeon.

The successful application of imitation learning methods in training surgical robots has created a significant breakthrough. Instead of having to meticulously program each movement, robots can now learn and emulate surgical skills from leading experts, leading to greater efficiency and accuracy in surgeries.

Researchers say this achievement brings us closer to a future where surgical robots can automatically perform complex surgeries without direct intervention from doctors. This is a significant step forward, opening up limitless possibilities for the application of robots in the medical field.

The groundbreaking findings of a research team from Johns Hopkins University and Stanford University in the US will be presented at the Robotics Learning Conference in Munich, Germany, this weekend. This event is considered one of the leading forums on artificial intelligence (AI), and their research results promise to attract significant attention from the international scientific community.

"What's really impressive is that we just provided the model with image data from the camera, and it was able to automatically predict the entire complex sequence of movements the robot needed to perform during surgery," shared Professor Axel Krieger, Associate Professor of Mechanical Engineering at Johns Hopkins University (USA).

Professor Krieger added: "We believe this is a significant step towards a new field in medical robotics. This model is very good at learning things we haven't taught it. For example, if it drops a needle, it will automatically pick it up and continue. This is not something I taught it to do."

The research team successfully trained the Da Vinci robotic surgical system to proficiently perform three basic surgical skills: needle manipulation, tissue lifting, and suturing. Surprisingly, the robot achieved performance comparable to that of professional surgeons.

The Da Vinci surgical system, with over 7,000 units in use globally, has become a popular robotic surgery platform. Having over 50,000 doctors trained to use the system has created a massive database of surgical cases, providing an invaluable resource for robots to learn from and improve their skills.

Unlike ChatGPT, which uses natural language, this model leverages machine learning architecture to analyze and predict robot movement based on kinematic language. Instead of processing text, this model works with data on the robot's position, velocity, acceleration, and other technical parameters.

Researchers collected a large amount of video data from hundreds of real-life surgeries, recorded directly from the perspective of the Da Vinci robotic arm. This dataset includes detailed images of complex surgical procedures, providing a valuable source of information for training the model.

Although the Da Vinci surgical system is widely used, previous studies have shown that it often encounters accuracy issues during surgical procedures. The research team has found a new approach to address this problem by focusing on training the model to perform relative movements rather than absolute actions. This enhances the robot's accuracy and flexibility during surgery.

"All we need is image data, and then this AI system will figure out the appropriate action," said lead author Ji Woong "Brian" Kim, a postdoctoral researcher at Johns Hopkins University.

Ji Woong "Brian" Kim added: "We found that even with several hundred simulations, the model can still learn the process and generalize to new environments it has never encountered before."

Researchers believe this model could revolutionize surgical robot training. Instead of manually programming each surgery, the model can quickly train a robot to perform any procedure, from simple to complex operations. By applying a mimicry learning method, the robot can learn from surgical experts and perform entire surgeries automatically.