A DVRK-based Framework for Surgical Subtask Automation

Abstract

Robotic assistance is becoming a standard in Minimally Invasive Surgery.
\nDespite its clinical benefits and technical potential, surgeons still have to perform manu-
\nally a number of monotonous and time-consuming surgical subtasks, like knot-tying or
\nblunt dissection. Many believe that the next bold step in the advancement of robotic
\nsurgery is the automation of such subtasks. Partial automation can reduce the cogni-
\ntive load on surgeons, and support them in paying more attention to the critical elements
\nof the surgical workflow. Our aim was to develop a software framework to ease and
\nhasten the automation of surgical subtasks. This framework was built alongside the Da
\nVinci Research Kit (DVRK), while it can be ported onto other robotic platforms, since
\nit is based on the Robot Operating System (ROS). The software includes both stereo
\nvision-based and hierarchical motion planning, with a wide palette of often used surgi-
\ncal gestures—such as grasping, cutting or soft tissue manipulation—as building blocks to
\nsupport the high-level implementation of autonomous surgical subtask execution routines.
\nThis open-source surgical automation framework—named irob-saf—is available at
\nhttps://github.com/ABC-iRobotics/irob-saf.