Though many doctors today get help from robots for procedures starting from hernia repairs to coronary bypasses, those are used to help surgeons, not replace them. This latest research marks progress toward robots that may operate more autonomously on very intricate, complicated tasks like suturing. The teachings learned in its development is also useful in other fields of robotics.

“From a robotics perspective, this can be a really difficult manipulation task,” says Ken Goldberg, a researcher at UC Berkeley and director of the lab that worked on the robot.  

One issue is that shiny or reflective objects like needles can throw off a robot’s image sensors. Computers even have a tough time modeling how “deformable” objects, like skin and thread, react when poked and prodded. Unlike transferring a needle from one human hand to a different, moving a needle between robotic arms is an immense challenge in dexterity.

The robot uses a pair of cameras to absorb its surroundings. Then, having been trained on a neural network, it’s capable of discover where the needle is and use a motion controller to plan all six motions involved in making a stitch. 

Though we’re a great distance from seeing these types of robots utilized in operating rooms to stitch up wounds and organs on their very own, the goal of automating a part of the suturing process holds serious medical potential, says Danyal Fer, a physician and researcher on the project. 

“There’s loads of work inside a surgery,” Fer says, “and oftentimes, suturing is the last task you’ve to do.” Meaning doctors usually tend to be fatigued when doing stitches, and in the event that they don’t close the wound properly, it will possibly mean an extended healing time and a bunch of other complications. Because suturing can be a reasonably repetitive task, Goldberg and Fer saw it as a very good candidate for automation.

“Can we show that we actually recuperate patient outcomes?” Goldberg says. “It’s convenient for the doctor, yes, but most significantly, does this lead to raised sutures, faster healing, and fewer scarring?”

That’s an open query, for the reason that success of the robot comes with caveats. The machine made a record of six complete stitches before a human needed to intervene, but it surely could only complete a median of about three across the trials. The test wound was limited to 2 dimensions, unlike a wound on a rounded a part of the body just like the elbow or knuckle. Also, the robot has only been tested on “phantoms,” a type of fake skin utilized in medical training settings—not on organ tissue or animal skin.