Current methods of guiding flexible surgical robots within the human body are often expensive and require exposure to radiation. Engineers at the University of California San Diego said they have developed an easy-to-use system to track the location of flexible medical robots that performs as well as current state-of-the-art methods but is much less costly and does not involve radiation.

The system was developed by Tania Morimoto, a professor of mechanical engineering at the Jacobs School of Engineering at UC San Diego, and mechanical engineering Ph.D. student Connor Watson. Their findings were published in the April 2020 issue of IEEE Robotics and Automation Letters.

Flexible medical robots can minimize impact

“Continuum medical robots work really well in highly constrained environments inside the body,” Morimoto said. “They’re inherently safer and more compliant than rigid tools. But it becomes a lot harder to track their location and their shape inside the body. And so if we are able track them more easily, that would be a great benefit both to patients and surgeons.”

The researchers embedded a magnet in the tip of a flexible medical robot that can be used in delicate places inside the body, such as arterial passages in the brain.

“We worked with a growing robot, which is a robot made of a very thin nylon that we invert, almost like a sock, and pressurize with a fluid, which causes the robot to grow,” Watson said. Because the surgical robot is soft and moves by growing, it has very little impact on its surroundings, making it ideal for use in medical settings.

Magnetic localization works like GPS

The researchers then used existing magnet localization methods, which work very much like GPS, to develop a computer model that predicts the robot’s location. GPS satellites ping smartphones and based on how long it takes for the signal to arrive, the GPS receiver in the smartphone can determine where the cell phone is.

Similarly, researchers know how strong the magnetic field should be around the magnet embedded in the flexible medical robot. They rely on four sensors that are carefully spaced around the area where the robot operates to measure the magnetic field strength. Based on how strong the field is, they are able to determine where the tip of the robot is.

The whole system, including the robot, magnets, and magnet localization setup, costs only around $100.

Neural network improves localization

Morimoto and Watson then trained a neural network to learn the difference between what the sensors were reading and what the model said the sensors should be reading. As a result, they improved localization accuracy to track the tip of the flexible medical robot.

“Ideally, we are hoping that our localization tools can help improve these kinds of growing robot technologies,” said Morimoto. “We want to push this research forward so that we can test our system in a clinical setting and eventually translate it into clinical use.”

About the author

Ioana Patringenaru is associate media relations director at the Jacobs School of Engineering at UC San Diego.