Watch this robot as it learns to stitch up wounds

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

“From a robotics perspective, this is a really challenging 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 also have a hard time modeling how “deformable” objects, like skin and thread, react when poked and prodded. Unlike transferring a needle from one human hand to another, moving a needle between robotic arms is an immense challenge in dexterity.

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

Though we’re a long way from seeing these sorts of robots used in operating rooms to sew up wounds and organs on their own, the goal of automating part of the suturing process holds serious medical potential, says Danyal Fer, a physician and researcher on the project. 

“There’s a lot of work within a surgery,” Fer says, “and oftentimes, suturing is the last task you have to do.” That means doctors are more likely to be fatigued when doing stitches, and if they don’t close the wound properly, it can mean a longer healing time and a host of other complications. Because suturing is also a fairly repetitive task, Goldberg and Fer saw it as a good candidate for automation.

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

That’s an open question, since the success of the robot comes with caveats. The machine made a record of six complete stitches before a human had to intervene, but it could only complete an average of about three across the trials. The test wound was limited to two dimensions, unlike a wound on a rounded part of the body like the elbow or knuckle. Also, the robot has only been tested on “phantoms,” a sort of fake skin used in medical training settings—not on organ tissue or animal skin.